Adaptive Kalman Filter with power transformation for online multi-object tracking

Liu, Youyu; Li, Yang; Xu, Dezhang; Yang, Qi; Tao, Wanbao

doi:10.1007/s00530-023-01052-7

Cited by 3 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al [47] introduced a lightweight Re-ID network which was termed as fast omni-scale network (Fast-OSNet) for MOT. The hierarchical adaptive exponential moving average (HAEMA) was employed to decrease the occlusion noise effect on the trajectory's appearance, by use of adaptive modified weights with a two-stage linear transformation.…”

Section: Literature Surveymentioning

confidence: 99%

ResNet50-deep affinity network for object detection and tracking in videos

2024

IJATEE

View full text Add to dashboard Cite

Multiple-object tracking (MOT) plays a crucial role in addressing many fundamental challenges within the fields of computer vision and video analysis. The majority of MOT methods rely on two primary processes: object detection and data association. Initially, each video frame is analyzed to detect objects, followed by a subsequent step that establishes correlations among the detected objects across multiple frames to generate their tracks. However, the data association for tracking often relies on manually defined criteria such as motion, appearance, grouping, and spatial proximity, among others. In the study, the ResNet50-deep affinity network (DAN) was introduced, which had been designed for the detection and tracking of objects in videos, including those that appear and disappear between frames. The proposed method was evaluated using the widely recognized MOT17 dataset to address MOT challenges. During the preprocessing phase, photometric distortion correction, frame expansion, and cropping were performed. The ResNet50 model was utilized to extract features. The DAN was employed to identify object appearances in video frames and to calculate their cross-frame affinities (CFA). The approach was compared with existing research, including DAN, ByteTrack, the graph neural network for simultaneous detection and tracking (GSDT), the reptile search optimization algorithm with deep learning-based multiple object detection and tracking (RSOADL-MODT), the center graph network (CGTracker), the hybrid motion model, FlowNet2-deep learning, and the super chained tracker (SCT), to validate the efficiency of theResNet50-DAN method. The ResNet50-DAN method achieved superior results, with a multiple-object tracking accuracy (MOTA) of 84.2%, an F1 score for identification metrics (IDF1) of 80.3%, 10,352 false positives (FP), and 1,284 identity switches (ID-Sw). The ResNet50-DAN method demonstrated higher MOTA compared to the existing approaches, including DAN, ByteTrack, GSDT, RSOADL-MODT, CGTracker, the hybrid motion model, FlowNet2-DL, and SCT.

show abstract

Section: Literature Surveymentioning

confidence: 99%

ResNet50-deep affinity network for object detection and tracking in videos

2024

IJATEE

View full text Add to dashboard Cite

show abstract

“…With the development of detector networks and multi-task learning [55], multi-object tracking usually utilizes the backbone network to extract the detections and features first, and then completes the tracking task through tracking association models such as SORT [1,4,9,10,18,20,52]. Although the SORT model is favored for its simplicity and efficiency, its robustness needs to be improved, and the tracking results are more dependent on the confidence of the detections [9,26,53].…”

Section: Introductionmentioning

confidence: 99%

Effective Hierarchical Data Association in Multi-Object Tracking Using an Enhanced Network Flow Framework

Zhang,

Zhu

et al. 2024

Preprint

View full text Add to dashboard Cite

In the realm of multi-object tracking, the SORT model is esteemed for its simplicity and efficiency, yet its tracking efficacy hinges significantly on detector performance. Randomly discarding low-threshold detections can result in critical misses and track fragmentation. Hence, it is often complemented by a hierarchical data association strategy centered on detection thresholds. Nonetheless, relying solely on threshold-based categorization may segregate detections and lead to redundant detections for the same target, thereby increasing the impact of redundancies on tracking and causing trajectory drift. To address this, this paper introduces a novel hierarchical data association framework based on network flow, integrating historical trajectory and domain information to efficiently group detections and redundancies. Additionally, an effective global topological structure graph is proposed to manage redundant detections. Experimental results demonstrate competitive performance on MOTChallenge, with a 1-2\% improvement in MOTA over the benchmark, particularly nearing 2% on MOT20.

show abstract