Traffic sign detection model training method and device, storage medium and electronic equipment

• Main Authors: ZHOU KEYU, FANG DALONG, KONG DECONG, CHU WENBO, PENG PENGZHI
• Format: Patent
• Language: Chinese; English
• Published: 09.02.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention discloses a traffic sign detection model training method and device, a storage medium and electronic equipment, and relates to the technical field of information, and the method comprises the steps: constructing an initial traffic sign detection model; applying sparse constraint to the initial traffic sign detection model to obtain a sparse constraint function corresponding to the initial traffic sign detection model; calculating a filter correlation coefficient matrix of each layer of network in the initial traffic sign detection model; constructing a correlation constraint function corresponding to the initial traffic sign detection model according to the filter correlation coefficient matrix of each layer of network; and training the initial traffic sign detection model based on the sparse constraint function and the correlation constraint function, and constructing a preset traffic sign detection model. The compression ratio of the traffic sign detection model can be improved. 本发明公开了一种交通标志检测