Multiple Object Tracking with Correlation Learning

Wang, Qiang; Zheng, Yun; Pan, Pan; Xu, Yinghui

doi:10.1109/cvpr46437.2021.00387

Cited by 132 publications

(57 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Benefiting from the rapid development of object detection [17,42,43,52,53,78], seperate trackers have dominated the MOT task for years. Recently, several joint trackers [30,32,38,57,59,65,68] have been proposed to train detection and some other components jointly, e.g., motion, embedding and association models. The main benefit of these trackers is their low computational cost and comparable performance.…”

Section: Seperate and Joint Trackersmentioning

confidence: 99%

“…The success of joint trackers has motivated researchers to design unified tracking frameworks for various components, e.g., detection, motion, embedding, and association models [30,32,38,57,59,65,68]. However, we argue that two problems exist in these joint frameworks: (1) the competition between different components and (2) limited data for training these components jointly.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

StrongSORT: Make DeepSORT Great Again

Du¹,

Yang²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Existing Multi-Object Tracking (MOT) methods can be roughly classified as tracking-by-detection and joint-detection-association paradigms. Although the latter has elicited more attention and demonstrates comparable performance relative to the former, we claim that the trackingby-detection paradigm is still the optimal solution in terms of tracking accuracy. In this paper, we revisit the classic tracker DeepSORT and upgrade it from various aspects, i.e., detection, embedding and association. The resulting tracker, called StrongSORT, sets new HOTA and IDF1 records on MOT17 and MOT20. We also present two lightweight and plug-and-play algorithms to further refine the tracking results. Firstly, an appearance-free link model (AFLink) is proposed to associate short tracklets into complete trajectories. To the best of our knowledge, this is the first global link model without appearance information. Secondly, we propose Gaussian-smoothed interpolation (GSI) to compensate for missing detections. Instead of ignoring motion information like linear interpolation, GSI is based on the Gaussian process regression algorithm and can achieve more accurate localizations. Moreover, AFLink and GSI can be plugged into various trackers with a negligible extra computational cost (591.9 and 140.9 Hz, respectively, on MOT17). By integrating StrongSORT with the two algorithms, the final tracker Strong-SORT++ ranks first on MOT17 and MOT20 in terms of HOTA and IDF1 metrics and surpasses the second-place one by 1.3 -2.2. Code will be released soon.

show abstract

Section: Seperate and Joint Trackersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

StrongSORT: Make DeepSORT Great Again

Du¹,

Yang²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Other relevant real-time multi-object trackers that have a JDE framework are QDTrack [183], TraDeS [184], CorrTracker [185], and transformer-based tracking models (TransTrack [186], MOTR [187]).…”

Section: B Multi-object Trackingmentioning

confidence: 99%

Continuous Human Action Recognition for Human-Machine Interaction: A Review

Gammulle¹,

Ahmedt-Aristizabal²,

Denman³

et al. 2022

Preprint

View full text Add to dashboard Cite

With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams. Recognising actions and detecting action transitions within an input video are challenging but necessary tasks for applications that require real-time human-machine interaction. By reviewing a large body of recent related work in the literature, we thoroughly analyse, explain and compare action segmentation methods and provide details on the feature extraction and learning strategies that are used on most state-of-the-art methods. We cover the impact of the performance of object detection and tracking techniques on human action segmentation methodologies. We investigate the application of such models to real-world scenarios and discuss several limitations and key research directions towards improving interpretability, generalisation, optimisation and deployment.

show abstract

“…The one-stage object detector RetinaNet [29] begin to be used by several methods such as [32,39]. CenterNet [76] is the most popular detector used by most methods [75,72,60,74,57,52,55] for its simplicity and efficiency. The YOLO series detectors [40,6] are also used by a large number of methods [58,27,28,13] for its excellent balance of accuracy and speed.…”

Section: Object Detection In Motmentioning

confidence: 99%

VariabilityTrack:Multi-Object Tracking with Variable Speed Object Movement

Luo¹,

Wei²,

Lin³

2022

Preprint

View full text Add to dashboard Cite

Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods can be roughly classified as tracking-by-detection and joint-detection-association paradigms. Although the latter has elicited more attention and demonstrates comparable performance relative than the former, we claim that the tracking-by-detection paradigm is still the optimal solution in terms of tracking accuracy,such as ByteTrack [70],which achieves 80.3 MOTA, 77.3 IDF1 and 63.1 HOTA on the test set of MOT17 with 30 FPS running speed on a single V100 GPU.However, under complex perspectives such as vehicle and UAV acceleration, the performance of such a tracker using uniform Kalman filter will be greatly affected, resulting in tracking loss.In this paper, we propose a variable speed Kalman filter algorithm based on environmental feedback and improve the matching process, which can greatly improve the tracking effect in complex variable speed scenes while maintaining high tracking accuracy in relatively static scenes. Eventually, higher MOTA and IDF1 results can be achieved on MOT17 test set than ByteTrack[70]

show abstract

Multiple Object Tracking with Correlation Learning

Cited by 132 publications

References 35 publications

StrongSORT: Make DeepSORT Great Again

StrongSORT: Make DeepSORT Great Again

Continuous Human Action Recognition for Human-Machine Interaction: A Review

VariabilityTrack:Multi-Object Tracking with Variable Speed Object Movement

Contact Info

Product

Resources

About