Search

Surface defect inspection of metal components plays a critical role in ensuring product quality, enhancing production efficiency, and reducing costs, with particular emphasis on the detection of small-sized surface defects to ensure the safety and reliability of metal components during their usage. Existing detection methods for small size defects on the surfaces of metal components have some shortcomings, such as low precision and poor real-time performance. To solve these two problems, this paper proposes a real-time defect detection method based on improved YOLO. Firstly, the LSandGlass (LSG) module is used to replace the residual module in the backbone network, which reduces information loss, eliminates the low-resolution feature layer, and minimizes semantic loss. The network then uses a lightweight Ghost convolution at the neck to extract the network features. In addition, the convolutional block attention mechanism (CBAM) module is added to improve the detection precision of small-size defects. Finally, soft intersection over union (SIoU) is used to further enhance target detection capability. The experiment was carried out a self-made hexagonal bolt data set of typical commonly used metal components. The experimental results show that compared to the original YOLOv5, the mAP (0.5) is improved by 5.7% to 95.50%, and the reasoning FPS is improved by 21 fps to 95 fps. These results indicate that the proposed LCG-YOLO improves the real-time detection performance of metal component surface defects.

The foreign object doped in the conveying belt is the most important factor to cause the tearing of the conveying belt. In order to solve the problem of low accuracy and poor real-time performance of foreign object detection, a new method based on improved Nanodet is proposed in this paper. The hardware of conveyor belt foreign object detection system is designed with ARM processor, and the system software is designed based on Android. It uses a conveyor belt foreign object detection system to detect foreign object. In order to detect foreign object images, a better Nanodet model is suggested. In order to increase detection accuracy while preserving processing speed, the model uses SIoU in place of the original position loss function. When the enhanced Nanodet model is applied to the conveyor belt foreign object detection system, the image of the foreign object appearing on the conveyor belt can be identified. The experimental findings indicate that a conveyor belt foreign object detection system based on an ARM processor and an Android operating system is capable of detecting foreign objects on conveyor belts with an average detection accuracy of 94.3%, a detection speed of 30 frames per second. The application of this method in the detection of foreign objects in conveyor belt can solve the shortcomings of existing methods. At the same time meet the requirements of the conveyor belt foreign object detection site environment.

The existing object detection methods are facing significant challenges when applied to marine environments, such as underwater image degradation caused by absorption and scattering of light, and domain transfer in water bodies with different water qualities. In this letter, we propose a marine organism detection framework to improve the detection performance and the domain generalization performance. First, a double domains data augmentation is proposed. This method combines underwater image enhancement and water quality transfer to improve the domain diversity of the original dataset. Second, we utilize the self-attention operations and the convolution to improve the detection performance of the YOLOv7, fully utilizing the advantages of self-attention and convolutional computation. Meanwhile, this model uses SIoU loss to accelerate convergence speed and improve the regression. Experiments on the URPC2019 and URPC2020 datasets show that the proposed object detection method achieves a mean average precision of 82.3% and 83.6%, respectively, which is superior to all other methods used for comparison.

A large number of insulators play an important role in insulating and supporting complex power grids, and they are constantly exposed to challenges such as lightning strikes and contamination from the external environment. Only by accurately detecting insulator damage can potential safety hazards and equipment damage due to damaged insulators be avoided in time. Aiming at the problems of low accuracy and large model computation of existing insulator and defect detection algorithms, this paper proposes the insulator and defect detection model YOLO-S (YOLO-Small). First, the PAN structure in Neck uses lightweight convolutional GSConv instead of the standard convolutional Conv, introduces GSbottleneck on the basis of GSConv, and uses the method of OSA to design the cross-level partial network GSCSP module (VoV-GSCSP). The use of VoV-GSCSP instead of the C3 module in Neck reduces the computational effort and maintains the accuracy. Secondly, a new attention module, MaECA (MainECA), is designed based on the ECA attention mechanism to enhance target perception. After that, the SILU function in the SPPF in YOLOv5s is replaced with the Mish function, HardSwish function, and ReLU function, respectively, and the results show that the replacement of the Mish function (MishSPPF) is more effective in preventing the distortion of the image caused by image cropping and scaling, and thus improving the accuracy. Finally, the SIoU loss function is used to replace the original loss function CIoU, which improves the number of transmitted frames per second and the detection accuracy of the pictures. The mAP of YOLO-S is 4.2% higher than that of YOLOv5s, the detection accuracy is improved by 2.1%, and the model parameter computation is reduced by 6.0%, which still gives YOLO-S a higher recognition accuracy when compared with existing detection algorithms under the same conditions.

Steel strip can develop surface defects during manufacturing and processing, affecting structural integrity and usability. These defects can be caused by both internal and external factors. However, traditional manual error detection techniques do not meet today’s accuracy standards. Therefore, an improved version of the YOLOv7 algorithm for steel strip surface defect detection is proposed in this work. A lightweight and inexpensive Coordinate Attention (CA) mechanism is built into the structure of the head of YOLOv7. The SCYLLA-Intersection over Union (SIoU) loss function is used to improve detection efficiency. Furthermore, to enhance the dataset, a vertical flip augmentation technique is applied to create the optimal model:YOLOv7-CSF through fusion of CA and SIoU. It has been observed in the experimental findings that the modified YOLOv7-CSF algorithm’s mAP value in the detection is 4.09% better than that of the original YOLOv7 method, reaching 66.1% and a maximum of 96.9% accuracy in a single category of defects. The efficacy and superiority of the updated model are shown by comparing it with the recently announced YOLOv8, other steel strip datasets and other hyper-parameter tuned models, providing a novel way for daily surface defect detection on steel strips.