Development of a deep learning-based system in Python 3.9 with YOLOv5: A case study on real-time fish counting based on classification

Abstract

This study developed a real-time fish classification and counting system for six types of fish using the YOLOv5 machine learning model with high accuracy. The system achieved an F1-score of 0.87 and a precision confidence curve with an all-classes value of 1.00 at a confidence level of 0.920, demonstrating the model’s reliability in object detection and classification. Real-time testing showed that the system could operate quickly and accurately under various environmental conditions with an average inference speed of 30 FPS. However, several challenges remain, such as sensitivity to low-light conditions. Overall, this system has significant potential for applications in aquaculture, particularly for automated and real-time fish monitoring. With compatibility through the ONNX format, the system is also flexible for integration into IoT-based devices or cross-platform applications, providing a solid foundation for further advancements in computer vision-based fish monitoring technology.