3D Multiview Basketball Players Detection and Localization Based on Probabilistic Occupancy

Yang, Yukun; Xu, Min; Wu, Wanneng; Zhang, Ruiheng; Peng, Yu

doi:10.1109/dicta.2018.8615798

Cited by 16 publications

(12 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…where P z represents the number of correctly detected goals and P j represents the number of detected goals. e number of shots is set to 45. e methods of [8], the methods of [9], and the proposed methods are used to detect the basketball shooting training goal image, respectively. e comparison results of the detection accuracy of basketball shooting training goals of different methods are calculated according to formula (25), as shown in Figure 6.…”

Section: Analysis Of the Accuracy Of Goal Detection In Basketballmentioning

confidence: 99%

“…This method has certain validity. Yang et al [ 9 ] proposed a three-dimensional multiviewpoint basketball player detection and location method based on probability occupancy. Combine player detection based on deep learning and player positioning based on occupancy rate to extract the characteristics of three-dimensional multiview basketball players.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Concrete Application of Computer Virtual Image Technology in Modern Sports Training

Chi

Li²

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The efficiency of basketball shooting training has always been an urgent problem to be solved in basketball sports. Applying computer virtual image technology to basketball sports training is the key to improve basketball shooting ability and improve the effect of basketball sports training. Therefore, based on the design of basketball shooting automatic recognition system based on the background difference method, this study puts forward the specific application of computer virtual image technology in modern sports training. By analyzing the techniques of image denoising, image detection, and image calibration, a goal detection algorithm for modern sports basketball shooting training is designed. Firstly, the camera is used for image capture, the RGB image is converted into gray image, and the median filter is used to suppress the noise in the image. Then, the background difference method is used to detect the moving region, and the background modeling is combined with the mean method. After obtaining the background reference model, the image is differentiated, the gray image after image difference is binarized, and then the binary image is postprocessed by morphological middle closure operation. Finally, the image calibration technology is used to extract the basketball feature information. Through the region segmentation algorithm, the basketball shooting part is segmented and judged, so as to realize the basketball shooting training goal detection. The experimental results show that the proposed method has a good effect on basketball shooting training goal detection and can effectively improve the detection accuracy and efficiency.

show abstract

Section: Analysis Of the Accuracy Of Goal Detection In Basketballmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Concrete Application of Computer Virtual Image Technology in Modern Sports Training

Chi

Li²

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Multiple players tracking system generally consists of two steps: detecting players for each frame and then linking the detections into trajectories. The former part is our previous work that has been published as a conference paper [42]. As shown in Figure 2, given a basketball video, we first detect players in 2D images with Mask RCNN [43] frame by frame and then convert the input frames into binary images with foreground-background separation.…”

Section: An Overview Of the Proposed Multiple Players Tracking Frameworkmentioning

confidence: 99%

“…Since the main difference between our proposed method and the existing KSP tracking approach is that we consider the appearance features while the original KSP does not, we thus name our method KSP-AF. The pipline of the multiple-player tracking system based on the KSP-AF tracking method mainly consists of three parts: (1) 3D player detection [42], (2) feature extraction, and (3) tracking by k-shortest paths with appearance feature (KSP-AF). The input of the whole system is multi-view basketball videos, and the output is multiple player trajectories.…”

Section: An Overview Of the Proposed Multiple Players Tracking Frameworkmentioning

confidence: 99%

Multi-Player Tracking for Multi-View Sports Videos with Improved K-Shortest Path Algorithm

Liang

Yang

et al. 2020

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Sports analysis has recently attracted increasing research efforts in computer vision. Among them, basketball video analysis is very challenging due to severe occlusions and fast motions. As a typical tracking-by-detection method, k-shortest paths (KSP) tracking framework has been well used for multiple-person tracking. While effective and fast, the neglect of the appearance model would easily lead to identity switches, especially when two or more players are intertwined with each other. This paper addresses this problem by taking the appearance features into account based on the KSP framework. Furthermore, we also introduce a similarity measurement method that can fuse multiple appearance features together. In this paper, we select jersey color and jersey number as two example features. Experiments indicate that about 70% of jersey color and 50% of jersey number over a whole sequence would ensure our proposed method preserve the player identity better than the existing KSP tracking method.

show abstract

“…More recently, like for general object detection, CNNbased methods have also been the dominant trend for detecting sports players. In [34] a shallow CNN was trained to detect players on a hockey field, while others use pretrained networks like Mask R-CNN for handball videos [30] and basketball videos [41], or YOLO for handball videos [6]. In [43] a reverse connected convolutional neural network (RC-CNN) is proposed for player detection.…”

Section: Related Workmentioning

confidence: 99%

Multimodal and multiview distillation for real-time player detection on a football field

Cioppa

Deliège

Huda

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Monitoring the occupancy of public sports facilities is essential to assess their use and to motivate their construction in new places. In the case of a football field, the area to cover is large, thus several regular cameras should be used, which makes the setup expensive and complex. As an alternative, we developed a system that detects players from a unique cheap and wide-angle fisheye camera assisted by a single narrow-angle thermal camera. In this work, we train a network in a knowledge distillation approach in which the student and the teacher have different modalities and a different view of the same scene. In particular, we design a custom data augmentation combined with a motion detection algorithm to handle the training in the region of the fisheye camera not covered by the thermal one. We show that our solution is effective in detecting players on the whole field filmed by the fisheye camera. We evaluate it quantitatively and qualitatively in the case of an online distillation, where the student detects players in real time while being continuously adapted to the latest video conditions.

show abstract

3D Multiview Basketball Players Detection and Localization Based on Probabilistic Occupancy

Cited by 16 publications

References 20 publications

Concrete Application of Computer Virtual Image Technology in Modern Sports Training

Concrete Application of Computer Virtual Image Technology in Modern Sports Training

Multi-Player Tracking for Multi-View Sports Videos with Improved K-Shortest Path Algorithm

Multimodal and multiview distillation for real-time player detection on a football field

Contact Info

Product

Resources

About