Zobraziť v EDS

Real-Time Robust 2.5D Stereo Multi-Object Tracking with Lightweight Stereo Matching Algorithm.

Uložené v:
Podrobná bibliografia
Názov: Real-Time Robust 2.5D Stereo Multi-Object Tracking with Lightweight Stereo Matching Algorithm.
Autori: Lee, Jinhyeong, Shin, Junyoung, Park, Eunwoo, Kim, Daekeun
Zdroj: Sensors (14248220); Nov2025, Vol. 25 Issue 21, p6773, 27p
Predmety: MULTIPLE target tracking, OBJECT tracking (Computer vision), STEREO vision (Computer science), MATHEMATICAL optimization, AUTOMATIC tracking
Abstrakt: Highlights: What are the main findings? Lightweight stereo matching using only bounding box coordinates achieves robust multi-object tracking with a MOTA of 0.932 and an IDF1 of 0.823, outperforming state-of-the-art monocular trackers. A dual-tracker design with a re-identification mechanism maintains consistent object identities during occlusions and truncations by leveraging stereo redundancy. What are the implications of the main findings? Resource-efficient 2.5D tracking enables real-time deployment (70 FPS) on standard hardware without expensive 3D reconstruction or dense stereo matching. Stereo vision's inherent redundancy provides a practical solution for robust tracking in challenging real-world scenarios like retail monitoring and autonomous systems. Multi-object tracking faces persistent challenges from occlusions and truncations in monocular vision systems. While stereo vision provides depth information, existing approaches require computationally expensive dense matching or 3D reconstruction. This paper presents a real-time 2.5D stereo multi-object tracking framework combining lightweight stereo matching with resilient tracker management. The stereo matching module employs Direct Linear Transform-based triangulation using only bounding box coordinates, eliminating costly feature extraction while maintaining robust correspondence through geometric constraints. A dual-tracker architecture maintains independent trackers in both views, enabling re-identification when objects become occluded in one view but remain visible in the other. Experimental validation on a refrigerator monitoring dataset demonstrates that StereoSORT achieves a multiple object tracking accuracy (MOTA) of 0.932 and an identification F1 score (IDF1) of 0.823, substantially outperforming monocular trackers, including OC-SORT (IDF1: 0.765) and ByteTrack (IDF1: 0.609). The system achieves a 50.1 mm median depth error, comparable to commercial sensors, while maintaining 70 FPS on standard hardware. These results validate that geometric constraints alone enable robust stereo tracking without appearance features, offering a practical solution for resource-constrained environments where computational efficiency and tracking reliability are equally critical. [ABSTRACT FROM AUTHOR]
Copyright of Sensors (14248220) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáza: Complementary Index
Popis
Abstrakt:Highlights: What are the main findings? Lightweight stereo matching using only bounding box coordinates achieves robust multi-object tracking with a MOTA of 0.932 and an IDF1 of 0.823, outperforming state-of-the-art monocular trackers. A dual-tracker design with a re-identification mechanism maintains consistent object identities during occlusions and truncations by leveraging stereo redundancy. What are the implications of the main findings? Resource-efficient 2.5D tracking enables real-time deployment (70 FPS) on standard hardware without expensive 3D reconstruction or dense stereo matching. Stereo vision's inherent redundancy provides a practical solution for robust tracking in challenging real-world scenarios like retail monitoring and autonomous systems. Multi-object tracking faces persistent challenges from occlusions and truncations in monocular vision systems. While stereo vision provides depth information, existing approaches require computationally expensive dense matching or 3D reconstruction. This paper presents a real-time 2.5D stereo multi-object tracking framework combining lightweight stereo matching with resilient tracker management. The stereo matching module employs Direct Linear Transform-based triangulation using only bounding box coordinates, eliminating costly feature extraction while maintaining robust correspondence through geometric constraints. A dual-tracker architecture maintains independent trackers in both views, enabling re-identification when objects become occluded in one view but remain visible in the other. Experimental validation on a refrigerator monitoring dataset demonstrates that StereoSORT achieves a multiple object tracking accuracy (MOTA) of 0.932 and an identification F1 score (IDF1) of 0.823, substantially outperforming monocular trackers, including OC-SORT (IDF1: 0.765) and ByteTrack (IDF1: 0.609). The system achieves a 50.1 mm median depth error, comparable to commercial sensors, while maintaining 70 FPS on standard hardware. These results validate that geometric constraints alone enable robust stereo tracking without appearance features, offering a practical solution for resource-constrained environments where computational efficiency and tracking reliability are equally critical. [ABSTRACT FROM AUTHOR]
ISSN:14248220
DOI:10.3390/s25216773