Online multiple object tracking using joint detection and embedding network

Chan, Sixian; Jia, Yangwei; Zhou, Xiaolong; Bai, Cong; Chen, Shengyong; Zhang, Xiaoqin

doi:10.1016/j.patcog.2022.108793

Cited by 16 publications

(9 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…JDE-based methods typically employ a single network to directly predict detection and appearance features [ 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 ]. In general, these methods employ a single backbone to predict both object bounding boxes and appearance features.…”

Section: Related Workmentioning

confidence: 99%

“…In general, these methods employ a single backbone to predict both object bounding boxes and appearance features. For example, FasterVideo [ 18 ] and Online Tracker [ 19 ] adopt Faster R-CNN [ 20 ] and Yolov5 for feature detection and feature re-identification, respectively. Although their pipelines are relatively simple, the competitive relationship between detection and identification harms the optimization procedure in the multi-task learning of object detection and appearance feature extraction.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking

Ding

Wei

et al. 2022

Sensors

View full text Add to dashboard Cite

Joint detection and embedding (JDE) methods usually fuse the target motion information and appearance information as the data association matrix, which could fail when the target is briefly lost or blocked in multi-object tracking (MOT). In this paper, we aim to solve this problem by proposing a novel association matrix, the Embedding and GioU (EG) matrix, which combines the embedding cosine distance and GioU distance of objects. To improve the performance of data association, we develop a simple, effective, bottom-up fusion tracker for re-identity features, named SimpleTrack, and propose a new tracking strategy which can mitigate the loss of detection targets. To show the effectiveness of the proposed method, experiments are carried out using five different state-of-the-art JDE-based methods. The results show that by simply replacing the original association matrix with our EG matrix, we can achieve significant improvements in IDF1, HOTA and IDsw metrics, and increase the tracking speed of these methods by around 20%. In addition, our SimpleTrack has the best data association capability among the JDE-based methods, e.g., 61.6 HOTA and 76.3 IDF1, on the test set of MOT17 with 23 FPS running speed on a single GTX2080Ti GPU.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking

Ding

Wei

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…There are several strategies to observe the vehicles' behavior, such as using traffic camera footage. Several researchers proposed Multi-Object Tracking (MOT) to classify multiple vehicles throughout the video [19]. In MOT, there are three approaches, which are joint detection and tracking [19], attention mechanism [20] and tracking by detection [21].…”

Section: Introductionmentioning

confidence: 99%

“…Several researchers proposed Multi-Object Tracking (MOT) to classify multiple vehicles throughout the video [19]. In MOT, there are three approaches, which are joint detection and tracking [19], attention mechanism [20] and tracking by detection [21]. The latter was deployed as it was the best approach to detect multiple vehicles per frame.…”

Section: Introductionmentioning

confidence: 99%

Investigation of the Vehicle Driving Trajectory During Turning at Intersectional Roads Using Deep Learning Model

Yong,

Peeie,

Zulkifli

et al. 2024

View full text Add to dashboard Cite

Two-thirds of vehicle accidents in Malaysia occurred at the straight type of roads, followed by intersection-type roads. Despite the deployment of traffic lights on the road, accidents still occur which are caused by illegal maneuvers, speeding or misjudgment of other’s actions. Hence, motivated by the lack of previous research regarding causes of accidents on intersectional roads, this study aims to observe the pattern of the vehicles’ speed and turning angle during the right turn after the traffic stop at the intersection road. To obtain these parameters, video samples of vehicles at two types of intersections were obtained and analyzed via YOLOV7 and DeepSORT. The two road intersections researched are four-legged intersection and three-legged intersection. 153 and 35 vehicle samples were collected from these types of road intersections, respectively. It was observed that 78 and 75 vehicles exit towards the nearest and furthest lanes at four-leg controlled crossings on divided roads. While, at a single-lane to a dual carriageway road intersection, 26 and 9 vehicles exit towards the nearest and furthest lanes, respectively. From the research, 16.52 - 17.53 km/h and 67.57°-73.33° are the most optimal turning speeds and angles respectively for vehicles at four-leg controlled crossings. Whereas 14.48 - 15.51 km/h and 144.77° - 154.403° are the most optimal turning speeds and angles respectively for vehicles at a single-lane to a dual carriageway road intersection.

show abstract

“…Multiple object tracking (MOT) can be defined as localizing various objects in a scene after obtaining a sequence of data (i.e., a series of RGB images) over a period of time from sensors, combining these with data association techniques to accomplish the correct matching of the same object between data frames, and forming the tracking trajectory of each object. MOT has enormous potential in both academia and industry and has gained increasing attention in the fields of computer vision and artificial intelligence [1][2][3]. Autonomous driving is the emerging future of the automotive industry, helping to alleviate traffic congestion, reduce traffic accidents, improve driving safety, meet the various needs of different people groups, etc.…”

Section: Introductionmentioning

confidence: 99%

Online Multiple Object Tracking Using Min-Cost Flow on Temporal Window for Autonomous Driving

Wei,

Huang,

Zhang

et al. 2023

WEVJ

View full text Add to dashboard Cite

Multiple object tracking (MOT), as a core technology for environment perception in autonomous driving, has attracted attention from researchers. Combing the advantages of batch global optimization, we present a novel online MOT framework for autonomous driving, consisting of feature extraction and data association on a temporal window. In the feature extraction stage, we design a three-channel appearance feature extraction network based on metric learning by using ResNet50 as the backbone network and the triplet loss function and employ a Kalman Filter with a constant acceleration motion model to optimize and predict the object bounding box information, so as to obtain reliable and discriminative object representation features. For data association, to reduce the ID switches, the min-cost flow of global association is introduced within the temporal window composed of consecutive multi-frame images. The trajectories within the temporal window are divided into two categories, active trajectories and inactive trajectories, and the appearance, motion affinities between each category of trajectories, and detections are calculated, respectively. Based on this, a sparse affinity network is constructed, and the data association is achieved using the min-cost flow problem of the network. Qualitative experimental results on KITTI MOT public benchmark dataset and real-world campus scenario sequences validate the effectiveness and robustness of our method. Compared with the homogeneous, vision-based MOT methods, quantitative experimental results demonstrate that our method has competitive advantages in terms of higher order tracking accuracy, association accuracy, and ID switches.

show abstract

Online multiple object tracking using joint detection and embedding network

Cited by 16 publications

References 6 publications

SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking

SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking

Investigation of the Vehicle Driving Trajectory During Turning at Intersectional Roads Using Deep Learning Model

Online Multiple Object Tracking Using Min-Cost Flow on Temporal Window for Autonomous Driving

Contact Info

Product

Resources

About