During the production of strip steel, there are often some defects on the surface of the product. Therefore, the detection of such defect is the key to produce high-quality products. At the same time, the surface defects of the steel cause huge economic losses to the high-tech industry. A steel surface defect detection algorithm based on improved YOLO-V7 is proposed to address the problems of low detection speed and poor detection accuracy of traditional steel surface defect detection methods. First, we use the de-weighted BiFPN structure to make full use of the deep, shallow and original feature information to strengthen feature fusion, reduce the loss of feature information during the convolution process, and improve the detection accuracy. Secondly, the ECA attention mechanism is combined in the backbone part to strengthen the important feature channels. Finally, the original bounding box loss function is replaced by the SIoU loss function, where the penalty term is redefined by taking the vector angle between the required regressions into account. The experimental results show that the improved model proposed in this paper has higher performance compared with other comparison models. Based on our experiments, the proposed model yields 80.2% mAP on the GC10-DET dataset and 81.9% mAP on the NEU-DET dataset with high detection speed, which is better than other existing models.

Since UAVs usually fly at higher altitudes, resulting in a more significant proportion of small targets after imaging, this poses a challenge to the target detection algorithm at this stage; in addition, the high-speed flight of UAVs causes a sense of blurring on the detected objects, which leads to difficulties in target feature extraction. To address the two problems presented above, we propose a UAV target detection algorithm based on improved YOLOv8. First, the small target detection structure (STC) is embedded in the network, which acts as a bridge between shallow and deep features to improve the collection of semantic information of small targets and enhance detection accuracy. Second, using the feature of global information of UAV imaging-focused targets, the global attention GAM is introduced to the bottom layer of YOLOv8m’s backbone to prevent the loss of image feature information during sampling and thus increase the algorithm’s detection performance by feeding back feature information of different dimension. The modified model effectively increases the detection of tiny targets with an mAP value of 39.3%, which is 4.4% higher than the baseline approach, according to experimental results on the VisDrone2021 dataset, and outperforms mainstream algorithms such as SSD and YOLO series, effectively increasing the detection performance of UAVs for small targets.

Aiming at the problems of tiny targets, large target scale changes, and background information interference in target detection of UAV(Unmanned Aerial Vehicle) aerial images, a revised UAV target detection algorithm MCA-YOLOv7 based on YOLOv7 is proposed, and the algorithm advances from the following points: optimizing the FPN(Feature Pyramid Networks) structure to increase the small-target detection layer, and boosting the network’s detection ability for small targets. To enhance the multi-scale feature extraction capability, the Efficient Multi-Scale Attention(EMA) is added. In order to reduce the complexity of the model and reduce the confusion of background information, the context aggregation block (CABlock) was introduced and improved, and an effective context aggregation block (ECABlock) was proposed. The loss function CIoU is enhanced and a new loss function FCIoU is proposed, which accelerates the convergence speed of the model, and obtains more accurate regression results. The experimental results demonstrate that the MCA-YOLOv7 model reduces the number of model parameters by 4.7 M and increases the average accuracy (mAP@0.5) by 2.9% when compared to YOLOv7 on the VisDrone2019 dataset. The new algorithm is more capable of handling situations involving UAV aerial photography.

Since the UAV is far away from the detected target when performing target detection at high altitudes, there is a significant difference in the size of the detected object, and there are problems such as the detected target being blocked by the object. This paper proposed an improved algorithm BDH-YOLO for UAV high-altitude small target detection based on YOLOv8s. The backbone network of YOLOv8s is used, and the weighted bidirectional feature pyramid network (BiFPN) is combined with the backbone network to enhance the integration of multi-level features and obtain more multi-scale semantic information. Deal with multiple downsampling of the feature map will lead to the reduction of the resolution of the feature map, which will make the pixels on the feature map overlap, thus losing a large amount of spatial information, a dynamic detection head DyHead (Dynamic Head) combined with self-attention is introduced, which significantly improves the performance of the object detector by combining the perception capabilities of the three dimensions of scale perception, spatial perception, and task perception. Experimental results show that on the VisDrone2019-DET dataset, Compared with the YOLOv8s model, the BDH-YOLO model has an average accuracy (mAP@0.5) improvement of 3 targets than other mainstream models.

Aiming at the problem that traditional surface detection is easily affected by complex industrial environments and cannot extract effective features, a deep learning-based knowledge distillation anomaly detection model is proposed. Firstly, a pre-trained teacher network was used to transfer knowledge of normal samples to the student network in the training phase. In the testing phase, defect detection was achieved based on the feature differences in the output of the teacher-student network for abnormal samples. Secondly, the attention mechanism module and the feature fusion module were added to the teacher network, which enhanced the detection ability of various defects of different sizes and increased the difference in output features between the teacher network and the student network. Finally, the defect image was located at the pixel level. Compared with the advanced knowledge distillation methods, the experimental results of the proposed model on the detection on MVTecAD and the anomaly localization on MVTecAD showed that the method in this paper improved to 90.3% and 90.1% on AUROC respectively, which verified the effectiveness of the method.

Existing projection-based person re-identification methods usually suffer from long time training, high dimension of projection matrix, and low matching rate. In addition, the intra-class instances may be much less than the inter-class instances when a training data set is built. To solve these problems, a novel relative distance metric leaning based on clustering centralization and projection vectors learning is proposed. When constructing training data set, the images of a same target person are clustering centralized with fuzzy c-means). The training data sets are built by these clusters in order to alleviate the imbalanced data problem of the training data sets. In addition, during learning projection matrix, the resulted projection vectors can be approximately orthogonal by using an iteration strategy and a conjugate gradient projection vector learning method to update training data sets. Experimental results show that the proposed algorithm has higher efficiency. The matching rate can be significantly improved, and the time of training is much shorter than most of existing algorithms of person re-identification.