A crayfish quality detection model using YOLOv4 deep learning algorithm is designed. The algorithm is optimized in terms of network architecture, data processing, and feature extraction. The crayfish image data is collected by video capture and image expansion, and then the data is annotated by LableImage platform. The model is trained under the Darknet framework. By contrast, the final model performance is higher than other common target detection models, and the detection accuracy rate is 97.8%, the average detection time is 37 ms, which proves that the method can effectively detect the quality of crayfish in the production process.