Multiple Object Tracking by Flowing and Fusing

Zhang, Jimuyang; Zhou, Sanping; Chang, Xin; Wan, Fangbin; Wang, Jinjun; Wu, Yang; Huang, Dong

doi:10.48550/arxiv.2001.11180

Cited by 10 publications

(11 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, [5] aggregates node embeddings based on graph neural networks (GNN) using GraphConv [161] given a pair of sequential frames. [162] generates fused targets based on proposed FuseTrack from detected objects and tracked targets with the guide of optical flows estimated from input frames.…”

Section: Head-level Feature Aggregated Embeddingmentioning

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

Section: Head-level Feature Aggregated Embeddingmentioning

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

show abstract

“…Instead, JDE incorporates detection model and embedding into a unified framework [6,23,39,48,50,60,63,69,79,82]. It typically modifies detectors, e.g., Faster R-CNN [57], CenterNet [83], YOLOv3 [56] by adding a predictor [6,29,77,82] or an embedding branch [69,79] and leverages them to implement detection and tracking jointly. Generally, JDE meth-ods usually behave better and faster than SDE in common applications.…”

Section: Sde and Jdementioning

confidence: 99%

GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021

Wan

Zhao

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

In recent years, algorithms for multiple object tracking tasks have benefited from great progresses in deep models and video quality. However, in challenging scenarios like drone videos, they still suffer from problems, such as small objects, camera movements and view changes. In this paper, we propose a new multiple object tracker, which employs Global Information And some Optimizing strategies, named GIAOTracker. It consists of three stages, i.e., online tracking, global link and post-processing. Given detections in every frame, the first stage generates reliable tracklets using information of camera motion, object motion and object appearance. Then they are associated into trajectories by exploiting global clues and refined through four post-processing methods. With the effectiveness of the three stages, GIAOTracker achieves state-of-the-art performance on the VisDrone MOT dataset and wins the 2nd place in the VisDrone2021 MOT Challenge.

show abstract

“…Tracking with Optical Flow. FlowTrack [60] introduces optical flow to predict the target location. But explicitly using optical flow is not only time-consuming, but also only encodes the pixel-level motion.…”

Section: Related Workmentioning

confidence: 99%

Multiple Object Tracking with Correlation Learning

Wang¹,

Zheng²,

Pan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recent works have shown that convolutional networks have substantially improved the performance of multiple object tracking by simultaneously learning detection and appearance features. However, due to the local perception of the convolutional network structure itself, the long-range dependencies in both the spatial and temporal cannot be obtained efficiently. To incorporate the spatial layout, we propose to exploit the local correlation module to model the topological relationship between targets and their surrounding environment, which can enhance the discriminative power of our model in crowded scenes. Specifically, we establish dense correspondences of each spatial location and its context, and explicitly constrain the correlation volumes through self-supervised learning. To exploit the temporal context, existing approaches generally utilize two or more adjacent frames to construct an enhanced feature representation, but the dynamic motion scene is inherently difficult to depict via CNNs. Instead, our paper proposes a learnable correlation operator to establish frameto-frame matches over convolutional feature maps in the different layers to align and propagate temporal context. With extensive experimental results on the MOT datasets, our approach demonstrates the effectiveness of correlation learning with the superior performance and obtains stateof-the-art MOTA of 76.5% and IDF1 of 73.6% on MOT17.

show abstract

Multiple Object Tracking by Flowing and Fusing

Cited by 10 publications

References 66 publications

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

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

GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021

Multiple Object Tracking with Correlation Learning

Contact Info

Product

Resources

About