Search Results (3)

Our previous work introduced the LW-YOLOv4-tiny and the LW-ResNet18 models by replacing traditional convolution with the Ghost Conv to achieve rapid object detection and steering angle prediction, respectively. However, the entire object detection and steering angle prediction process has encountered a speed limit problem. Therefore, this study aims to significantly speed up the object detection and the steering angle prediction simultaneously. This paper proposes the GhostBottleneck approach to speed the frame rate of feature extraction and add the SElayer method to maintain the existing precision of object detection, which constructs an enhanced object detection model abbreviated as LWGSE-YOLOv4-tiny. In addition, this paper also conducted depthwise separable convolution to simplify the Ghost Conv as depthwise separable and ghost convolution, which constructs an improved steering angle prediction model abbreviated as LWDSG-ResNet18 that can considerably speed up the prediction and slightly increase image recognition accuracy. Compared with our previous work, the proposed approach shows that the GhostBottleneck module can significantly boost the frame rate of feature extraction by 9.98%, and SElayer can upgrade the precision of object detection slightly by 0.41%. Moreover, depthwise separable and ghost convolution can considerably boost prediction speed by 20.55% and increase image recognition accuracy by 2.05%. Full article

Particleboard surface defects have a significant impact on product quality. A surface defect detection method is essential to enhancing the quality of particleboard because the conventional defect detection method has low accuracy and efficiency. This paper proposes a YOLO v5-Seg-Lab-4 (You Only Look Once v5 Segmentation-Lab-4) model based on deep learning. The model integrates object detection and semantic segmentation, which ensures real-time performance and improves the detection accuracy of the model. Firstly, YOLO v5s is used as the object detection network, and it is added into the SELayer module to improve the adaptability of the model to receptive field. Then, the Seg-Lab v3+ model is designed on the basis of DeepLab v3+. In this model, the object detection network is utilized as the backbone network of feature extraction, and the expansion rate of atrus convolution is reduced to the computational complexity of the model. The channel attention mechanism is added onto the feature fusion module, for the purpose of enhancing the feature characterization capabilities of the network algorithm as well as realizing the rapid and accurate detection of lightweight networks and small objects. Experimental results indicate that the proposed YOLO v5-Seg-Lab-4 model has mAP (Mean Average Precision) and mIoU (Mean Intersection over Union) of 93.20% and 76.63%, with a recognition efficiency of 56.02 fps. Finally, a case study of the Huizhou particleboard factory inspection is carried out to demonstrate the tiny detection accuracy and real-time performance of this proposed method, and the missed detection rate of surface defects of particleboard is less than 1.8%. Full article

Defect detection is the most important step in the postpartum reprocessing of kiwifruit. However, there are some small defects difficult to detect. The accuracy and speed of existing detection algorithms are difficult to meet the requirements of real-time detection. For solving these problems, we developed a defect detection model based on YOLOv5, which is able to detect defects accurately and at a fast speed. The main contributions of this research are as follows: (1) a small object detection layer is added to improve the model’s ability to detect small defects; (2) we pay attention to the importance of different channels by embedding SELayer; (3) the loss function CIoU is introduced to make the regression more accurate; (4) under the prerequisite of no increase in training cost, we train our model based on transfer learning and use the CosineAnnealing algorithm to improve the effect. The results of the experiment show that the overall performance of the improved network YOLOv5-Ours is better than the original and mainstream detection algorithms. The mAP@0.5 of YOLOv5-Ours has reached 94.7%, which was an improvement of nearly 9%, compared to the original algorithm. Our model only takes 0.1 s to detect a single image, which proves the effectiveness of the model. Therefore, YOLOv5-Ours can well meet the requirements of real-time detection and provides a robust strategy for the kiwi flaw detection system. Full article