Infrared image weak and small target detection method based on improved YOLO v3

Abstract

The invention provides an infrared image weak and small target detection method based on improved YOLOv3. The method comprises the steps: firstly improving the standard convolution operation in a YOLOv3 residual module through deep separable convolution in a lightweight feature extraction network, then introducing a channel self-attention mechanism into each residual module of the lightweight feature extraction network, introducing a spatial self-attention mechanism into each residual module of the lightweight feature extraction network, finally, accelerating network training in the lightweight feature extraction network by using an H-switch activation function, further constructing an infrared image weak and small target detection model based on improved YOLO v3, and constructing a lightweight feature extraction network. In the network model design process, depth separable convolution is used for replacing the standard convolution operation of YOLO v3, different receptive fields are obtained through multi-scale feature map extraction, parameters are reduced, and therefore the method has the advantages that the network parameters are greatly reduced, and the calculation speed is high.

Description

technical field [0001] The invention relates to the field of image target technology detection, in particular to a method for detecting weak and small targets in infrared images based on improved YOLO v3. Background technique [0002] Infrared imaging is based on the reflection of infrared light by the target and the thermal radiation of the target itself. It is less affected by the light intensity conditions. It can not only work well during the day, but also realize target detection at night. However, the contrast of the infrared image is low, the texture features are weak, and the interference is large. Under the influence of strong noise and similar background, the detection target becomes a weak target, and the general target recognition algorithm is difficult to apply. The emergence of deep learning has made a breakthrough in the detection of weak and small targets in infrared images. In particular, the regression-based YOLO v3 target detection algorithm only needs to...

AI Technical Summary

Problems solved by technology

This method has achieved certain results in the detection accuracy of infrared pedestrian small targets, but SENet only shows the interdependence between the modeling feature channels, and the acquisition of spatial information is insufficient.

Images