River floating pollutant identification method based on convolutional neural network

• Main Authors: SONG CHUNMEI, JIN JIXIN, WANG NING, ZHOU XIAOLEI, LIU SHOUZHENG, TAKEYOSHI, SONG YIGE, ZHANG NAN
• Format: Patent
• Language: Chinese; English
• Published: 20.12.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention relates to a river floating pollutant identification method based on a convolutional neural network. The method comprises the following steps: carrying out cutting preprocessing on a cleaned original river image; manually identifying the pollution condition of each piece of processed data, and taking the pollution condition as a label of the record; and training a convolutional neural network classification model by taking the processed images and labels as input. According to the method, the residual neural network is used, the degeneration phenomenon caused by the deep network is solved, and the designed network model can reach enough depth. Through fusion of space and channel attention mechanisms, local and global features are extracted, and more perfect and effective feature information can be obtained. According to the method, the defects of a traditional method in the aspect of data feature processing can be overcome, the recognition efficiency is improved, on the other hand, the training