Learning Non-Uniform Hypergraph for Multi-Object Tracking

Wen, Longyin; Du, Dawei; Li, Shengkun; Bian, Xiao; Lyu, Siwei

doi:10.1609/aaai.v33i01.33018981

Cited by 41 publications

(23 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tracking-by-detection is a generic framework employed by several multiple object trackers [33], [34], [35]. In this framework, the objects are first detected and then associated in different frames.…”

Section: Related Workmentioning

confidence: 99%

Deep Affinity Network for Multiple Object Tracking

Sun

Akhtar

Song

et al. 2019

IEEE Trans. Pattern Anal. Mach. Intell.

250

140

View full text Add to dashboard Cite

Multiple Object Tracking (MOT) plays an important role in solving many fundamental problems in video analysis and computer vision. Most MOT methods employ two steps: Object Detection and Data Association. The first step detects objects of interest in every frame of a video, and the second establishes correspondence between the detected objects in different frames to obtain their tracks. Object detection has made tremendous progress in the last few years due to deep learning. However, data association for tracking still relies on hand crafted constraints such as appearance, motion, spatial proximity, grouping etc. to compute affinities between the objects in different frames. In this paper, we harness the power of deep learning for data association in tracking by jointly modeling object appearances and their affinities between different frames in an end-to-end fashion. The proposed Deep Affinity Network (DAN) learns compact, yet comprehensive features of pre-detected objects at several levels of abstraction, and performs exhaustive pairing permutations of those features in any two frames to infer object affinities. DAN also accounts for multiple objects appearing and disappearing between video frames. We exploit the resulting efficient affinity computations to associate objects in the current frame deep into the previous frames for reliable on-line tracking. Our technique is evaluated on popular multiple object tracking challenges MOT15, MOT17 and UA-DETRAC. Comprehensive benchmarking under twelve evaluation metrics demonstrates that our approach is among the best performing techniques on the leader board for these challenges. The open source implementation of our work is available at https://github.com/shijieS/SST.git.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Affinity Network for Multiple Object Tracking

Sun

Akhtar

Song

et al. 2019

IEEE Trans. Pattern Anal. Mach. Intell.

250

140

View full text Add to dashboard Cite

show abstract

“…STDM methods has been utilised most computer vision tasks such as tracking Huang and Zhou ( 2019 ); Wen et al. ( 2019 ); Yin et al. ( 2019 ); Bai et al.…”

Section: Stdm Task-related Challengesmentioning

confidence: 99%

Spatiotemporal data mining: a survey on challenges and open problems

et al. 2021

View full text Add to dashboard Cite

Spatiotemporal data mining (STDM) discovers useful patterns from the dynamic interplay between space and time. Several available surveys capture STDM advances and report a wealth of important progress in this field. However, STDM challenges and problems are not thoroughly discussed and presented in articles of their own. We attempt to fill this gap by providing a comprehensive literature survey on state-of-the-art advances in STDM. We describe the challenging issues and their causes and open gaps of multiple STDM directions and aspects. Specifically, we investigate the challenging issues in regards to spatiotemporal relationships, interdisciplinarity, discretisation, and data characteristics. Moreover, we discuss the limitations in the literature and open research problems related to spatiotemporal data representations, modelling and visualisation, and comprehensiveness of approaches. We explain issues related to STDM tasks of classification, clustering, hotspot detection, association and pattern mining, outlier detection, visualisation, visual analytics, and computer vision tasks. We also highlight STDM issues related to multiple applications including crime and public safety, traffic and transportation, earth and environment monitoring, epidemiology, social media, and Internet of Things.

show abstract

“…[7] applied the classical multiple hypothesis tracking algorithm for association, based on which, [8] added the bilinear LSTM to improve the learning of long-term appearance information. [28] generated special non-uniform hypergraphs to model and associate detections on each frame. [30] proposed the spatial-temporal relation network in order to encode various cues across different domains simultaneously and generate better similarity scores.…”

Section: Related Workmentioning

confidence: 99%

Video Relation Detection via Multiple Hypothesis Association

Shang

Chen

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Video visual relation detection (VidVRD) aims at obtaining not only the trajectories of objects but also the dynamic visual relations between them. It provides abundant information for video understanding and can serve as a bridge between vision and language. Compared with visual relation detection on image, VidVRD requires one more step at last called visual relation association which associates relation segments across time dimension into video relations. This step plays an important role in the task but is less studied. Nevertheless, visual relation association is a difficult task as the association process is easily affected by inaccurate tracklet detection and relation prediction in the former steps. In this paper, we propose a novel relation association method called Multiple Hypothesis Association (MHA). It maintains multiple possible relation hypothesis during the association process in order to tolerate and handle the inaccurate or missing problem in the former steps and generate more accurate video relations. Our experiments on the benchmark datasets (Imagenet-VidVRD and VidOR) show that our method outperforms the state-of-the-art methods.

show abstract

Learning Non-Uniform Hypergraph for Multi-Object Tracking

Cited by 41 publications

References 33 publications

Deep Affinity Network for Multiple Object Tracking

Deep Affinity Network for Multiple Object Tracking

Spatiotemporal data mining: a survey on challenges and open problems

Video Relation Detection via Multiple Hypothesis Association

Contact Info

Product

Resources

About