Salient object detection method and system based on image segmentation technology

Abstract

The invention discloses a salient object detection method based on image segmentation technology. The method comprises the following steps: collecting a pixel value of each pixel in a background image; for each pixel, calculating the sum of distance between the pixel and other pixels; carrying out conversion on the distance sum of each pixel to obtain a saliency characteristic value of the pixel,and obtaining a feature image according to the saliency characteristic value of each pixel; recording the maximum value and the minimum value of all saliency characteristic values, and calculating thedifference between the maximum value and the minimum value and mapping the feature image to a numerical range; mapping the background image to the numerical range according to the corresponding pixelvalue and the saliency characteristic value to obtain a first stretching image; subtracting the first stretching image from the feature image to obtain a subbackground image; mapping the subbackground image to the numerical range to obtain a second stretching image; and subtracting the feature image from the second stretching image to obtain a target image. The invention also discloses a salientobject detection system based on the method above. The system comprises an acquisition module, an image processing module, a calculating module and an output module.

Description

technical field [0001] The invention relates to the field of image layering technology detection, in particular to a method and system for detecting a salient object based on image layering technology. Background technique [0002] At present, for target object detection in complex environmental backgrounds, it is often easily affected by background information. For example, when the vehicle target is detected on the road, the sun casts a huge shadow from the trees on both sides of the road on a sunny day, and the vehicle happens to be in the shadow. At this time, it will be found that the shadow is more prominent on the image, and the vehicle is prominent in a local area inside the shadow. Therefore, if you want to detect the vehicle from the image, you can first separate the shadow, and then separate the vehicle from the shadow. This is the so-called "image layering". [0003] In general, if the target object exists in the background image but it is not easy to separate ...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the above-mentioned technical defects, the object of the present invention is to provide an object detection method and system based on image layering technology, which is used to solve the problem that the target object in the shadow of the background image is difficult to be accurately identified

Images