Augmented haar cascade classifier for real-time ball detection in humanoid robots under dynamic environments

This study proposes an Augmented Haar Cascade Classifier (AHCC) to enhance real-time ball detection for humanoid robots operating in dynamic environments. The method integrates Convex Hull mapping, HSV-based segmentation, and Hough Circle validation to overcome challenges such as fluctuating illumination, complex backgrounds, and partial occlusions. Experiments were conducted entirely on a CPU-only Intel NUC platform running ROS without GPU acceleration, using a dataset containing variations in lighting, orientation, scale, and background clutter. Compared with baseline models (standard Haar Cascade Classifier (HCC) and YOLOv5) the proposed AHCC achieved 97% accuracy, 83% recall, 97% precision, and an 89% F1-score, while requiring only 0.00849 s per frame with 8.97% memory usage. Although YOLOv5 reached 99% accuracy, it demanded higher computational resources (0.0344 s per frame, 22.3% memory usage), limiting its practicality for embedded robotic systems. The AHCC therefore offers an optimal balance between detection reliability and computational efficiency, outperforming traditional HCC and providing a lightweight alternative to GPU-dependent detectors such as Tiny-YOLO and MobileNet-SSD.