YO-CSA-T: A Real-time Badminton Tracking System Utilizing YOLO Based on Contextual and Spatial Attention

2025-01-11

AI Summary

Real-time 3D trajectory tracking of shuttlecocks is challenging due to their high-speed motion, small size, low contrast, and visual occlusions—especially under competitive human–robot adversarial settings. Method: This paper proposes a real-time shuttlecock trajectory tracking system tailored for human–robot competition. It introduces YO-CSA, a YOLOv8s-based detection network incorporating both contextual and spatial attention mechanisms. Furthermore, it establishes a closed-loop architecture integrating stereo geometric mapping, temporal-driven 3D prediction, and cross-domain (2D–3D) feedback constraints. Contribution/Results: YO-CSA achieves 90.43% mAP@0.75—significantly outperforming YOLOv8s and YOLOv8n. The full system operates robustly at over 130 fps across 12 real-world test sequences, achieving, for the first time, low-latency, robust 3D trajectory tracking meeting stringent requirements for competitive human–robot adversarial scenarios.

Technology Category

• Computer Vision: Motion & Tracking
• Multiagent Systems: Adversarial Agents
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The 3D trajectory of a shuttlecock required for a badminton rally robot for human-robot competition demands real-time performance with high accuracy. However, the fast flight speed of the shuttlecock, along with various visual effects, and its tendency to blend with environmental elements, such as court lines and lighting, present challenges for rapid and accurate 2D detection. In this paper, we first propose the YO-CSA detection network, which optimizes and reconfigures the YOLOv8s model's backbone, neck, and head by incorporating contextual and spatial attention mechanisms to enhance model's ability in extracting and integrating both global and local features. Next, we integrate three major subtasks, detection, prediction, and compensation, into a real-time 3D shuttlecock trajectory detection system. Specifically, our system maps the 2D coordinate sequence extracted by YO-CSA into 3D space using stereo vision, then predicts the future 3D coordinates based on historical information, and re-projects them onto the left and right views to update the position constraints for 2D detection. Additionally, our system includes a compensation module to fill in missing intermediate frames, ensuring a more complete trajectory. We conduct extensive experiments on our own dataset to evaluate both YO-CSA's performance and system effectiveness. Experimental results show that YO-CSA achieves a high accuracy of 90.43% mAP@0.75, surpassing both YOLOv8s and YOLO11s. Our system performs excellently, maintaining a speed of over 130 fps across 12 test sequences.

Problem

• Real-time Tracking
• Badminton Trajectory
• Visual Interference

Innovation

• Real-time Tracking
• YOLO Innovation
• High-speed Object Detection