Substation meter detection and recognition method based on lightweight deep learning model

Abstract

With the advancement of robotics, intelligent robots are widely used in substation inspections. In view of the problem that the parameters of the deep learning model are too large, and the performance of embedded devices is limited, this paper proposes a meter detection and recognition method based on a lightweight deep learning model, which provides support for deploying the model to the substation intelligent inspection robot. First perform target detection on the input image to detect the position frame of the dashboard; then extract the target area, perform semantic segmentation in the target area, segment the mask of the pointer and scale, and convert the mask into two-dimensional by scanning the image is converted into a one-dimensional array, and the position of the pointer and scale is predicted through peak detection, and finally the scale is calculated according to the scale and range. The invention applies the lightweight method of runing and knowledge distillation based on the YOLOv7-tiny model in the target detection stage, so that the model is greatly compressed while maintaining the prediction accuracy; in the semantic segmentation stage, a lightweight method based on depth-wise separable convolution is used. The lightweight U2NetP model replaces the U2Net model, which greatly reduces the amount of model parameters. The experimental results show that the lightweight method used in this paper can compress the original YOLOv7-tiny model by 95.7%, the average accuracy rate can reach 90.5%, the original U2NetP model can be compressed by 76.8%, the average IOU can reach 88.7%, and the average pixel accuracy rate can reach 99.4%.

Direction Consistency‐Guided Lightweight Power Line Detection Network for Aerial Images

“…Shi et al [44] replaced normal convolution with depth separable convolution, performing information exchange across channels to solve the problem of information blocking between channels. Yang et al [45] proposed a lightweight semantic segmentation network based on U2Net, replacing the normal convolution in upsampling and downsampling in U2Net with deeply separable convolutions, effectively reducing the computational effort of the model. Wu et al [46] introduced the InvolutionBottleneck module and modified the loss function to construct a lightweight YOLOv5-B, which is further used to detect and identify banana-bearing branches, rachides, and flower buds in orchards with complex background.…”

Research on target defect detection algorithm based on improved YOLO-V7

“…In ECA, the original feature image is first input, after which all of the image's channels are globally averaged and pooled. Next, channel weights are produced using a quick one-dimensional convolution with a size of Q, and the corresponding probabilities of the various channels are calculated and then compared to the original image [10]. As the input to the next layer, the input characteristics are multiplied collectively.…”

Segmentation of Wheat Lodging Areas from UAV Imagery Using an Ultra-Lightweight Network

“…UNet and its various variants have been widely used in segmentation tasks in various complex scenes. Its ultra-lightweight variant U2NetP is also being applied in multiple fields such as electricity meter detection [31] and ship draft detection [32]. The network has achieved good results for the abovementioned tasks, but there is still room for improvement in crop lodging segmentation where more complex features and unclear boundaries should be handled.…”