Multiple Object Tracking by Trajectory Map Regression with Temporal Priors Embedding

Wan, Xingyu; Zhou, Sanping; Wang, Jinjun; Meng, Rongye

doi:10.1145/3474085.3475304

Cited by 18 publications

(8 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The offline trackers (denoted using Off) include ApLift [19], Lif_T [18], and QD [37]. The online trackers (denoted as O) like OUTrack [26], Hugmot [49], TMOH [47], MPTC [45], TraDes [53], CTTrack [64], GSDT [50], HTA [25], CTracker [38], and Tube_TK [36]. The near-online trackers (denoted as NO) include MAT [15].…”

Section: Results On Motchallengementioning

confidence: 99%

NCT:noise-control multi-object tracking

Zeng

You

Shen

et al. 2023

Complex Intell. Syst.

View full text Add to dashboard Cite

Multi-Object Tracking (MOT) is an important topic in computer vision. Recent MOT methods based on the anchor-free paradigm trade complicated hierarchical structures for tracking performance. However, existing anchor-free MOT methods ignore the noise in detection, data association, and trajectory reconnection stages, which results in serious problems, such as missing detection of small objects, insufficient motion information, and trajectory drifting. To solve these problems, this paper proposes Noise-Control Tracker (NCT), which focuses on the noise-control design of detection, association, and reconnection. First, a prior depth denoise method is introduced to suppress the fusion feature redundant noise, which can recover the gradient information of the heatmap fusion features. Then, the Smoothing Gain Kalman filter is designed, which combines the Gaussian function with the adaptive observation coefficient matrix to stabilize the mutation noise of Kalman gain. Finally, to address the drift noise issue, the gradient boosting reconnection context mechanism is designed, which realizes adaptive trajectory reconnection to effectively fill the gaps in trajectories. With the assistance of the plug-and-play noise-control method, the experimental results on MOTChallenge 16 &17 datasets indicate that the NCT can achieve better performance than other state-of-the-art trackers.

show abstract

Section: Results On Motchallengementioning

confidence: 99%

NCT:noise-control multi-object tracking

Zeng

You

Shen

et al. 2023

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…Cen-terTrack [12] follows the CenterNet framework [133] and concatenates a pair of sequential frames and the heat map of the previous frame for joint embedding, object center location estimation, as well as size and offset prediction. [39] takes multiple frames using an encoder-decoder architecture with temporal priors embedding based on short connections [153] to estimate multi-channel trajectory maps simultaneously, including presence map, appearance map, and motion map.…”

Section: Multi-frame Spatial-temporal Embeddingmentioning

confidence: 99%

“…Some embedding methods combine multiple-task heads [16], [33], [34], [35], [36], including box regression, object classification, and re-identification. Some embedding methods consider spatial-temporal correlations [12], [14], [37], [38], [39], collaborating both appearance and motion information. Some methods exploit the interaction relationships among objects, foreground and background, local and global information with correlation and attention, to learn the track embeddings [40], [41], [42], [43].…”

Section: Introductionmentioning

confidence: 99%

Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey

Wang¹,

Song²,

Hwang³

2022

Preprint

View full text Add to dashboard Cite

Multi-object tracking (MOT) aims to associate target objects across video frames in order to obtain entire moving trajectories. With the advancement of deep neural networks and the increasing demand for intelligent video analysis, MOT has gained significantly increased interest in the computer vision community. Embedding methods play an essential role in object location estimation and temporal identity association in MOT. Unlike other computer vision tasks, such as image classification, object detection, re-identification, and segmentation, embedding methods in MOT have large variations, and they have never been systematically analyzed and summarized. In this survey, we first conduct a comprehensive overview with in-depth analysis for embedding methods in MOT from seven different perspectives, including patch-level embedding, single-frame embedding, cross-frame joint embedding, correlation embedding, sequential embedding, tracklet embedding, and cross-track relational embedding. We further summarize the existing widely used MOT datasets and analyze the advantages of existing state-of-the-art methods according to their embedding strategies. Finally, some critical yet under-investigated areas and future research directions are discussed.

show abstract

“…ing boxes and recognizing their identities throughout a whole video [40]. Though great progress has been made in the past few years, MOT still remains a challenging task due to the dynamic environment, such as dense crowds and extreme occlusions, in the tracking scenario.…”

Section: Introductionmentioning

confidence: 99%

“…In general, the existing MOT methods either follow the tracking-by-detection [2] or tracking-by-regression [39,40,59], paradigm. The former methods first detect objects in each video frame and then associate detections between adjacent frames to create individual object tracks over time.…”

Section: Introductionmentioning

confidence: 99%

MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking

Zheng¹,

Zhou²,

Wang³

et al. 2023

Preprint

View full text Add to dashboard Cite

The main challenge of Multi-Object Tracking (MOT) lies in maintaining a continuous trajectory for each target. Existing methods often learn reliable motion patterns to match the same target between adjacent frames and discriminative appearance features to re-identify the lost targets after a long period. However, the reliability of motion prediction and the discriminability of appearances can be easily hurt by dense crowds and extreme occlusions in the tracking process. In this paper, we propose a simple yet effective multi-object tracker, i.e., MotionTrack, which learns robust short-term and long-term motions in a unified framework to associate trajectories from a short to long range. For dense crowds, we design a novel Interaction Module to learn interaction-aware motions from short-term trajectories, which can estimate the complex movement of each target. For extreme occlusions, we build a novel Refind Module to learn reliable long-term motions from the target's history trajectory, which can link the interrupted trajectory with its corresponding detection. Our Interaction Module and Refind Module are embedded in the well-known tracking-bydetection paradigm, which can work in tandem to maintain superior performance. Extensive experimental results on MOT17 and MOT20 datasets demonstrate the superiority of our approach in challenging scenarios, and it achieves state-of-the-art performances at various MOT metrics.

show abstract

Multiple Object Tracking by Trajectory Map Regression with Temporal Priors Embedding

Cited by 18 publications

References 43 publications

NCT:noise-control multi-object tracking

NCT:noise-control multi-object tracking

Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey

MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking

Contact Info

Product

Resources

About