Visual inspection method and system in warehouse logistics

• Main Authors: FENG LIYUAN, YANG NING, ZHENG YI, LIU RUIGANG, PU SHIXIAN, FENG WENHUA, LI ZHONGHUA, HONG CHAO, CHEN QINGYONG
• Format: Patent
• Language: Chinese; English
• Published: 06.02.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a visual detection method in warehouse logistics, and the method comprises the steps: constructing a material model, and carrying out the model training through a deep learning algorithm for material defect features; image information of a to-be-detected material is collected, lens focusing is controlled through an intelligent focusing module according to the material specification, and camera light source opening, photographing and volume measurement are controlled through a time sequence control module; obtaining the three-dimensional size of the material through the trained appearance detection module, and detecting the label through the label identification module to obtain a label detection result; the appearance defects of the carton are detected through the high-performance image processor, specific characters are recognized, detection information is fused, and a detection result is obtained. The invention further discloses a visual inspection system in warehouse logistics. A pl