CNR Author
operator:
and / or
Typology
operator:
and / or
Language
operator:
and / or
Date
operator:
and / or
Rights
operator:
and / or
2023
Conference article
Open Access
GPU-Accelerating hierarchical descriptors for point set registration
Dutta S., Russig B., Gumhold S.
3D reconstruction based on structure from motion is one of the most techniques to produce sparse point-cloud model and camera parameter. However, this technique heavily relies on feature tracking method to obtain feature correspondences, then resulting in a heavy computation burden. To speed up 3D reconstruction, in this paper, we design a novel GPU-accelerated feature tracking (GFT) method for large-scale structure from motion (SFM)-based 3D reconstruction. The proposed GFT method consists of GPU-based Gaussian of image (DOG) keypoint detector, RootSIFT descriptor extractor, k nearest matching, and outlier removing. Firstly, our GPU-based DOG implementation can detect thousands of keypoints in real-time, whose speed is 30 times faster than that of the CPU version. Secondly, our GPU-based RootSIFT descriptor can compute thousands of descriptors in real-time. Thirdly, our GPU-based descriptor matching is 10 times faster than that of the state-of-the-art methods. Finally, we conduct thorough experiments on different datasets to evaluate the proposed method. Experimental results demonstrate the effectiveness and efficiency of the proposed method.Source: ITALIAN CHAPTER CONFERENCE, pp. 59-69. Matera, Italy, 16-17/11/2023
Project(s): CHARITY
Dutta S., Russig B., Gumhold S.
3D reconstruction based on structure from motion is one of the most techniques to produce sparse point-cloud model and camera parameter. However, this technique heavily relies on feature tracking method to obtain feature correspondences, then resulting in a heavy computation burden. To speed up 3D reconstruction, in this paper, we design a novel GPU-accelerated feature tracking (GFT) method for large-scale structure from motion (SFM)-based 3D reconstruction. The proposed GFT method consists of GPU-based Gaussian of image (DOG) keypoint detector, RootSIFT descriptor extractor, k nearest matching, and outlier removing. Firstly, our GPU-based DOG implementation can detect thousands of keypoints in real-time, whose speed is 30 times faster than that of the CPU version. Secondly, our GPU-based RootSIFT descriptor can compute thousands of descriptors in real-time. Thirdly, our GPU-based descriptor matching is 10 times faster than that of the state-of-the-art methods. Finally, we conduct thorough experiments on different datasets to evaluate the proposed method. Experimental results demonstrate the effectiveness and efficiency of the proposed method.Source: ITALIAN CHAPTER CONFERENCE, pp. 59-69. Matera, Italy, 16-17/11/2023
Project(s): CHARITY
See at:
diglib.eg.org 
| CNR IRIS | CNR IRIS 
2023
Conference article
Open Access
On-the-fly acquisition and rendering with low cost LiDAR and RGB cameras for marine navigation
Dutta S, Ganovelli F, Cignoni P
This paper describes a hardware/software system, dubbed NausicaaVR, for acquiring and rendering 3D environments in the context of marine navigation. Like other similar work, it focuses on system calibration and rendering but the specific context poses new and more difficult challenges for the development when compared to the classic automotive scenario. We provide a comprehensive description of all the components of the system, explicitly reporting on encountered problems and subtle choices to overcome those, in an attempt to render an insightful picture of how this and similar systems are built.
Dutta S, Ganovelli F, Cignoni P
This paper describes a hardware/software system, dubbed NausicaaVR, for acquiring and rendering 3D environments in the context of marine navigation. Like other similar work, it focuses on system calibration and rendering but the specific context poses new and more difficult challenges for the development when compared to the classic automotive scenario. We provide a comprehensive description of all the components of the system, explicitly reporting on encountered problems and subtle choices to overcome those, in an attempt to render an insightful picture of how this and similar systems are built.
See at:
CNR IRIS | ISTI Repository | www.scitepress.org | CNR IRIS | CNR IRIS
2024
Contribution to book
Open Access
Dynamic real-time spatio-temporal acquisition and rendering in adverse environments
Dutta S., Ganovelli F., Cignoni P.
This paper introduces NausicaaVR, a novel hardware/software system designed to acquire and render intricate 3D environments, with a particular emphasis on challenging and adverse contexts. In doing so, we navigate the complex landscape of system calibration and rendering, while seamlessly integrating data from multiple sensors. We explore the distinctive challenges inherent in adverse environments, juxtaposing them against conventional automotive scenarios. Through a comprehensive exposition of all constituent elements of the NausicaaVR system, we offer transparent insights into the encountered obstacles and the intricate decisions that were instrumental in surmounting them. This study seeks to illuminate the developmental trajectory of NausicaaVR and analogous systems, thereby furnishing a repository of knowledge and understanding poised to benefit future research and the pragmatic implementation of such cutting-edge technologies.Source: COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE, vol. 2107, pp. 34-53
Project(s): NAUtical Safety by means of Integrated Computer-Assisted Appliances 4.0
Dutta S., Ganovelli F., Cignoni P.
This paper introduces NausicaaVR, a novel hardware/software system designed to acquire and render intricate 3D environments, with a particular emphasis on challenging and adverse contexts. In doing so, we navigate the complex landscape of system calibration and rendering, while seamlessly integrating data from multiple sensors. We explore the distinctive challenges inherent in adverse environments, juxtaposing them against conventional automotive scenarios. Through a comprehensive exposition of all constituent elements of the NausicaaVR system, we offer transparent insights into the encountered obstacles and the intricate decisions that were instrumental in surmounting them. This study seeks to illuminate the developmental trajectory of NausicaaVR and analogous systems, thereby furnishing a repository of knowledge and understanding poised to benefit future research and the pragmatic implementation of such cutting-edge technologies.Source: COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE, vol. 2107, pp. 34-53
Project(s): NAUtical Safety by means of Integrated Computer-Assisted Appliances 4.0
See at:
CNR IRIS | link.springer.com | CNR IRIS | CNR IRIS