Exploring the application of automatic distance measurement for standing long jump based on image denoising and area detection.

This article focuses on the development of an automated, image recognition-based system for measuring standing long jump distances to overcome the subjectivity and inefficiency of traditional manual methods. The system integrates image denoising techniques—specifically an improved wavelet threshold denoising combined with morphological operations—and convolutional neural network (CNN) algorithms for accurate edge detection and feature extraction, achieving a maximum measurement accuracy of 96.23% and a minimum absolute error of 0.01 cm. Experimental results demonstrate that the proposed method outperforms conventional filters and existing CNN models in accuracy, stability, and processing time, with effective application in both indoor and outdoor environments. The study suggests future enhancements through deep learning and video analysis techniques to improve robustness under varying environmental conditions and to enable real-time monitoring of long jump phases.