Infrared target image segmentation method and system, electronic equipment and storage medium

Abstract

The invention provides an infrared target image segmentation method and system, electronic equipment and a storage medium. The method comprises the following steps: collecting infrared target images under various scenes as a training data set; preprocessing the infrared target image; marking a target instance and manufacturing a pixel-level binary mask; extracting a multi-level resolution size feature map of the infrared target image; presetting candidate boxes with different sizes for pixel points one by one; inputting the candidate boxes into a regional naming network for binary classification and boundary box modification; filtering the candidate boxes of the background, carrying out ROI Align operation on the foreground candidate boxes to obtain an ROI region, carrying out N category classification, bounding box regression and binary mask generation on the ROI region, and finally obtaining a trained infrared target image segmentation model. By means of the scheme, the problem thatthe real-time performance of an existing image processing method is difficult to guarantee in a complex scene is solved, the method can adapt to target detection in infrared images in various complexscenes, meanwhile, the real-time performance of infrared image processing is achieved, and the calculated amount is reduced.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an infrared target image segmentation method, system, electronic equipment and storage medium. Background technique [0002] In the field of computer vision, object detection, as a classic research direction, is widely used in traffic monitoring, image retrieval, and human-computer interaction. As an important branch of computer image processing, infrared target detection is suitable for situations where the color and shape of the target are similar to the surrounding environment, and can be used in security monitoring, military investigation, night driving, shipping and other fields. Infrared images reflect the relative temperature information of objects and are less affected by weather factors. Compared with lighting cameras, night vision and other equipment, infrared spectral imaging has the advantages of long detection distance and high detection reliability, but infrared imag...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiment of the present invention provides an infrared target image segmentation method to solve the problem that the existing image segmentation method is difficult to adapt to complex application scenarios while ensuring real-time image processing

Images