Part-based visual tracking with spatially regularized correlation filters

Zhang, Dejun; Zhang, Zhao; Zou, Lu; Xie, Zhuyang; He, Fazhi; Wu, Yonghong; Tu, Zhigang

doi:10.1007/s00371-019-01634-5

Cited by 21 publications

(7 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The idea of structure and correlation learning can be adopted for related vision tasks other than 3D points processing. Hence, in the future, we plan to optimize our network and to apply the method to more vision scenarios [53][54][55].…”

Section: Discussionmentioning

confidence: 99%

PointSCNet: Point Cloud Structure and Correlation Learning Based on Space-Filling Curve-Guided Sampling

Chen

et al. 2021

Symmetry

Self Cite

View full text Add to dashboard Cite

Geometrical structures and the internal local region relationship, such as symmetry, regular array, junction, etc., are essential for understanding a 3D shape. This paper proposes a point cloud feature extraction network named PointSCNet, to capture the geometrical structure information and local region correlation information of a point cloud. The PointSCNet consists of three main modules: the space-filling curve-guided sampling module, the information fusion module, and the channel-spatial attention module. The space-filling curve-guided sampling module uses Z-order curve coding to sample points that contain geometrical correlation. The information fusion module uses a correlation tensor and a set of skip connections to fuse the structure and correlation information. The channel-spatial attention module enhances the representation of key points and crucial feature channels to refine the network. The proposed PointSCNet is evaluated on shape classification and part segmentation tasks. The experimental results demonstrate that the PointSCNet outperforms or is on par with state-of-the-art methods by learning the structure and correlation of point clouds effectively.

show abstract

Section: Discussionmentioning

confidence: 99%

PointSCNet: Point Cloud Structure and Correlation Learning Based on Space-Filling Curve-Guided Sampling

Chen

et al. 2021

Symmetry

Self Cite

View full text Add to dashboard Cite

show abstract

“…This paper proposes an end-to-end hand pose estimation network which takes hand point clouds as inputs and outputs locations of 3D hand joints based on structural relationship information. As shown in Figure 2, first of all, a set of 3D points are transformed from the hand depth image and are normalized in an Oriented Bounding Box (OBB) [47]. The hand feature encoder takes the standardized hand point clouds as inputs and uses PointNet [25] to extract features from it.…”

Section: Methodsmentioning

confidence: 99%

3D Capsule Hand Pose Estimation Network Based on Structural Relationship Information

Zhang

et al. 2020

Symmetry

Self Cite

View full text Add to dashboard Cite

Hand pose estimation from 3D data is a key challenge in computer vision as well as an essential step for human–computer interaction. A lot of deep learning-based hand pose estimation methods have made significant progress but give less consideration to the inner interactions of input data, especially when consuming hand point clouds. Therefore, this paper proposes an end-to-end capsule-based hand pose estimation network (Capsule-HandNet), which processes hand point clouds directly with the consideration of structural relationships among local parts, including symmetry, junction, relative location, etc. Firstly, an encoder is adopted in Capsule-HandNet to extract multi-level features into the latent capsule by dynamic routing. The latent capsule represents the structural relationship information of the hand point cloud explicitly. Then, a decoder recovers a point cloud to fit the input hand point cloud via a latent capsule. This auto-encoder procedure is designed to ensure the effectiveness of the latent capsule. Finally, the hand pose is regressed from the combined feature, which consists of the global feature and the latent capsule. The Capsule-HandNet is evaluated on public hand pose datasets under the metrics of the mean error and the fraction of frames. The mean joint errors of Capsule-HandNet on MSRA and ICVL datasets reach 8.85 mm and 7.49 mm, respectively, and Capsule-HandNet outperforms the state-of-the-art methods on most thresholds under the fraction of frames metric. The experimental results demonstrate the effectiveness of Capsule-HandNet for 3D hand pose estimation.

show abstract

“…Chakraborty and Meher [13] suggested a video-based ball detection and tracking methodology that facilitates extensive path analysis of the ball during basketball long shots. Tracking skeleton and objects is a challenging task, especially if the tracked objects are moving (e.g., jogging, walking, cycling) or brusque camera movements [14].…”

Section: Computer Vision-based Tracking and Timingmentioning

confidence: 99%

Video-Based Analysis and Reporting of Riding Behavior in Cyclocross Segments

Bock

Verstockt

2021

Sensors

View full text Add to dashboard Cite

Video-based trajectory analysis might be rather well discussed in sports, such as soccer or basketball, but in cycling, this is far less common. In this paper, a video processing pipeline to extract riding lines in cyclocross races is presented. The pipeline consists of a stepwise analysis process to extract riding behavior from a region (i.e., the fence) in a video camera feed. In the first step, the riders are identified by an Alphapose skeleton detector and tracked with a spatiotemporally aware pose tracker. Next, each detected pose is enriched with additional meta-information, such as rider modus (e.g., sitting on the saddle or standing on the pedals) and detected team (based on the worn jerseys). Finally, a post-processor brings all the information together and proposes ride lines with meta-information for the riders in the fence. The presented methodology can provide interesting insights, such as intra-athlete ride line clustering, anomaly detection, and detailed breakdowns of riding and running durations within the segment. Such detailed rider info can be very valuable for performance analysis, storytelling, and automatic summarization.

show abstract

Part-based visual tracking with spatially regularized correlation filters

Cited by 21 publications

References 45 publications

PointSCNet: Point Cloud Structure and Correlation Learning Based on Space-Filling Curve-Guided Sampling

PointSCNet: Point Cloud Structure and Correlation Learning Based on Space-Filling Curve-Guided Sampling

3D Capsule Hand Pose Estimation Network Based on Structural Relationship Information

Video-Based Analysis and Reporting of Riding Behavior in Cyclocross Segments

Contact Info

Product

Resources

About