Method and system for monitoring periphytic algae based on binocular image

• Main Authors: LIU YUNBING, PENG YU, XU JIE, ZHENG HAOYING, LI RUIWEN, LI BIN, FANG BIAO, LIU HAOBING, ZHENG YIFAN, WANG PENGFEI, HUANG MIANDA, LIU XINYONG, XIAO XINZONG, NING HONGZHANG, WANG YINGCAI
• Format: Patent
• Language: Chinese; English
• Published: 03.05.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention provides a periphytic algae monitoring method and system based on binocular images, and belongs to the field of water ecological environment monitoring, and the method comprises the steps: S1, collecting periphytic algae image data shot by an underwater binocular camera, carrying out mask labeling, and building a data set; s2, training a deep learning-based periphytic algae semantic segmentation model by adopting the data set; s3, binocular sequence image data are collected, correction processing is carried out, binocular image data are reconstructed, and a reconstructed binocular image is obtained; s4, performing periphytic algae coverage detection and periphytic algae growth height detection on the reconstructed binocular image by using the trained periphytic algae semantic segmentation model; and S5, calculating a periphytic algae monitoring index according to the periphytic algae coverage and the growth height of the periphytic algae. According to the method, the periphytic algae are monitor