Smart City Gnosys
Smart city article details
| Title | Multi-Object Tracking Based On Attention Networks For Smart City System |
|---|---|
| ID_Doc | 38290 |
| Authors | Zhou X.; Jia Y.; Bai C.; Zhu H.; Chan S. |
| Year | 2022 |
| Published | Sustainable Energy Technologies and Assessments, 52 |
| DOI | http://dx.doi.org/10.1016/j.seta.2022.102216 |
| Abstract | The Smart City is a hot topic at present. Pedestrian tracking and behavior analysis play an important role in Smart City system. Therefore, it is urgent to design an universal and robust multi-object tracking(MOT) algorithm. MOT is a challenging problem with numerous significant applications, including robot navigation, autonomous driving and pedestrian behavior analysis. Among the existing MOT approaches, MOT models which joint learning detection and Re-ID are attracting increasing attention. Subsequently, there is competition between these two tasks jointly in a network inevitably leading to performance degradation. To address these difficulties, we propose an adaptive joint learning approach, called UnionTrack, for MOT in this paper. It handles with the problem of uniform learning between tasks in online MOT system. Firstly, UnionTrack introduces a scale-aware attention network that aggregates features from different scales for object localization and learning of the corresponding discriminative embeddings. Secondly, a cross-correlation module is designed to construct task-relevant feature maps and interact adaptively during training detection and Re-ID. Then, we perform inter-frame correlation at different stages by using high and low confidence detection to avoid occlusions and backgrounds. UnionTrack is trained in an end-to-end manner to better accommodate the training between detection and Re-ID tasks. Finally, our proposed UnionTrack is compared with state-of-the-art methods in extensively experiments and detailed performance analysis is performed in MOT15, MOT16, MOT17 and MOT20 which are all urban scene to demonstrate the effectiveness of our proposed method. Looking forward to playing a role in the Smart City systems. © 2022 Elsevier Ltd |
| Author Keywords | Anchor-free; Multi-object tracking; One-shot; Real-time; Smart City |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
17814  | 0.887 | Wang X.; Sun Z.; Chehri A.; Jeon G.; Song Y. | Deep Learning And Multi-Modal Fusion For Real-Time Multi-Object Tracking: Algorithms, Challenges, Datasets, And Comparative Study | Information Fusion, 105 (2024) |
| 29919 | 0.87 | Yang P.; Luo X.; Sun J. | Iampdnet: Instance-Aware And Multi-Part Decoupled Network For Joint Detection And Embedding | Journal of Internet Technology, 23, 6 (2022) |
| 14737 | 0.854 | Sun H.; Chen Y.; Aved A.; Blasch E. | Collaborative Multi-Object Tracking As An Edge Service Using Transfer Learning | Proceedings - 2020 IEEE 22nd International Conference on High Performance Computing and Communications, IEEE 18th International Conference on Smart City and IEEE 6th International Conference on Data Science and Systems, HPCC-SmartCity-DSS 2020 (2020) |
| 17929 | 0.854 | Li H.; Liu X.; Jia H.; Ahanger T.A.; Xu L.; Alzamil Z.; Li X. | Deep Learning-Based 3D Multi-Object Tracking Using Multimodal Fusion In Smart Cities | Human-centric Computing and Information Sciences, 14 (2024) |
| 6289 | 0.852 | Sun H.; Zhao H.; Zhang W.; Xu L.; Guan H. | Adaptive Multi-Task Learning For Multi-Par In Real World | IEEE Journal of Radio Frequency Identification, 8 (2024) |
| 22093 | 0.852 | Hua S.; Anastasiu D.C. | Effective Vehicle Tracking Algorithm For Smart Traffic Networks | Proceedings - 13th IEEE International Conference on Service-Oriented System Engineering, SOSE 2019, 10th International Workshop on Joint Cloud Computing, JCC 2019 and 2019 IEEE International Workshop on Cloud Computing in Robotic Systems, CCRS 2019 (2019) |