Tracking Objects as Pixel-Wise Distributions

Zhao, Zelin; Wu, Ze; Zhuang, Yueqing; Li, Boxun; Jia, Jiaya

doi:10.1007/978-3-031-20047-2_5

Cited by 32 publications

(5 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ByteTrack (Zhang et al 2022) addressed fragmented trajectories and missing detections by utilizing low-confidence detection similarities. P3AFormer (Zhao et al 2022) combined pixel-wise distribution architecture with Kalman filter to refine object association, and OC-SORT (Cao et al 2022) amended the linear motion assumption within the Klaman Filter for superior adaptability to occlusion and non-linear motion. Graph-based methods, including Graph Neural Networks (GNN) (Gori, Monfardini, and Scarselli 2005) and Graph Convolutional Networks (GCN) (Kipf and Welling 2016), have been widely explored in MOT, with vertices representing detection bounding boxes or tracklets and edges across frames denoting similarities.…”

Section: Related Workmentioning

confidence: 99%

“…based trackers (Bewley et al 2016;Cao et al 2022;Zhang et al 2022;Aharon, Orfaig, and Bobrovsky 2022;Zhao et al 2022;Wojke, Bewley, and Paulus 2017;Zhang et al 2021;Liu et al 2023) that employ the Kalman filter framework (Welch, Bishop et al 1995). In addition, certain TBD approaches establish object associations through the utilization of Re-identification (Re-ID) techniques (Chen et al 2018;Bergmann, Meinhardt, and Leal-Taixe 2019a), and others that rely on graph-based trackers (He et al 2021;Rangesh et al 2021;Li, Gao, and Jiang 2020) that model the association process as minimization of a cost flow problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DiffusionTrack: Diffusion Model for Multi-Object Tracking

Luo,

Song,

et al. 2024

AAAI

View full text Add to dashboard Cite

Multi-object tracking (MOT) is a challenging vision task that aims to detect individual objects within a single frame and associate them across multiple frames. Recent MOT approaches can be categorized into two-stage tracking-by-detection (TBD) methods and one-stage joint detection and tracking (JDT) methods. Despite the success of these approaches, they also suffer from common problems, such as harmful global or local inconsistency, poor trade-off between robustness and model complexity, and lack of flexibility in different scenes within the same video. In this paper we propose a simple but robust framework that formulates object detection and association jointly as a consistent denoising diffusion process from paired noise boxes to paired ground-truth boxes. This novel progressive denoising diffusion strategy substantially augments the tracker's effectiveness, enabling it to discriminate between various objects. During the training stage, paired object boxes diffuse from paired ground-truth boxes to random distribution, and the model learns detection and tracking simultaneously by reversing this noising process. In inference, the model refines a set of paired randomly generated boxes to the detection and tracking results in a flexible one-step or multi-step denoising diffusion process. Extensive experiments on three widely used MOT benchmarks, including MOT17, MOT20, and DanceTrack, demonstrate that our approach achieves competitive performance compared to the current state-of-the-art methods. Code is available at https://github.com/RainBowLuoCS/DiffusionTrack.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

DiffusionTrack: Diffusion Model for Multi-Object Tracking

Luo,

Song,

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…While using ReID information to match reappearing objects is a common method to handle occlusion [63], it does not work well for scenarios where the object is often locally invisible [13]. To address this issue, MotionTrack [46] uses the Interaction Module to model the relationship between tracks for better results in dense scenes; FineTrack [48] uses locally unoccluded parts for fine-grained feature extraction; P3AFormer [95] uses a point-wise approach to solve the occlusion problem at the pixel level; Some methods [44] also use calculation in the case of occlusion to determine whether the trajectory is terminated, rather than relying on inactivity time.…”

Section: Occlusion Handlingmentioning

confidence: 99%

DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions

Fu,

Wang,

et al. 2023

Proceedings of the 31st ACM International Conference on Multimedia

View full text Add to dashboard Cite

Multiple object tracking (MOT) tends to become more challenging when severe occlusions occur. In this paper, we analyze the limitations of traditional Convolutional Neural Network-based methods and Transformer-based methods in handling occlusions and propose DNMOT, an end-to-end trainable DeNoising Transformer for MOT. To address the challenge of occlusions, we explicitly simulate the scenarios when occlusions occur. Specifically, we augment the trajectory with noises during training and make our model learn the denoising process in an encoder-decoder architecture, so that our model can exhibit strong robustness and perform well under crowded scenes. Additionally, we propose a Cascaded Mask strategy to better coordinate the interaction between different types of queries in the decoder to prevent the mutual suppression between neighboring trajectories under crowded scenes. Notably, the proposed method requires no additional modules like matching strategy and motion state estimation in inference. We conduct extensive experiments on the MOT17, MOT20, and DanceTrack datasets, and the experimental results show that our method outperforms previous state-of-the-art methods by a clear margin.

show abstract

“…These tracking-byattention methods lack motion cues, which are sensitive to occlusions. Methods like P3AFormer [41] re-introduce motion cues by methods like optical flows. Some other methods solve the occlusion problem from aspects of learning long-term temporal features and understanding scenes.…”

Section: A Multiple Pedestrian Trackingmentioning

confidence: 99%

METFormer: A Motion Enhanced Transformer for Multiple Object Tracking

Gao

Yap

Wang

et al. 2023

2023 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

Multiple pedestrian tracking faces the challenge of tracking pedestrians in the presence of occlusion. Existing methods suffer from inaccurate motion estimation, appearance feature extraction, and association due to occlusion, leading to inadequate Identification F1-Score (IDF1), excessive ID switches (IDSw), and insufficient association accuracy and recall (AssA and AssR). We found that the main reason is abnormal detections caused by partial occlusion. In this paper, we suggest that the key insight is explicit motion estimation, reliable appearance features, and fair association in occlusion scenes. Specifically, we propose an adaptive occlusion-aware multiple pedestrian tracker, OccluTrack. We first introduce an abnormal motion suppression mechanism into the Kalman Filter to adaptively detect and suppress outlier motions caused by partial occlusion. Second, we propose a pose-guided re-ID module to extract discriminative part features for partially occluded pedestrians. Last, we design a new occlusion-aware association method towards fair IoU and appearance embedding distance measurement for occluded pedestrians. Extensive evaluation results demonstrate that our OccluTrack outperforms state-of-the-art methods on MOT-Challenge datasets. Particularly, the improvements on IDF1, IDSw, AssA, and AssR demonstrate the effectiveness of our OccluTrack on tracking and association performance.

show abstract

Tracking Objects as Pixel-Wise Distributions

Cited by 32 publications

References 55 publications

DiffusionTrack: Diffusion Model for Multi-Object Tracking

DiffusionTrack: Diffusion Model for Multi-Object Tracking

DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions

METFormer: A Motion Enhanced Transformer for Multiple Object Tracking

Contact Info

Product

Resources

About