Semaphore Recognition Using Deep Learning

This study explored the application of deep learning models for signal flag recognition, comparing YOLO11 with basic CNN, ResNet18, and DenseNet121. Experimental results demonstrated that YOLO11 outperformed the other models, achieving superior performance across all common evaluation metrics. The confusion matrix further confirmed that YOLO11 exhibited the highest classification accuracy among the tested models. Moreover, by integrating MediaPipe's human posture data with image data to create multimodal inputs for training, it was observed that the posture data significantly enhanced the model's performance. Leveraging MediaPipe's posture data for annotation generation and model training enabled YOLO11 to achieve an impressive 99% accuracy on the test set. This study highlights the effectiveness of YOLO11 for flag signal recognition tasks. Furthermore, it demonstrates that when handling tasks involving human posture, MediaPipe not only enhances model performance through posture feature data but also facilitates data processing and contributes to validating prediction results in subsequent stages.