Light Cascaded Convolutional Neural Networks for Accurate Player Detection

TL;DR

This paper introduces a lightweight cascaded CNN for real-time, accurate player detection in sports, capable of handling challenging conditions with significantly fewer parameters than traditional CNNs.

Contribution

The paper proposes a novel cascaded CNN architecture that is efficient, accurate, and suitable for real-time sports player detection with low memory usage.

Findings

Achieves state-of-the-art accuracy on basketball and soccer datasets.

Uses 1000x fewer parameters than conventional CNNs.

Performs well under challenging conditions like motion blur and lighting changes.

Abstract

Vision based player detection is important in sports applications. Accuracy, efficiency, and low memory consumption are desirable for real-time tasks such as intelligent broadcasting and automatic event classification. In this paper, we present a cascaded convolutional neural network (CNN) that satisfies all three of these requirements. Our method first trains a binary (player/non-player) classification network from labeled image patches. Then, our method efficiently applies the network to a whole image in testing. We conducted experiments on basketball and soccer games. Experimental results demonstrate that our method can accurately detect players under challenging conditions such as varying illumination, highly dynamic camera movements and motion blur. Comparing with conventional CNNs, our approach achieves state-of-the-art accuracy on both games with 1000x fewer parameters (i.e., it is light}.