Automated player identification and indexing using two-stage deep learning network

Abstract

American football games attract significant worldwide attention every year. Identifying players from videos in each play is also essential for the indexing of player participation. Processing football game video presents great challenges such as crowded settings, distorted objects, and imbalanced data for identifying players, especially jersey numbers. In this work, we propose a deep learning-based player tracking system to automatically track players and index their participation per play in American football games. It is a two-stage network design to highlight areas of interest and identify jersey number information with high accuracy. First, we utilize an object detection network, a detection transformer, to tackle the player detection problem in a crowded context. Second, we identify players using jersey number recognition with a secondary convolutional neural network, then synchronize it with a game clock subsystem. Finally, the system outputs a complete log in a database for play indexing. We demonstrate the effectiveness and reliability of player tracking system by analyzing the qualitative and quantitative results on football videos. The proposed system shows great potential for implementation in and analysis of football broadcast video.

Enhancing soccer pass receiver prediction in broadcast images through advanced deep learning techniques: A comprehensive study on model optimization and performance evaluation

“…Second, they use a secondary convolutional neural network to recognize player jersey numbers in order to identify them, and they synchronize this with a game clock subsystem. To index plays, the system outputs a complete log into a database [12]. The authors describe a "role-based" representation that dynamically modifies the relative roles of each player at every frame.…”

Optimised CNN Architectures for Handwritten Arabic Character Recognition

“…Optical Character Recognition (OCR) converts printed or handwritten text inside the image into a text [1]. OCR has many applications such as form processing [2,3], automatic indexing [4,5] bank checks processing [6,7], card scanner [8,9], and text translation [10,11]. The extracted text is usually used for further processing according to the user's needs.…”