Aiming at the problems of inefficient detection caused by traditional manual inspection and unclear features in metal surface defect detection, an improved metal surface defect detection technology based on the You Only Look Once (YOLO) model is presented. The shallow features of the 11th layer in the Darknet-53 are combined with the deep features of the neural network to generate a new scale feature layer using the basis of the network structure of YOLOv3. Its goal is to extract more features of small defects. Furthermore, then, K-Means++ is used to reduce the sensitivity to the initial cluster center when analyzing the size information of the anchor box. The optimal anchor box is selected to make the positioning more accurate. The performance of the modified metal surface defect detection technology is compared with other detection methods on the Tianchi dataset. The results show that the average detection accuracy of the modified YOLO model is 75.1%, which ia higher than that of YOLOv3. Furthermore, it also has a great detection speed advantage, compared with faster region-based convolutional neural network (Faster R-CNN) and other detection algorithms. The improved YOLO model can make the highly accurate location information of the small defect target and has strong real-time performance.

In the process of steel production, the defects on the surface of steel will adversely affect the subsequent processing of a product. Accurate detection of such defects is the key to improve production efficiency and economic benefits. In this paper, an end-to-end steel surface defect detection and size measurement system based on the YOLOv5 model is designed. Firstly, in consideration of the defect location and direction correlation in the production process, a coordinate attention mechanism is added at the head of YOLOv5 to strengthen the spatial correlation of the steel surface and an adaptive anchor box generation method based on defect shape difference feature is proposed, which realizes the detection of three main types of defects on the Pytorch deep learning framework. Secondly, BiFPN is used to strengthen the feature fusion and a transformer encoder is added to improve the performance of detecting small defects. Thirdly, calculate the conversion ratio between the pixel and the actual size according to the standard reference specimen and obtain the actual size through the pixel statistics of the defect area to achieve pixel level size measurement. Finally, the steel surface defect detection and size measurement system are designed in this paper, which consist of various hardware, related measurement, and detection algorithms. According to the experimental results, the comprehensive defect detection accuracy of this method reaches 93.6%, of which the scratch detection accuracy reaches 95.7%. The detection speed reaches 133 fps and the defect size measurement accuracy reaches 0.5 mm. Experimental result shows that the defect detection and size measurement system designed in this paper can accurately detect and measure various industrial production defects and can be applied to the actual production process.

Recently, people’s demand for action recognition has extended from the initial high classification accuracy to the high accuracy of the temporal action detection. It is challenging to meet the two requirements simultaneously. The key to behavior recognition lies in the quantity and quality of the extracted features. In this paper, a two-stream convolutional network is used. A three-dimensional convolutional neural network (3D-CNN) is used to extract spatiotemporal features from the consecutive frames. A two-dimensional convolutional neural network (2D-CNN) is used to extract spatial features from the key-frames. The integration of the two networks is excellent for improving the model’s accuracy and can complete the task of distinguishing the start–stop frame. In this paper, a multi-scale feature extraction method is presented to extract more abundant feature information. At the same time, a multi-task learning model is introduced. It can further improve the accuracy of classification via sharing the data between multiple tasks. The experimental result shows that the accuracy of the modified model is improved by 10%. Meanwhile, we propose the confidence gradient, which can optimize the distinguishing method of the start–stop frame to improve the temporal action detection accuracy. The experimental result shows that the accuracy has been enhanced by 11%.