Garbage classification and detection method based on improved YOLOX
Fei Ouyang, Xu Wu, Shanwen Wang, Dongsheng Xiang · Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics · 2022
In order to solve the problems of low efficiency and strong subjectivity of manual garbage classification, this paper proposes a garbage classification detection method based on improved YOLOX to improve the efficiency and accuracy of garbage classification. By training YOLOX network with self-made garbage classification dataset, garbage detection and classification can be realized. In order to get better test results, a YOLOX algorithm with ECA-Net attention mechanism is proposed to improve feature extraction ability and information transmission among features. Experimental results show that [email protected] of the improved algorithm is 89.2%, and the number of detected frames per second is 63.1. Compared with YOLOX algorithm, [email protected] improves by 3.3%, while the number of detected frames per second only decreases by 0.3. Compared with the original algorithm, the accuracy is greatly improved without loss of performance, which can meet the requirements of real-time detection.