Salient target detection method and system based on local and global context fusion

Abstract

The invention discloses a saliency target detection method and system based on local and global context fusion, and the method comprises the following steps: obtaining an RGB image to be subjected to saliency target detection, inputting the RGB image into a pre-trained saliency target detection model, and obtaining a saliency target detection result; wherein the saliency target detection model comprises a feature extraction network used for obtaining multi-scale features; the splicing fusion network is used for obtaining low-level detail features and high-level semantic features; the local context extraction network is used for outputting fine local context features; the global context extraction network is used for outputting fine global context features; and the fusion output network is used for outputting a saliency target detection result. According to the method, local and global context information can be effectively extracted, and the efficiency and accuracy of saliency detection in a complex scene can be improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a method and system for salient target detection based on local and global context fusion. Background technique [0002] Saliency object detection refers to accurately segmenting the most interesting regions in an image that attract human attention in a given image. Such tasks have broad and meaningful real-world applications in information retrieval, public safety and other fields, such as: using saliency content as a guide for image description; using saliency detection to guide unsupervised feature learning on high-resolution satellite images scene classification; transforming unsupervised learning into multi-instance learning to achieve localization and classification tasks; providing object-level cues to help unsupervised video object segmentation; providing image saliency contour information for object detection tasks, etc. [0003] At present, there ar...

AI Technical Summary

Problems solved by technology

[0004] (1) Existing works mainly focus on how to aggregate multi-level features from different layers of fully convolutional networks, which is still an open problem in the deep learning community; at the same time, existing methods focus on images where the background is similar to the foreground (low contrast ) and other complex situations, the saliency detection performance is not ideal;

[0005] (2) Although there are many networks that extract local and global information and fuse the two, it is still challenging to design effective networks to extract local and global features;

Images