Typology
operator:
and / or
Language
operator:
and / or
Date
operator:
and / or
Rights
operator:
and / or
2022
Other
Open Access
Deep Learning techniques for visual counting
Ciampi L
In this thesis, I investigated and enhanced Deep Learning (DL)-based techniques for the visual counting task, which automatically estimates the number of objects, such as people or vehicles, present in images and videos. Specifically, I tackled the problem related to the lack of data needed for training current DL-based solutions by exploiting synthetic data gathered from video games, employing Domain Adaptation strategies between different data distributions, and taking advantage of the redundant information characterizing datasets labeled by multiple annotators. Furthermore, I addressed the engineering challenges coming out of the adoption of DL-based techniques in environments with limited power resources, mainly due to the high computational budget the AI-based algorithms require.
Ciampi L
In this thesis, I investigated and enhanced Deep Learning (DL)-based techniques for the visual counting task, which automatically estimates the number of objects, such as people or vehicles, present in images and videos. Specifically, I tackled the problem related to the lack of data needed for training current DL-based solutions by exploiting synthetic data gathered from video games, employing Domain Adaptation strategies between different data distributions, and taking advantage of the redundant information characterizing datasets labeled by multiple annotators. Furthermore, I addressed the engineering challenges coming out of the adoption of DL-based techniques in environments with limited power resources, mainly due to the high computational budget the AI-based algorithms require.
See at:
etd.adm.unipi.it 
| CNR IRIS | ISTI Repository | CNR IRIS 
2023
Conference article
Open Access
CrowdSim2: an open synthetic benchmark for object detectors
Foszner P, Szczesna A, Ciampi L, Messina N, Cygan A, Bizon B, Cogiel M, Golba D, Macioszek E, Staniszewski M
Data scarcity has become one of the main obstacles to developing supervised models based on Artificial Intelligence in Computer Vision. Indeed, Deep Learning-based models systematically struggle when applied in new scenarios never seen during training and may not be adequately tested in non-ordinary yet crucial real-world situations. This paper presents and publicly releases CrowdSim2, a new synthetic collection of images suitable for people and vehicle detection gathered from a simulator based on the Unity graphical engine. It consists of thousands of images gathered from various synthetic scenarios resembling the real world, where we varied some factors of interest, such as the weather conditions and the number of objects in the scenes. The labels are automatically collected and consist of bounding boxes that precisely localize objects belonging to the two object classes, leaving out humans from the annotation pipeline. We exploited this new benchmark as a testing ground for some state-of-the-art detectors, showing that our simulated scenarios can be a valuable tool for measuring their performances in a controlled environment.DOI: 10.5220/0011692500003417
Project(s): AI4Media
Metrics:
Foszner P, Szczesna A, Ciampi L, Messina N, Cygan A, Bizon B, Cogiel M, Golba D, Macioszek E, Staniszewski M
Data scarcity has become one of the main obstacles to developing supervised models based on Artificial Intelligence in Computer Vision. Indeed, Deep Learning-based models systematically struggle when applied in new scenarios never seen during training and may not be adequately tested in non-ordinary yet crucial real-world situations. This paper presents and publicly releases CrowdSim2, a new synthetic collection of images suitable for people and vehicle detection gathered from a simulator based on the Unity graphical engine. It consists of thousands of images gathered from various synthetic scenarios resembling the real world, where we varied some factors of interest, such as the weather conditions and the number of objects in the scenes. The labels are automatically collected and consist of bounding boxes that precisely localize objects belonging to the two object classes, leaving out humans from the annotation pipeline. We exploited this new benchmark as a testing ground for some state-of-the-art detectors, showing that our simulated scenarios can be a valuable tool for measuring their performances in a controlled environment.DOI: 10.5220/0011692500003417
Project(s): AI4Media
Metrics:
See at:
CNR IRIS | ISTI Repository | www.scitepress.org | CNR IRIS | CNR IRIS
2023
Conference article
Open Access
Development of a realistic crowd simulation environment for fine-grained validation of people tracking methods
Foszner P, Szczesna A, Ciampi L, Messina N, Cygan A, Bizon B, Cogiel M, Golba D, Macioszek E, Staniszewski M
Generally, crowd datasets can be collected or generated from real or synthetic sources. Real data is generated by using infrastructure-based sensors (such as static cameras or other sensors). The use of simulation tools can significantly reduce the time required to generate scenario-specific crowd datasets, facilitate data-driven research, and next build functional machine learning models. The main goal of this work was to develop an extension of crowd simulation (named CrowdSim2) and prove its usability in the application of people-tracking algorithms. The simulator is developed using the very popular Unity 3D engine with particular emphasis on the aspects of realism in the environment, weather conditions, traffic, and the movement and models of individual agents. Finally, three methods of tracking were used to validate generated dataset: IOU-Tracker, Deep-Sort, and Deep-TAMA.DOI: 10.5220/0011691500003417
Project(s): AI4Media
Metrics:
Foszner P, Szczesna A, Ciampi L, Messina N, Cygan A, Bizon B, Cogiel M, Golba D, Macioszek E, Staniszewski M
Generally, crowd datasets can be collected or generated from real or synthetic sources. Real data is generated by using infrastructure-based sensors (such as static cameras or other sensors). The use of simulation tools can significantly reduce the time required to generate scenario-specific crowd datasets, facilitate data-driven research, and next build functional machine learning models. The main goal of this work was to develop an extension of crowd simulation (named CrowdSim2) and prove its usability in the application of people-tracking algorithms. The simulator is developed using the very popular Unity 3D engine with particular emphasis on the aspects of realism in the environment, weather conditions, traffic, and the movement and models of individual agents. Finally, three methods of tracking were used to validate generated dataset: IOU-Tracker, Deep-Sort, and Deep-TAMA.DOI: 10.5220/0011691500003417
Project(s): AI4Media
Metrics:
See at:
CNR IRIS | ISTI Repository | www.scitepress.org | CNR IRIS | CNR IRIS
2023
Conference article
Open Access
Unsupervised domain adaptation for video violence detection in the wild
Ciampi L, Santiago C, Costeira Jp, Falchi F Gennaro C, Amato G
Video violence detection is a subset of human action recognition aiming to detect violent behaviors in trimmed video clips. Current Computer Vision solutions based on Deep Learning approaches provide astonishing results. However, their success relies on large collections of labeled datasets for supervised learning to guarantee that they generalize well to diverse testing scenarios. Although plentiful annotated data may be available for some pre-specified domains, manual annotation is unfeasible for every ad-hoc target domain or task. As a result, in many real-world applications, there is a domain shift between the distributions of the train (source) and test (target) domains, causing a significant drop in performance at inference time. To tackle this problem, we propose an Unsupervised Domain Adaptation scheme for video violence detection based on single image classification that mitigates the domain gap between the two domains. We conduct experiments considering as the source labeled domain some datasets containing violent/non-violent clips in general contexts and, as the target domain, a collection of videos specific for detecting violent actions in public transport, showing that our proposed solution can improve the performance of the considered models.DOI: 10.5220/0011965300003497
Project(s): AI4Media
Metrics:
Ciampi L, Santiago C, Costeira Jp, Falchi F Gennaro C, Amato G
Video violence detection is a subset of human action recognition aiming to detect violent behaviors in trimmed video clips. Current Computer Vision solutions based on Deep Learning approaches provide astonishing results. However, their success relies on large collections of labeled datasets for supervised learning to guarantee that they generalize well to diverse testing scenarios. Although plentiful annotated data may be available for some pre-specified domains, manual annotation is unfeasible for every ad-hoc target domain or task. As a result, in many real-world applications, there is a domain shift between the distributions of the train (source) and test (target) domains, causing a significant drop in performance at inference time. To tackle this problem, we propose an Unsupervised Domain Adaptation scheme for video violence detection based on single image classification that mitigates the domain gap between the two domains. We conduct experiments considering as the source labeled domain some datasets containing violent/non-violent clips in general contexts and, as the target domain, a collection of videos specific for detecting violent actions in public transport, showing that our proposed solution can improve the performance of the considered models.DOI: 10.5220/0011965300003497
Project(s): AI4Media
Metrics:
See at:
CNR IRIS | ISTI Repository | www.scitepress.org | CNR IRIS | CNR IRIS
2019
Conference article
Open Access
Counting vehicles with deep learning in onboard UAV imagery
Amato G, Ciampi L, Falchi F, Gennaro C
The integration of mobile and ubiquitous computing with deep learning methods is a promising emerging trend that aims at moving the processing task closer to the data source rather than bringing the data to a central node. The advantages of this approach range from bandwidth reduction, high scalability, to high reliability, just to name a few. In this paper, we propose a real-time deep learning approach to automatically detect and count vehicles in videos taken from a UAV (Unmanned Aerial Vehicle). Our solution relies on a convolutional neural network-based model fine-tuned to the specific domain of applications that is able to precisely localize instances of the vehicles using a regression approach, straight from image pixels to bounding box coordinates, reasoning globally about the image when making predictions and implicitly encoding contextual information. A comprehensive experimental evaluation on real-world datasets shows that our approach results in state-of-the-art performances. Furthermore, our solution achieves real-time performances by running at a speed of 4 Frames Per Second on an NVIDIA Jetson TX2 board, showing the potentiality of this approach for real-time processing in UAVs.DOI: 10.1109/iscc47284.2019.8969620
Metrics:
Amato G, Ciampi L, Falchi F, Gennaro C
The integration of mobile and ubiquitous computing with deep learning methods is a promising emerging trend that aims at moving the processing task closer to the data source rather than bringing the data to a central node. The advantages of this approach range from bandwidth reduction, high scalability, to high reliability, just to name a few. In this paper, we propose a real-time deep learning approach to automatically detect and count vehicles in videos taken from a UAV (Unmanned Aerial Vehicle). Our solution relies on a convolutional neural network-based model fine-tuned to the specific domain of applications that is able to precisely localize instances of the vehicles using a regression approach, straight from image pixels to bounding box coordinates, reasoning globally about the image when making predictions and implicitly encoding contextual information. A comprehensive experimental evaluation on real-world datasets shows that our approach results in state-of-the-art performances. Furthermore, our solution achieves real-time performances by running at a speed of 4 Frames Per Second on an NVIDIA Jetson TX2 board, showing the potentiality of this approach for real-time processing in UAVs.DOI: 10.1109/iscc47284.2019.8969620
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | ISTI Repository | doi.org | CNR IRIS | CNR IRIS
2020
Conference article
Open Access
Unsupervised vehicle counting via multiple camera domain adaptation
Ciampi L, Santiago C, Costeira Jp, Gennaro C, Amato G
Monitoring vehicle flow in cities is a crucial issue to improve the urban environment and quality of life of citizens. Images are the best sensing modality to perceive and asses the flow of vehicles in large areas. Current technologies for vehicle counting in images hinge on large quantities of annotated data, preventing their scalability to city-scale as new cameras are added to the system. This is a recurrent problem when dealing with physical systems and a key research area in Machine Learning and AI. We propose and discuss a new methodology to design image-based vehicle density estimators with few labeled data via multiple camera domain adaptations.Source: CEUR WORKSHOP PROCEEDINGS, pp. 1-4. Online Conference, 04 September, 2020
Project(s): AI4EU
Ciampi L, Santiago C, Costeira Jp, Gennaro C, Amato G
Monitoring vehicle flow in cities is a crucial issue to improve the urban environment and quality of life of citizens. Images are the best sensing modality to perceive and asses the flow of vehicles in large areas. Current technologies for vehicle counting in images hinge on large quantities of annotated data, preventing their scalability to city-scale as new cameras are added to the system. This is a recurrent problem when dealing with physical systems and a key research area in Machine Learning and AI. We propose and discuss a new methodology to design image-based vehicle density estimators with few labeled data via multiple camera domain adaptations.Source: CEUR WORKSHOP PROCEEDINGS, pp. 1-4. Online Conference, 04 September, 2020
Project(s): AI4EU
See at:
ceur-ws.org | CNR IRIS | ISTI Repository | CNR IRIS
2021
Conference article
Open Access
Domain adaptation for traffic density estimation
Ciampi L, Santiago C, Costeira Jp, Gennaro C, Amato G
Convolutional Neural Networks have produced state-of-the-art results for a multitude of computer vision tasks under supervised learning. However, the crux of these methods is the need for a massive amount of labeled data to guarantee that they generalize well to diverse testing scenarios. In many real-world applications, there is indeed a large domain shift between the distributions of the train (source) and test (target) domains, leading to a significant drop in performance at inference time. Unsupervised Domain Adaptation (UDA) is a class of techniques that aims to mitigate this drawback without the need for labeled data in the target domain. This makes it particularly useful for the tasks in which acquiring new labeled data is very expensive, such as for semantic and instance segmentation. In this work, we propose an end-to-end CNN-based UDA algorithm for traffic density estimation and counting, based on adversarial learning in the output space. The density estimation is one of those tasks requiring per-pixel annotated labels and, therefore, needs a lot of human effort. We conduct experiments considering different types of domain shifts, and we make publicly available two new datasets for the vehicle counting task that were also used for our tests. One of them, the Grand Traffic Auto dataset, is a synthetic collection of images, obtained using the graphical engine of the Grand Theft Auto video game, automatically annotated with precise per-pixel labels. Experiments show a significant improvement using our UDA algorithm compared to the model's performance without domain adaptation.DOI: 10.5220/0010303401850195
Project(s): AI4EU, AI4Media
Metrics:
Ciampi L, Santiago C, Costeira Jp, Gennaro C, Amato G
Convolutional Neural Networks have produced state-of-the-art results for a multitude of computer vision tasks under supervised learning. However, the crux of these methods is the need for a massive amount of labeled data to guarantee that they generalize well to diverse testing scenarios. In many real-world applications, there is indeed a large domain shift between the distributions of the train (source) and test (target) domains, leading to a significant drop in performance at inference time. Unsupervised Domain Adaptation (UDA) is a class of techniques that aims to mitigate this drawback without the need for labeled data in the target domain. This makes it particularly useful for the tasks in which acquiring new labeled data is very expensive, such as for semantic and instance segmentation. In this work, we propose an end-to-end CNN-based UDA algorithm for traffic density estimation and counting, based on adversarial learning in the output space. The density estimation is one of those tasks requiring per-pixel annotated labels and, therefore, needs a lot of human effort. We conduct experiments considering different types of domain shifts, and we make publicly available two new datasets for the vehicle counting task that were also used for our tests. One of them, the Grand Traffic Auto dataset, is a synthetic collection of images, obtained using the graphical engine of the Grand Theft Auto video game, automatically annotated with precise per-pixel labels. Experiments show a significant improvement using our UDA algorithm compared to the model's performance without domain adaptation.DOI: 10.5220/0010303401850195
Project(s): AI4EU
, AI4Media Metrics:
See at:
CNR IRIS | ISTI Repository | www.scitepress.org | CNR IRIS | CNR IRIS
2020
Other
Open Access
Monitoring traffic flows via unsupervised domain adaptation
Ciampi L, Gennaro C, Amato G
Monitoring traffic flows in cities is crucial to improve urban mobility, and images are the best sensing modality to perceive and assess the flow of vehicles in large areas. However, current machine learning-based technologies using images hinge on large quantities of annotated data, preventing their scalability to city-scale as new cameras are added to the system. We propose a new methodology to design image-based vehicle density estimators with few labeled data via an unsupervised domain adaptation technique.Project(s): AI4EU
Ciampi L, Gennaro C, Amato G
Monitoring traffic flows in cities is crucial to improve urban mobility, and images are the best sensing modality to perceive and assess the flow of vehicles in large areas. However, current machine learning-based technologies using images hinge on large quantities of annotated data, preventing their scalability to city-scale as new cameras are added to the system. We propose a new methodology to design image-based vehicle density estimators with few labeled data via an unsupervised domain adaptation technique.Project(s): AI4EU
See at:
CNR IRIS | icities2020.unisa.it | ISTI Repository | ISTI Repository | CNR IRIS | CNR IRIS
2021
Conference article
Open Access
Traffic density estimation via unsupervised domain adaptation
Ciampi L, Santiago C, Costeira Jp, Gennaro C, Amato G
Monitoring traffic flows in cities is crucial to improve urban mobility, and images are the best sensing modality to perceive and assess the flow of vehicles in large areas. However, current machine learning-based technologies using images hinge on large quantities of annotated data, preventing their scalability to city-scale as new cameras are added to the system. We propose a new methodology to design image-based vehicle density estimators with few labeled data via an unsupervised domain adaptation technique.Source: CEUR WORKSHOP PROCEEDINGS, pp. 442-449. Pizzo Calabro, Italy, 05-09/09/2021
Project(s): AI4EU
Ciampi L, Santiago C, Costeira Jp, Gennaro C, Amato G
Monitoring traffic flows in cities is crucial to improve urban mobility, and images are the best sensing modality to perceive and assess the flow of vehicles in large areas. However, current machine learning-based technologies using images hinge on large quantities of annotated data, preventing their scalability to city-scale as new cameras are added to the system. We propose a new methodology to design image-based vehicle density estimators with few labeled data via an unsupervised domain adaptation technique.Source: CEUR WORKSHOP PROCEEDINGS, pp. 442-449. Pizzo Calabro, Italy, 05-09/09/2021
Project(s): AI4EU
See at:
ceur-ws.org | CNR IRIS | ISTI Repository | CNR IRIS
2022
Conference article
Open Access
Counting or localizing? Evaluating cell counting and detection in microscopy images
Ciampi L, Carrara F, Amato G, Gennaro C
Image-based automatic cell counting is an essential yet challenging task, crucial for the diagnosing of many diseases. Current solutions rely on Convolutional Neural Networks and provide astonishing results. However, their performance is often measured only considering counting errors, which can lead to masked mistaken estimations; a low counting error can be obtained with a high but equal number of false positives and false negatives. Consequently, it is hard to determine which solution truly performs best. In this work, we investigate three general counting approaches that have been successfully adopted in the literature for counting several different categories of objects. Through an experimental evaluation over three public collections of microscopy images containing marked cells, we assess not only their counting performance compared to several state-of-the-art methods but also their ability to correctly localize the counted cells. We show that commonly adopted counting metrics do not always agree with the localization performance of the tested models, and thus we suggest integrating the proposed evaluation protocol when developing novel cell counting solutions.DOI: 10.5220/0010923000003124
Project(s): AI4Media
Metrics:
Ciampi L, Carrara F, Amato G, Gennaro C
Image-based automatic cell counting is an essential yet challenging task, crucial for the diagnosing of many diseases. Current solutions rely on Convolutional Neural Networks and provide astonishing results. However, their performance is often measured only considering counting errors, which can lead to masked mistaken estimations; a low counting error can be obtained with a high but equal number of false positives and false negatives. Consequently, it is hard to determine which solution truly performs best. In this work, we investigate three general counting approaches that have been successfully adopted in the literature for counting several different categories of objects. Through an experimental evaluation over three public collections of microscopy images containing marked cells, we assess not only their counting performance compared to several state-of-the-art methods but also their ability to correctly localize the counted cells. We show that commonly adopted counting metrics do not always agree with the localization performance of the tested models, and thus we suggest integrating the proposed evaluation protocol when developing novel cell counting solutions.DOI: 10.5220/0010923000003124
Project(s): AI4Media
Metrics:
See at:
CNR IRIS | ISTI Repository | www.scitepress.org | CNR IRIS | CNR IRIS
2022
Dataset
Open Access
Night and day instance segmented park (NDISPark) dataset: a collection of images taken by day and by night for vehicle detection, segmentation and counting in parking areas
Ciampi L, Santiago C, Costeira Jp, Gennaro C, Amato G
NDIS Park is a collection of images of parking lots for vehicle detection, segmentation, and counting. Each image is manually labeled with pixel-wise masks and bounding boxes localizing vehicle instances. The dataset includes 259 images depicting several parking areas describing most of the problematic situations that we can find in a real scenario: seven different cameras capture the images under various weather conditions and viewing angles. Another challenging aspect is the presence of partial occlusion patterns in many scenes such as obstacles (trees, lampposts, other cars) and shadowed cars. The main peculiarity is that images are taken during the day and the night, showing utterly different lighting conditions.Project(s): AI4EU, AI4Media
Ciampi L, Santiago C, Costeira Jp, Gennaro C, Amato G
NDIS Park is a collection of images of parking lots for vehicle detection, segmentation, and counting. Each image is manually labeled with pixel-wise masks and bounding boxes localizing vehicle instances. The dataset includes 259 images depicting several parking areas describing most of the problematic situations that we can find in a real scenario: seven different cameras capture the images under various weather conditions and viewing angles. Another challenging aspect is the presence of partial occlusion patterns in many scenes such as obstacles (trees, lampposts, other cars) and shadowed cars. The main peculiarity is that images are taken during the day and the night, showing utterly different lighting conditions.Project(s): AI4EU
, AI4Media
See at:
CNR IRIS | ISTI Repository | zenodo.org | CNR IRIS
2021
Dataset
Open Access
A multi-rater benchmark for perineuronal nets detection and counting in fluorescence microscopy images
Ciampi L, Carrara F, Totaro V, Mazziotti R, Lupori L, Santiago C, Amato G, Pizzorusso T, Gennaro C
Dataset of fluorescence microscopy images of mice brain slices stained against perineuronal nets (PNNs). The dataset is composed of two subsets: a large single-rater subset (PNN-SR) and a smaller multi-rater subset (PNN-MR). i) PNN-SR consists of 25 images having different sizes ranging from 8184×6163 to 15120×9477 pixels. Among all the images, there are roughly 34k annotated PNNs, varying from a few dozens to some thousand per image, dot-annotated by a single human rater. ii) PNN-MR comprises 12 microscopic images of 2000×2000 pixels representing different portions of a mouse brain, with a total of 2,532 dot-annotated PNNs. The annotation procedure has been performed by seven different raters.Project(s): AI4Media
Ciampi L, Carrara F, Totaro V, Mazziotti R, Lupori L, Santiago C, Amato G, Pizzorusso T, Gennaro C
Dataset of fluorescence microscopy images of mice brain slices stained against perineuronal nets (PNNs). The dataset is composed of two subsets: a large single-rater subset (PNN-SR) and a smaller multi-rater subset (PNN-MR). i) PNN-SR consists of 25 images having different sizes ranging from 8184×6163 to 15120×9477 pixels. Among all the images, there are roughly 34k annotated PNNs, varying from a few dozens to some thousand per image, dot-annotated by a single human rater. ii) PNN-MR comprises 12 microscopic images of 2000×2000 pixels representing different portions of a mouse brain, with a total of 2,532 dot-annotated PNNs. The annotation procedure has been performed by seven different raters.Project(s): AI4Media
See at:
CNR IRIS | zenodo.org | CNR IRIS
2022
Journal article
Open Access
Learning to count biological structures with raters' uncertainty
Ciampi L, Carrara F, Totaro V, Mazziotti R, Lupori L, Santiago C, Amato G, Pizzorusso T, Gennaro C
Exploiting well-labeled training sets has led deep learning models to astonishing results for counting biological structures in microscopy images. However, dealing with weak multi-rater annotations, i.e., when multiple human raters disagree due to non-trivial patterns, remains a relatively unexplored problem. More reliable labels can be obtained by aggregating and averaging the decisions given by several raters to the same data. Still, the scale of the counting task and the limited budget for labeling prohibit this. As a result, making the most with small quantities of multi-rater data is crucial. To this end, we propose a two-stage counting strategy in a weakly labeled data scenario. First, we detect and count the biological structures; then, in the second step, we refine the predictions, increasing the correlation between the scores assigned to the samples and the raters' agreement on the annotations. We assess our methodology on a novel dataset comprising fluorescence microscopy images of mice brains containing extracellular matrix aggregates named perineuronal nets. We demonstrate that we significantly enhance counting performance, improving confidence calibration by taking advantage of the redundant information characterizing the small sets of available multi-rater data.Source: MEDICAL IMAGE ANALYSIS, vol. 80
DOI: 10.1016/j.media.2022.102500
Project(s): AI4Media
Metrics:
Ciampi L, Carrara F, Totaro V, Mazziotti R, Lupori L, Santiago C, Amato G, Pizzorusso T, Gennaro C
Exploiting well-labeled training sets has led deep learning models to astonishing results for counting biological structures in microscopy images. However, dealing with weak multi-rater annotations, i.e., when multiple human raters disagree due to non-trivial patterns, remains a relatively unexplored problem. More reliable labels can be obtained by aggregating and averaging the decisions given by several raters to the same data. Still, the scale of the counting task and the limited budget for labeling prohibit this. As a result, making the most with small quantities of multi-rater data is crucial. To this end, we propose a two-stage counting strategy in a weakly labeled data scenario. First, we detect and count the biological structures; then, in the second step, we refine the predictions, increasing the correlation between the scores assigned to the samples and the raters' agreement on the annotations. We assess our methodology on a novel dataset comprising fluorescence microscopy images of mice brains containing extracellular matrix aggregates named perineuronal nets. We demonstrate that we significantly enhance counting performance, improving confidence calibration by taking advantage of the redundant information characterizing the small sets of available multi-rater data.Source: MEDICAL IMAGE ANALYSIS, vol. 80
DOI: 10.1016/j.media.2022.102500
Project(s): AI4Media
Metrics:
See at:
CNR IRIS | ISTI Repository | www.sciencedirect.com | CNR IRIS | CNR IRIS | CNR IRIS
2022
Conference article
Open Access
A spatio-temporal attentive network for video-based crowd counting
Avvenuti M, Bongiovanni M, Ciampi L, Falchi F, Gennaro C, Messina N
Automatic people counting from images has recently drawn attention for urban monitoring in modern Smart Cities due to the ubiquity of surveillance camera networks. Current computer vision techniques rely on deep learning-based algorithms that estimate pedestrian densities in still, individual images. Only a bunch of works take advantage of temporal consistency in video sequences. In this work, we propose a spatio-temporal attentive neural network to estimate the number of pedestrians from surveillance videos. By taking advantage of the temporal correlation between consecutive frames, we lowered state-of-the-art count error by 5% and localization error by 7.5% on the widely-used FDST benchmark.Source: PROCEEDINGS - IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS. Rhodes Island, Greece, 30/06/2022-03/07/2022
DOI: 10.1109/iscc55528.2022.9913019
Project(s): AI4Media
Metrics:
Avvenuti M, Bongiovanni M, Ciampi L, Falchi F, Gennaro C, Messina N
Automatic people counting from images has recently drawn attention for urban monitoring in modern Smart Cities due to the ubiquity of surveillance camera networks. Current computer vision techniques rely on deep learning-based algorithms that estimate pedestrian densities in still, individual images. Only a bunch of works take advantage of temporal consistency in video sequences. In this work, we propose a spatio-temporal attentive neural network to estimate the number of pedestrians from surveillance videos. By taking advantage of the temporal correlation between consecutive frames, we lowered state-of-the-art count error by 5% and localization error by 7.5% on the widely-used FDST benchmark.Source: PROCEEDINGS - IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS. Rhodes Island, Greece, 30/06/2022-03/07/2022
DOI: 10.1109/iscc55528.2022.9913019
Project(s): AI4Media
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | ISTI Repository | CNR IRIS | CNR IRIS
2023
Journal article
Open Access
A comprehensive atlas of perineuronal net distribution and colocalization with parvalbumin in the adult mouse brain
Lupori L, Totaro V, Cornuti S, Ciampi L, Carrara F, Grilli E, Viglione A, Tozzi F, Putignano E, Mazziotti R, Amato G, Gennaro G, Tognini P, Pizzorusso T
Perineuronal nets (PNNs) surround specific neurons in the brain and are involved in various forms of plasticity and clinical conditions. However, our understanding of the PNN role in these phenomena is limited by the lack of highly quantitative maps of PNN distribution and association with specific cell types. Here, we present a comprehensive atlas of Wisteria floribunda agglutinin (WFA)-positive PNNs and colocalization with parvalbumin (PV) cells for over 600 regions of the adult mouse brain. Data analysis shows that PV expression is a good predictor of PNN aggregation. In the cortex, PNNs are dramatically enriched in layer 4 of all primary sensory areas in correlation with thalamocortical input density, and their distribution mirrors intracortical connectivity patterns. Gene expression analysis identifies many PNN-correlated genes. Strikingly, PNN-anticorrelated transcripts are enriched in synaptic plasticity genes, generalizing PNNs' role as circuit stability factors.Source: CELL REPORTS, vol. 42 (issue 7)
DOI: 10.1016/j.celrep.2023.112788
Project(s): AI4Media
Metrics:
Lupori L, Totaro V, Cornuti S, Ciampi L, Carrara F, Grilli E, Viglione A, Tozzi F, Putignano E, Mazziotti R, Amato G, Gennaro G, Tognini P, Pizzorusso T
Perineuronal nets (PNNs) surround specific neurons in the brain and are involved in various forms of plasticity and clinical conditions. However, our understanding of the PNN role in these phenomena is limited by the lack of highly quantitative maps of PNN distribution and association with specific cell types. Here, we present a comprehensive atlas of Wisteria floribunda agglutinin (WFA)-positive PNNs and colocalization with parvalbumin (PV) cells for over 600 regions of the adult mouse brain. Data analysis shows that PV expression is a good predictor of PNN aggregation. In the cortex, PNNs are dramatically enriched in layer 4 of all primary sensory areas in correlation with thalamocortical input density, and their distribution mirrors intracortical connectivity patterns. Gene expression analysis identifies many PNN-correlated genes. Strikingly, PNN-anticorrelated transcripts are enriched in synaptic plasticity genes, generalizing PNNs' role as circuit stability factors.Source: CELL REPORTS, vol. 42 (issue 7)
DOI: 10.1016/j.celrep.2023.112788
Project(s): AI4Media
Metrics:
See at:
CNR IRIS | www.cell.com | CNR IRIS
2023
Journal article
Open Access
A deep learning-based pipeline for whitefly pest abundance estimation on chromotropic sticky traps
Ciampi L, Zeni V, Incrocci L, Canale A, Benelli G, Falchi F, Amato G, Chessa S
Integrated Pest Management (IPM) is an essential approach used in smart agriculture to manage pest populations and sustainably optimize crop production. One of the cornerstones underlying IPM solutions is pest monitoring, a practice often performed by farm owners by using chromotropic sticky traps placed on insect hot spots to gauge pest population densities. In this paper, we propose a \rev{1}{modular model-agnostic} deep learning-based counting pipeline for estimating the number of insects present in pictures of chromotropic sticky traps, thus reducing the need for manual trap inspections and minimizing human effort. Additionally, our solution generates a set of raw positions of the counted insects and confidence scores expressing their reliability, allowing practitioners to filter out unreliable predictions. We train and assess our technique by exploiting PST - Pest Sticky Traps, a new collection of dot-annotated images we created on purpose and we publicly release, suitable for counting whiteflies. Experimental evaluation shows that our proposed counting strategy can be a valuable Artificial Intelligence-based tool to help farm owners to control pest outbreaks and prevent crop damages effectively. Specifically, our solution achieves an average counting error of approximately $9\%$ compared to human capabilities requiring a matter of seconds, a large improvement respecting the time-intensive process of manual human inspections, which often take hours or even days.Source: ECOLOGICAL INFORMATICS, vol. 78
DOI: 10.1016/j.ecoinf.2023.102384
Project(s): AI4Media
Metrics:
Ciampi L, Zeni V, Incrocci L, Canale A, Benelli G, Falchi F, Amato G, Chessa S
Integrated Pest Management (IPM) is an essential approach used in smart agriculture to manage pest populations and sustainably optimize crop production. One of the cornerstones underlying IPM solutions is pest monitoring, a practice often performed by farm owners by using chromotropic sticky traps placed on insect hot spots to gauge pest population densities. In this paper, we propose a \rev{1}{modular model-agnostic} deep learning-based counting pipeline for estimating the number of insects present in pictures of chromotropic sticky traps, thus reducing the need for manual trap inspections and minimizing human effort. Additionally, our solution generates a set of raw positions of the counted insects and confidence scores expressing their reliability, allowing practitioners to filter out unreliable predictions. We train and assess our technique by exploiting PST - Pest Sticky Traps, a new collection of dot-annotated images we created on purpose and we publicly release, suitable for counting whiteflies. Experimental evaluation shows that our proposed counting strategy can be a valuable Artificial Intelligence-based tool to help farm owners to control pest outbreaks and prevent crop damages effectively. Specifically, our solution achieves an average counting error of approximately $9\%$ compared to human capabilities requiring a matter of seconds, a large improvement respecting the time-intensive process of manual human inspections, which often take hours or even days.Source: ECOLOGICAL INFORMATICS, vol. 78
DOI: 10.1016/j.ecoinf.2023.102384
Project(s): AI4Media
Metrics:
See at:
CNR IRIS | ISTI Repository | CNR IRIS
2024
Conference article
Open Access
Teacher-student models for AI vision at the edge: a car parking case study
Molo M. J., Carlini E., Ciampi L., Gennaro C., Vadicamo L.
The surge of the Internet of Things has sparked a multitude of deep learning-based computer vision applications that extract relevant information from the deluge of data coming from Edge devices, such as smart cameras. Nevertheless, this promising approach introduces new obstacles, including the constraints posed by the limited computational resources on these devices and the challenges associated with the generalization capabilities of the AI-based models against novel scenarios never seen during the supervised training, a situation frequently encountered in this context. This work proposes an efficient approach for detecting vehicles in parking lot scenarios monitored by multiple smart cameras that train their underlying AI-based models by exploiting knowledge distillation. Specifically, we consider an architectural scheme comprising a powerful and large detector used as a teacher and several shallow models acting as students, more appropriate for computational-bounded devices and designed to run onboard the smart cameras. The teacher is pre-trained over general-context data and behaves like an oracle, transferring its knowledge to the smaller nodes; on the other hand, the students learn to localize cars in new specific scenarios without using further labeled data, relying solely on the distilled loss coming from the oracle. Preliminary results show that student models trained only with distillation loss increase their performances, sometimes even outperforming the results achieved by the same models supervised with the ground truth.DOI: 10.5220/0012376900003660
Project(s): AI4Media, National Centre for HPC, Big Data and Quantum Computing, Sustainable Mobility Center
Metrics:
Molo M. J., Carlini E., Ciampi L., Gennaro C., Vadicamo L.
The surge of the Internet of Things has sparked a multitude of deep learning-based computer vision applications that extract relevant information from the deluge of data coming from Edge devices, such as smart cameras. Nevertheless, this promising approach introduces new obstacles, including the constraints posed by the limited computational resources on these devices and the challenges associated with the generalization capabilities of the AI-based models against novel scenarios never seen during the supervised training, a situation frequently encountered in this context. This work proposes an efficient approach for detecting vehicles in parking lot scenarios monitored by multiple smart cameras that train their underlying AI-based models by exploiting knowledge distillation. Specifically, we consider an architectural scheme comprising a powerful and large detector used as a teacher and several shallow models acting as students, more appropriate for computational-bounded devices and designed to run onboard the smart cameras. The teacher is pre-trained over general-context data and behaves like an oracle, transferring its knowledge to the smaller nodes; on the other hand, the students learn to localize cars in new specific scenarios without using further labeled data, relying solely on the distilled loss coming from the oracle. Preliminary results show that student models trained only with distillation loss increase their performances, sometimes even outperforming the results achieved by the same models supervised with the ground truth.DOI: 10.5220/0012376900003660
Project(s): AI4Media
, National Centre for HPC, Big Data and Quantum Computing, Sustainable Mobility CenterMetrics:
See at:
CNR IRIS | www.scitepress.org | CNR IRIS | CNR IRIS
2024
Journal article
Open Access
In the wild video violence detection: an unsupervised domain adaptation approach
Ciampi L., Santiago C., Falchi F., Gennaro C., Amato G.
This work addresses the challenge of video violence detection in data-scarce scenarios, focusing on bridging the domain gap that often hinders the performance of deep learning models when applied to unseen domains. We present a novel unsupervised domain adaptation (UDA) scheme designed to effectively mitigate this gap by combining supervised learning in the train (source) domain with unlabeled test (target) data. We employ single-image classification and multiple instance learning (MIL) to select frames with the highest classification scores, and, upon this, we exploit UDA techniques to adapt the model to unlabeled target domains. We perform an extensive experimental evaluation, using general-context data as the source domain and target domain datasets collected in specific environments, such as violent/non-violent actions in hockey matches and public transport. The results demonstrate that our UDA pipeline substantially enhances model performances, improving their generalization capabilities in novel scenarios without requiring additional labeled data.Source: SN COMPUTER SCIENCE, vol. 5 (issue 7)
DOI: 10.1007/s42979-024-03126-3
Project(s): AI4Media, SUN
Metrics:
Ciampi L., Santiago C., Falchi F., Gennaro C., Amato G.
This work addresses the challenge of video violence detection in data-scarce scenarios, focusing on bridging the domain gap that often hinders the performance of deep learning models when applied to unseen domains. We present a novel unsupervised domain adaptation (UDA) scheme designed to effectively mitigate this gap by combining supervised learning in the train (source) domain with unlabeled test (target) data. We employ single-image classification and multiple instance learning (MIL) to select frames with the highest classification scores, and, upon this, we exploit UDA techniques to adapt the model to unlabeled target domains. We perform an extensive experimental evaluation, using general-context data as the source domain and target domain datasets collected in specific environments, such as violent/non-violent actions in hockey matches and public transport. The results demonstrate that our UDA pipeline substantially enhances model performances, improving their generalization capabilities in novel scenarios without requiring additional labeled data.Source: SN COMPUTER SCIENCE, vol. 5 (issue 7)
DOI: 10.1007/s42979-024-03126-3
Project(s): AI4Media
, SUN Metrics:
See at:
CNR IRIS | link.springer.com | CNR IRIS
2019
Other
Open Access
SmartPark@Lucca - D5. Integrazione e sperimentazione sul campo
Amato G, Bolettieri P, Carrara F, Ciampi L, Gennaro C, Leone Gr Moroni D Pieri G Vairo C
In questo deliverable sono descritte le attività eseguite all'interno del WP3, in particolare relative al Task 3.1 - Integrazione e al Task 3.2 - Sperimentazione sul campo.
Amato G, Bolettieri P, Carrara F, Ciampi L, Gennaro C, Leone Gr Moroni D Pieri G Vairo C
In questo deliverable sono descritte le attività eseguite all'interno del WP3, in particolare relative al Task 3.1 - Integrazione e al Task 3.2 - Sperimentazione sul campo.
See at:
CNR IRIS | ISTI Repository | CNR IRIS
2018
Conference article
Open Access
Counting vehicles with cameras
Ciampi L, Amato G, Falchi F, Gennaro C, Rabitti F
This paper aims to develop a method that can accurately count vehicles from images of parking areas captured by smart cameras. To this end, we have proposed a deep learning-based approach for car detection that permits the input images to be of arbitrary perspectives, illumination, and occlusions. No other information about the scenes is needed, such as the position of the parking lots or the perspective maps. This solution is tested using Counting CNRPark-EXT, a new dataset created for this specific task and that is another contribution to our research. Our experiments show that our solution outperforms the state-of-the-art approaches.Source: CEUR WORKSHOP PROCEEDINGS, pp. 1-8. Castellaneta Marina - Taranto - Italy, 24-27/06/2018
Ciampi L, Amato G, Falchi F, Gennaro C, Rabitti F
This paper aims to develop a method that can accurately count vehicles from images of parking areas captured by smart cameras. To this end, we have proposed a deep learning-based approach for car detection that permits the input images to be of arbitrary perspectives, illumination, and occlusions. No other information about the scenes is needed, such as the position of the parking lots or the perspective maps. This solution is tested using Counting CNRPark-EXT, a new dataset created for this specific task and that is another contribution to our research. Our experiments show that our solution outperforms the state-of-the-art approaches.Source: CEUR WORKSHOP PROCEEDINGS, pp. 1-8. Castellaneta Marina - Taranto - Italy, 24-27/06/2018
See at:
ceur-ws.org | CNR IRIS | ISTI Repository | CNR IRIS