HDS-YOLOv5: An improved safety harness hook detection algorithm based on YOLOv5s

Abstract

<abstract> <p>Improperly using safety harness hooks is a major factor of safety hazards during power maintenance operation. The machine vision-based traditional detection methods have low accuracy and limited real-time effectiveness. In order to quickly discern the status of hooks and reduce safety incidents in the complicated operation environments, three improvements are incorporated in YOLOv5s to construct the novel HDS-YOLOv5 network. First, HOOK-SPPF (spatial pyramid pooling fast) feature extraction module replaces the SPPF backbone network. It can enhance the network's feature extraction capability with less feature loss and extract more distinctive hook features from complex backgrounds. Second, a decoupled head module modified with confidence and regression frames is implemented to reduce negative conflicts between classification and regression, resulting in increased recognition accuracy and accelerated convergence. Lastly, the Scylla intersection over union (SIoU) is employed to optimize the loss function by utilizing the vector angle between the real and predicted frames, thereby improving the model's convergence. Experimental results demonstrate that the HDS-YOLOv5 algorithm achieves a 3% increase in mAP@0.5, reaching 91.2%. Additionally, the algorithm achieves a detection rate of 24.0 FPS (frames per second), demonstrating its superior performance compared to other models.</p> </abstract>

YOLOv5-based Student Counting Software Design

“…YOLOv5 introduces the Focus structure, a special design that plays a key role in processing the input image for feature extraction. Specifically, it operates by cropping and splitting the input feature map into four sub-maps and interleaving and stacking these four sub-maps [4].The Focus structure effectively reduces the complexity and the number of parameters of the network. The Focus structure plays an important role in the YOLOv5 algorithm,this design not only improves the efficiency and accuracy of the model, but also enhances the detection of small targets.…”

“…Figure 3. Training Results ChartEnhancement with Mosaic data improves the performance and generalization of the model in target detection tasks.2.2.5 Multiple positive sample matchingMulti-positive sample matching is a key technique in target detection in YOLOv5, which is used to effectively deal with the problem of matching multiple target objects existing in the same lattice[4]. Usually, there may exist multiple target objects in a lattice, and traditional target detection algorithms tend to match only one of the targets in this case, resulting in the problem of missed or false…”