[3Win5] Poster session 3

[3Win5-103] Enhancing Sports Ball Detection and Tracking Baseline

〇Shuhei Tarashima^1,2, Muhammad Abdul Haq², Yushan Wang², Norio Tagawa² (1.NTT Communications, 2.Tokyo Metropolitan University)

Keywords:Sports Video Analysis, Object Detection, Object Tracking, Sports Ball, Dataset

In this work, we aim to enhance the sports ball detection and tracking baseline introduced in our previous study. Specifically, we replace the standard convolution operations with depth-wise separable convolutions to reduce model parameters and computational costs. Additionally, we adjust the number of input and output frames and incorporate multi-dataset pretraining to boost detection and tracking performance. Experimental results demonstrate that our approach successfully decreases model parameters and computational costs while achieving superior performance compared to existing methods especially on the Tennis dataset.