A Co-Salient Object Detection Method Based on PSO-based RGBD Graphs

Abstract

The invention discloses a cooperative salient target detection method based on a PSO RGBD image. The method comprises the following steps: S1, inputting an RGB image, a depth image and a salient image of a corresponding RGBD single image; using gPb-owt- The ucm segmentation method is used to segment the area to obtain the candidate target area; S2, use the PSO method to obtain the optimal number of cluster centers and the optimal characteristics of each particle; S3, obtain a saliency map by clustering the initial population; S4, use the clustering The optimal particle is selected according to the class quality, and the saliency map is updated. The present invention uses PSO to extract target features to carry out subsequent salient detection. The number of classifications can be automatically determined by PSO and features can be extracted at the same time, so as to perform collaborative salient detection. First, PSO is used to obtain features, and these features are used to classify regions. Get the final multi-classification results and co-saliency map. The present invention proves its validity and obvious advantages in effect through image library test and comparison.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a collaborative salient target detection method based on a PSO RGBD image. Background technique [0002] Salient object detection in computer vision has attracted increasing attention in recent years. Numerous saliency detection models focus on detecting salient objects from a single image and achieve excellent performance. Co-saliency detection, as an emerging and challenging problem based on salient object detection, has received increasing attention in recent years. Different from traditional single saliency detection models, co-saliency detection methods focus on finding common salient objects in multiple images. Co-saliency detection is mostly used in public pattern recognition, image matching, and co-recognition. It can be regarded as a combination of similar object recognition and co-classification tasks, and it belongs to the basic research work in computer vision. [00...

AI Technical Summary

Problems solved by technology

[0005] The above existing technologies generally have the defects of insufficient detection effectiveness and effect. Accordingly, there is an urgent need for an efficient and effective collaborative salient object detection method based on PSO RGBD images.

Images