Do Different Tracking Tasks Require Different Appearance Models?

Wang, Zhongdao; Zhao, Hengshuang; Li, Yali; Wang, Shengjin; Torr, Philip H. S.; Bertinetto, Luca

doi:10.48550/arxiv.2107.02156

Cited by 4 publications

(5 citation statements)

References 105 publications

(135 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The implementation source codes of ByteTrack [46], Deep OC_SORT [47], BoTSORT [48], OC_SORT [49], and Strong_SORT [50] come from [51], while TransTrack [52] and Uni-Track [53] adopt the authors' original codes, and DeepSORT uses an implementation from [54]. These methodologies all rely on YOLOX-x, as we know that the anchor-free weights file (yolox_x.pth, 756 MB) outperformed all other detectors and facilitated a relatively fair comparison among various tracking and association processes.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

Head-Integrated Detecting Method for Workers under Complex Construction Scenarios

Liu,

Zhou,

Wang

et al. 2024

Buildings

View full text Add to dashboard Cite

Real-time detection of workers is crucial in construction safety management. Deep learning-based detecting methods are valuable, but always challenged by the possibility of target missing or identity errors under complex scenarios. To address these limitations, previous research depended on re-training for new models or datasets, which are prohibitively time-consuming and incur high computing demands. However, we demonstrate that the better detecting model might not rely on more re-training of weights; instead, a training-free model can achieve even better performance by integrating head information. In this paper, a new head-detecting branch (55 MB) is added to the Keypoint Region-based Convolutional Network (Keypoint R-CNN, 226 MB) without altering its original weights, allowing for a less occluded head to aid in body detection. We also deployed motion information and anthropometric data through a post-processing module to calculate movement relationships. This study achieved an identity F1-score (IDF1) of 97.609%, recall (Rcll) of 98.173%, precision (Prcn) of 97.052%, and accuracy of 95.329% as a state-of-the-art (SOTA) method for worker detection. This exploration breaks the inertial attitudes of re-training dependency and accelerates the application of universal models, in addition to reducing the computational difficulty for most construction sites, especially in scenarios with an insufficient graphics processing unit (GPU). More importantly, this study can address occlusion challenges effectively in the worker detection field, making it of practical significance.

show abstract

Section: Comparison With Other Methodsmentioning

confidence: 99%

Head-Integrated Detecting Method for Workers under Complex Construction Scenarios

Liu,

Zhou,

Wang

et al. 2024

Buildings

View full text Add to dashboard Cite

show abstract

“…These five methods were retrained on 26.6 K images of CrowdHuman, MOT17, Cityperson and ETHZ datasets [7]. TransTrack [24] and Uni-Track [31] are in the authors' original codes, and DeepSORT uses an implementation from [41]. These three methodologies rely on vanilla YOLOX-x (yolox_x.pth, 756 MB).…”

Section: Comparision Of Other Sota Methodsmentioning

confidence: 99%

Bidirectional Tracking Method for Construction Workers in Dealing with Identity Errors

Liu,

Wang,

Zhou

2024

Mathematics

View full text Add to dashboard Cite

Online multi-object tracking (MOT) techniques are instrumental in monitoring workers’ positions and identities in construction settings. Traditional approaches, which employ deep neural networks (DNNs) for detection followed by body similarity matching, often overlook the significance of clear head features and stable head motions. This study presents a novel bidirectional tracking method that integrates intra-frame processing, which combines head and body analysis to minimize false positives and inter-frame matching to control ID assignment. By leveraging head information for enhanced body tracking, the method generates smoother trajectories with reduced ID errors. The proposed method achieved a state-of-the-art (SOTA) performance, with a multiple-object tracking accuracy (MOTA) of 95.191%, higher-order tracking accuracy (HOTA) of 78.884% and an identity switch (IDSW) count of 0, making it a strong baseline for future research.

show abstract

“…GMPHD_MAF [23] takes instance segmentation results as input and performs data association based on the Gaussian mixture probability hypothesis density filter for position and motion, and kernelized correlation filter for appearance. UniTrack [26] proposes a unified framework for solving five different tasks. It consists of an appearance model that is task agnostic, and several heads which are used for solving each task and do not require training.…”

Section: Multiple Object Tracking and Segmentationmentioning

confidence: 99%

PolyTrack: Tracking with Bounding Polygons

Faure¹,

Perreault²,

Bilodeau³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we present a novel method called PolyTrack for fast multi-object tracking and segmentation using bounding polygons. Polytrack detects objects by producing heatmaps of their center keypoint. For each of them, a rough segmentation is done by computing a bounding polygon over each instance instead of the traditional bounding box. Tracking is done by taking two consecutive frames as input and computing a center offset for each object detected in the first frame to predict its location in the second frame. A Kalman filter is also applied to reduce the number of ID switches. Since our target application is automated driving systems, we apply our method on urban environment videos. We trained and evaluated PolyTrack on the MOTS and KITTIMOTS datasets. Results show that tracking polygons can be a good alternative to bounding box and mask tracking. The code of PolyTrack is available at https://github.com/gafaua/PolyTrack.Preprint. Under review.

show abstract

Do Different Tracking Tasks Require Different Appearance Models?

Cited by 4 publications

References 105 publications

Head-Integrated Detecting Method for Workers under Complex Construction Scenarios

Head-Integrated Detecting Method for Workers under Complex Construction Scenarios

Bidirectional Tracking Method for Construction Workers in Dealing with Identity Errors

PolyTrack: Tracking with Bounding Polygons

Contact Info

Product

Resources

About