TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications

by   Yu-Chuan Huang, et al.

Ball trajectory data are one of the most fundamental and useful information in the evaluation of players' performance and analysis of game strategies. Although vision-based object tracking techniques have been developed to analyze sport competition videos, it is still challenging to recognize and position a high-speed and tiny ball accurately. In this paper, we develop a deep learning network, called TrackNet, to track the tennis ball from broadcast videos in which the ball images are small, blurry, and sometimes with afterimage tracks or even invisible. The proposed heatmap-based deep learning network is trained to not only recognize the ball image from a single frame but also learn flying patterns from consecutive frames. TrackNet takes images with a size of 640×360 to generate a detection heatmap from either a single frame or several consecutive frames to position the ball and can achieve high precision even on public domain videos. The network is evaluated on the video of the men's singles final at the 2017 Summer Universiade, which is available on YouTube. The precision, recall, and F1-measure of TrackNet reach 99.7%, 97.3%, and 98.5%, respectively. To prevent overfitting, 9 additional videos are partially labeled together with a subset from the previous dataset to implement 10-fold cross-validation, and the precision, recall, and F1-measure are 95.3%, 75.7%, and 84.3%, respectively. A conventional image processing algorithm is also implemented to compare with TrackNet. Our experiments indicate that TrackNet outperforms conventional method by a big margin and achieves exceptional ball tracking performance. The dataset and demo video are available at


page 1

page 5

page 6

page 7


Deep-Learning-Based Computer Vision Approach For The Segmentation Of Ball Deliveries And Tracking In Cricket

There has been a significant increase in the adoption of technology in c...

A Badminton Recognition and Tracking System Based on Context Multi-feature Fusion

Ball recognition and tracking have traditionally been the main focus of ...

A Tracking System For Baseball Game Reconstruction

The baseball game is often seen as many contests that are performed betw...

Utilizing Temporal Information in DeepConvolutional Network for Efficient Soccer BallDetection and Tracking

Soccer ball detection is identified as one of the critical challenges in...

Utilizing Temporal Information in Deep Convolutional Network for Efficient Soccer Ball Detection and Tracking

Soccer ball detection is identified as one of the critical challenges in...

Intra-frame Object Tracking by Deblatting

Objects moving at high speed along complex trajectories often appear in ...

Sperm detection and tracking in phase-contrast microscopy image sequences using deep learning and modified CSR-DCF

Nowadays, computer-aided sperm analysis (CASA) systems have made a big l...

Please sign up or login with your details

Forgot password? Click here to reset