Pixel-Guided Association for Multi-Object Tracking

Boragule, Abhijeet; Jang, Hyunsung; Ha, Namkoo; Jeon, Moongu

doi:10.3390/s22228922

Cited by 10 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transformer Tracking. Transformer-based tracking has recently become a focal point of research in the field of Multiple Object Tracking, yielding significant progress [14,[24][25][26]. In contrast to straightforwardly leveraging attention mechanism [2,3], the architecture of transformer tracking involves employing an encoder-decoder and attention mechanism between queries and keys to associate targets between the current and previous frames.…”

Section: Relative Workmentioning

confidence: 99%

“…Subsequently, it calculates the offset of target centers, followed by IOU matching to associate detections and tracks. Pixel-Guide [24] employs a shared backbone, encoder, and decoder for processing both the previous frame and the current frame. It establishes an association network to calculate the similarity between every pair of pixels, facilitating the association of tracks and detections.…”

Section: Relative Workmentioning

confidence: 99%

“…Many of association methods of traking-by-detection paradigms are independent from optimizing training a traking model. They typically employing the Hungarian algorithm [1,3,6,22,24] or other greedy algorithm [27][28][29] to complete the task of matching after training, where each detection or track is a node, and edges indicates possible link among them. However, these method themselves do not fiTable join in the optimize the traking network, it might be the bottleneck of the MOT algorithm.…”

Section: Relative Workmentioning

confidence: 99%

See 2 more Smart Citations

Application of ROI Feature Decomposition and Local Matching in Multi-Object Tracking

Yang,

Ban,

Liu

2024

Preprint

View full text Add to dashboard Cite

For multi-object tracking (MOT), matching newly detected target features and trajectory features often involves template matching. Typically, feature embedding for multi-object tracking relies on either the mean feature within the Region of Interest (ROI) or the vector at the target's center. However, both of these feature embeddings are vulnerable to interference in scenarios involving occlusion. Additionally, one-to-many (O-T-M) style matching strategies are prone to causing the loss of trajectories and detections, as one target only represented by a single indicator. To overcome those limitations, we propose utilizing Principal Component Analysis (PCA) on the target ROI to decompose target features, expressing the identical feature of targets by collectively representing the principal component features of the ROI region, and utilizing these principal component features to form local features, the identical features are then trained through a classification task. Furthermore, in the template matching process, we introduce a local features matching algorithm for targets and trajectories. This algorithm adopts a many-to-many (M-T-M) matching style, aiming to associate every detailed part of the ROI feature. Experimental results demonstrate that the proposed local matching algorithm effectively handles complex and dynamic scenes. The approach achieves leading performance on the motchallenge benchmark, validating its effectiveness.

show abstract

Section: Relative Workmentioning

confidence: 99%

Section: Relative Workmentioning

confidence: 99%

Section: Relative Workmentioning

confidence: 99%

See 1 more Smart Citation

Application of ROI Feature Decomposition and Local Matching in Multi-Object Tracking

Yang,

Ban,

Liu

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Thus, MOT is known to have rapidly evolved and demonstrated great progress [20]. The MOT's application is very important in crowded places to evaluate people's movement in a video surveillance system [21]. The challenge in MODT is the association of data for tracking which still relies on handcrafted constraints like spatial proximity, motion, appearance, grouping, and so on, for determining affinities among the objects in various frames, as the objects emerge and disappear between the video frames.…”

Section: Introductionmentioning

confidence: 99%

ResNet50-deep affinity network for object detection and tracking in videos

2024

IJATEE

View full text Add to dashboard Cite

Multiple-object tracking (MOT) plays a crucial role in addressing many fundamental challenges within the fields of computer vision and video analysis. The majority of MOT methods rely on two primary processes: object detection and data association. Initially, each video frame is analyzed to detect objects, followed by a subsequent step that establishes correlations among the detected objects across multiple frames to generate their tracks. However, the data association for tracking often relies on manually defined criteria such as motion, appearance, grouping, and spatial proximity, among others. In the study, the ResNet50-deep affinity network (DAN) was introduced, which had been designed for the detection and tracking of objects in videos, including those that appear and disappear between frames. The proposed method was evaluated using the widely recognized MOT17 dataset to address MOT challenges. During the preprocessing phase, photometric distortion correction, frame expansion, and cropping were performed. The ResNet50 model was utilized to extract features. The DAN was employed to identify object appearances in video frames and to calculate their cross-frame affinities (CFA). The approach was compared with existing research, including DAN, ByteTrack, the graph neural network for simultaneous detection and tracking (GSDT), the reptile search optimization algorithm with deep learning-based multiple object detection and tracking (RSOADL-MODT), the center graph network (CGTracker), the hybrid motion model, FlowNet2-deep learning, and the super chained tracker (SCT), to validate the efficiency of theResNet50-DAN method. The ResNet50-DAN method achieved superior results, with a multiple-object tracking accuracy (MOTA) of 84.2%, an F1 score for identification metrics (IDF1) of 80.3%, 10,352 false positives (FP), and 1,284 identity switches (ID-Sw). The ResNet50-DAN method demonstrated higher MOTA compared to the existing approaches, including DAN, ByteTrack, GSDT, RSOADL-MODT, CGTracker, the hybrid motion model, FlowNet2-DL, and SCT.

show abstract

“…Yoo et al [ 22 ] designed an object constraint learning method to raise the tracking efficiency. Boragule et al [ 23 ] advanced a pixel-guided method to combine the joint-detection and tracking task for MOT.…”

Section: Introductionmentioning

confidence: 99%

Multi-Target Tracking Based on a Combined Attention Mechanism and Occlusion Sensing in a Behavior-Analysis System

Zhou

Chan

Qiu

et al. 2023

Sensors

View full text Add to dashboard Cite

Multi-object tracking (MOT) is a topic of great interest in the field of computer vision, which is essential in smart behavior-analysis systems for healthcare, such as human-flow monitoring, crime analysis, and behavior warnings. Most MOT methods achieve stability by combining object-detection and re-identification networks. However, MOT requires high efficiency and accuracy in complex environments with occlusions and interference. This often increases the algorithm’s complexity, affects the speed of tracking calculations, and reduces real-time performance. In this paper, we present an improved MOT method combining an attention mechanism and occlusion sensing as a solution. A convolutional block attention module (CBAM) calculates the weights of space and channel attention from the feature map. The attention weights are used to fuse the feature maps to extract adaptively robust object representations. An occlusion-sensing module detects an object’s occlusion, and the appearance characteristics of an occluded object are not updated. This can enhance the model’s ability to extract object features and improve appearance feature pollution caused by the short-term occlusion of an object. Experiments on public datasets demonstrate the competitive performance of the proposed method compared with the state-of-the-art MOT methods. The experimental results show that our method has powerful data association capability, e.g., 73.2% MOTA and 73.9% IDF1 on the MOT17 dataset.

show abstract

Pixel-Guided Association for Multi-Object Tracking

Cited by 10 publications

References 28 publications

Application of ROI Feature Decomposition and Local Matching in Multi-Object Tracking

Application of ROI Feature Decomposition and Local Matching in Multi-Object Tracking

ResNet50-deep affinity network for object detection and tracking in videos

Multi-Target Tracking Based on a Combined Attention Mechanism and Occlusion Sensing in a Behavior-Analysis System

Contact Info

Product

Resources

About