Object Detection Method Based On Improved SSD Algorithm For Smart Grid

Abstract

SSD (Single Shot Multi-Box Detector) is an object detection algorithm based on deep learning. As one of the most mainstream detection algorithms, it can greatly improve the detection speed and ensure the detection accuracy. In this paper, in order to improve the feature extraction capability of the network and the ability of the algorithm to detect small objects, the CBAM (Convolutional Block Attention Module) is introduced into the SSD network. The improved network uses DIoU (Distance-IoU) instead of IoU (Intersection over Union) in the original network. DIoU is more consistent with the mechanism of target frame regression than IoU. DIoU takes into account the distance between the target and the anchor, the overlap rate, and the scale, so that the target frame regression becomes more stable, and there will be no problems such as divergence during training like IoU and GIoU. The improved SSD algorithm was tested for comparison on the National Grid dataset. The experimental results show that the detection accuracy of the improved SSD algorithm on the test set is increased by 3.3% compared with the original SSD algorithm.