Complementary-View Multiple Human Tracking

Han, Ruize; Feng, Wei; Zhao, Jing; Niu, Zicheng; Zhang, Yujun; Wan, Liang; Wang, Song

doi:10.1609/aaai.v34i07.6724

Cited by 21 publications

(7 citation statements)

References 28 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[41] proposes an efficient online min-cost flow tracking algorithm with bounded memory and computation. In addition to the single-view tracking, graph based methods are also explored in multi-view tracking tasks [45]- [47], where the multi-view tracking is formulated as a graph clustering problem. Usually, detections or tracklets are adopted as graph nodes.…”

Section: A Tracking With Graph Modelsmentioning

confidence: 99%

Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking

Wang

et al. 2023

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Multi-object tracking (MOT) is an essential task in the computer vision field. With the fast development of deep learning technology in recent years, MOT has achieved great improvement. However, some challenges still remain, such as sensitiveness to occlusion, instability under different lighting conditions, non-robustness to deformable objects, etc. To address such common challenges in most of the existing trackers, in this paper, a tracklet booster algorithm is proposed, which can be built upon any other tracker. The motivation is simple and straightforward: split tracklets on potential ID-switch positions and then connect multiple tracklets into one if they are from the same object. In other words, the tracklet booster consists of two parts, i.e., Splitter and Connector. First, an architecture with stacked temporal dilated convolution blocks is employed for the splitting position prediction via label smoothing strategy with adaptive Gaussian kernels. Then, a multi-head self-attention based encoder is exploited for the tracklet embedding, which is further used to connect tracklets into larger groups. We conduct sufficient experiments on MOT17 and MOT20 benchmark datasets, which demonstrates promising results. Combined with the proposed tracklet booster, existing trackers usually can achieve large improvements on the IDF1 score, which shows the effectiveness of the proposed method.

show abstract

Section: A Tracking With Graph Modelsmentioning

confidence: 99%

Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking

Wang

et al. 2023

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…In recent years, there have been a few works about multiview MOT [256], [257], [258], [259], [260], [261], [262], [263], [264], where multiple objects are tracked from several different overlapping views simultaneously, aiming to address occlusion issues with multi-view geometry and consistency. The embedding framework is learned for both cross-frames and cross-views.…”

Section: Multi-view Collaborated Motmentioning

confidence: 99%

“…Specifically, [260] proposes a hierarchical composition model and re-formulates multi-view MOT as a problem of compositional structure optimization. [263] models the data similarity using appearance, motion, and spatial reasoning and formulates the multi-view MOT as a joint optimization problem solved by constrained integer programming. [261] formulates multi-view MOT as a constrained mixed-integer programming problem and effectively measures subjects' similarity over time and across views.…”

Section: Multi-view Collaborated Motmentioning

confidence: 99%

Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey

Wang¹,

Song²,

Hwang³

2022

Preprint

View full text Add to dashboard Cite

Multi-object tracking (MOT) aims to associate target objects across video frames in order to obtain entire moving trajectories. With the advancement of deep neural networks and the increasing demand for intelligent video analysis, MOT has gained significantly increased interest in the computer vision community. Embedding methods play an essential role in object location estimation and temporal identity association in MOT. Unlike other computer vision tasks, such as image classification, object detection, re-identification, and segmentation, embedding methods in MOT have large variations, and they have never been systematically analyzed and summarized. In this survey, we first conduct a comprehensive overview with in-depth analysis for embedding methods in MOT from seven different perspectives, including patch-level embedding, single-frame embedding, cross-frame joint embedding, correlation embedding, sequential embedding, tracklet embedding, and cross-track relational embedding. We further summarize the existing widely used MOT datasets and analyze the advantages of existing state-of-the-art methods according to their embedding strategies. Finally, some critical yet under-investigated areas and future research directions are discussed.

show abstract

“…Most existing methods use fixed cameras for video collection, whose field of view (FOV) is unchanged and limited. In contrast, wearable cameras, e.g., GoPro and Google glass, worn by and moved with wearers, have time-varying non-specific observation coverage [1][2][3][4][5] and can be used to track and observe people at different sites by varying the camera views, which enables more flexible and wide-range outdoor video surveillance of crowded scenes. The goal of this paper is to study the new problem of MHT in non-specific fields using wearable cameras.…”

Section: Introductionmentioning

confidence: 99%

Multiple Human Tracking in Non-Specific Coverage with Wearable Cameras

Wang

Han

Feng

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Compared to fixed cameras, wearable cameras have timevarying non-specific view coverage and can be used to alternately observe people at different sites by varying the camera views. However, such view change of wearable cameras may introduce intervals of transitional frames without useful information, which brings new challenge for the important multiple object tracking (MOT) task -existing MOT methods can not handle well frequent disappearing/reappearing targets in the field of view, especially in the presence of informationless transitional sequences of frames. To address this problem, in this paper we propose a Markov Decision Process with jump state (JMDP) to model the target's lifetime in tracking, and use optical flow of the camera motion and the statistical information of the targets to model the camera state transition. We further develop a frame-level classification algorithm to locate the transitional sequence. By combining all of them, we formulate the proposed non-specific-coverage MOT problem as a joint state transition problem, which can be solved by the state transfer mechanism of the targets and the camera. We collect a new dataset for performance evaluation and the experimental results show the effectiveness of the proposed method.

show abstract

Complementary-View Multiple Human Tracking

Cited by 21 publications

References 28 publications

Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking

Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking

Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey

Multiple Human Tracking in Non-Specific Coverage with Wearable Cameras

Contact Info

Product

Resources

About