Joint Detection and Online Multi-object Tracking

Kieritz, Hilke; Hübner, Wolfgang; Arens, Michael

doi:10.1109/cvprw.2018.00195

Cited by 34 publications

(23 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conducted all these experiments in MOT15, MOT17, Urban Tracker and Visual Tracker Benchmark and its performance was compared to MOT methods which are MOT_LST [33], MASS [17], POI [20] and OMOT_JD [19], FPSN [18].…”

Section: B Tracking Methods Based On E-mcgmmentioning

confidence: 99%

See 1 more Smart Citation

Multiple Object Tracking Using Edge Multi-Channel Gradient Model With ORB Feature

Chen

Chi

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Section: B Tracking Methods Based On E-mcgmmentioning

confidence: 99%

“…In addition, most of deep learning-based tracking by detection frameworks can yield accurate tracking results by using object detector with powerful feature representation capabilities [17,18,19,20]. However, these methods are mostly time-consuming and data-intensive.…”

Section: Introductionmentioning

confidence: 99%

Multiple Object Tracking Using Edge Multi-Channel Gradient Model With ORB Feature

Chen

Chi

et al. 2021

IEEE Access

View full text Add to dashboard Cite

“…Various JoDT methods have been proposed in (Zhang et al 2021;Wang, Kitani, and Weng 2020;Peng et al 2020;Hu et al 2019;Shenoi et al 2020;Kim and Kim 2016;Kieritz, Hubner, and Arens 2018;Ke et al 2019;Munjal et al 2020). In the early phase, the idea of JoDT was adopted for 2D MOT.…”

Section: Joint Object Detection and Trackingmentioning

confidence: 99%

“…Several works relevant to JoDT have been reported in the literature (Zhang et al 2021;Wang, Kitani, and Weng 2020;Hu et al 2019;Kim and Kim 2016;Kieritz, Hubner, and Arens 2018;Voigtlaender et al 2019;Shenoi et al 2020). The previous JoDT methods can be categorized into two approaches.…”

Section: Introductionmentioning

confidence: 99%

Joint 3D Object Detection and Tracking Using Spatio-Temporal Representation of Camera Image and LiDAR Point Clouds

Koh¹,

Kim²,

Yoo³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we propose a new joint object detection and tracking (JoDT) framework for 3D object detection and tracking based on camera and LiDAR sensors. The proposed method, referred to as 3D DetecTrack, enables the detector and tracker to cooperate to generate a spatio-temporal representation of the camera and LiDAR data, with which 3D object detection and tracking are then performed. The detector constructs the spatio-temporal features via the weighted temporal aggregation of the spatial features obtained by the camera and LiDAR fusion. Then, the detector reconfigures the initial detection results using information from the tracklets maintained up to the previous time step. Based on the spatio-temporal features generated by the detector, the tracker associates the detected objects with previously tracked objects using a graph neural network (GNN). We devise a fullyconnected GNN facilitated by a combination of rule-based edge pruning and attention-based edge gating, which exploits both spatial and temporal object contexts to improve tracking performance. The experiments conducted on both KITTI and nuScenes benchmarks demonstrate that the proposed 3D DetecTrack achieves significant improvements in both detection and tracking performances over baseline methods and achieves state-of-the-art performance among existing methods through collaboration between the detector and tracker.

show abstract

“…MTT is closely related to pedestrian recognition. Based on the time order of trajectory generation [8]- [10], MTT algorithms can be divided into online [11], [12], offline [13], [14], or nearonline [15] approaches. Offline MTT is generally constructed using graph models from target detection relationships.…”

Section: Introductionmentioning

confidence: 99%

Multi-Target Tracking Based on High-Order Appearance Feature Fusion

2019

View full text Add to dashboard Cite

Multi-target tracking (MTT) is among the fundamental problems in the field of video analysis and monitoring. In the tracking-by-detection framework, data association is one of the most important and difficult problems. In this paper, we propose a framework to obtain the appearance features of a target in an end-to-end fashion, which fuses high-level and low-level semantic information. The high-order feature map is abstracted using the high-order apparent relationship for each target between the current frame and the previous frames, whereas the similarity matrix is used to describe the high-order features of the target. The best matching relationships between targets are obtained using hierarchical data association and the Hungarian algorithm. This proposed method is called Multi-target tracking Based on High-order Appearance Feature Fusion (MTT-HAFF), which can handle a large number of input sequences, local association failures, and identity exchanges that result from unreliable detections. The results show that the proposed algorithm has a good robustness for long-term occlusion tracking.INDEX TERMS Multi-target tracking, data association, high-order features, multi-feature fusion.

show abstract

Joint Detection and Online Multi-object Tracking

Cited by 34 publications

References 24 publications

Multiple Object Tracking Using Edge Multi-Channel Gradient Model With ORB Feature

Multiple Object Tracking Using Edge Multi-Channel Gradient Model With ORB Feature

Joint 3D Object Detection and Tracking Using Spatio-Temporal Representation of Camera Image and LiDAR Point Clouds

Multi-Target Tracking Based on High-Order Appearance Feature Fusion

Contact Info

Product

Resources

About