Saliency object detection method based on Faster R-CNN

Abstract

The invention discloses a saliency object detection method based on Faster R-CNN. The method comprises the steps of first performing multi-scale segmentation on an image, then outlining possible saliency objects using the Faster R-CNN, establishing an object analogue map, thereafter distributing a foreground specific gravity to a superpixel via foreground connectivity, then obtaining round and smooth saliency maps in combination with specific gravities of a foreground and a background using a saliency optimization technology, and at last performing fusion using an MCA (Multi-layer Cellular Automata) to obtain a final saliency map. The segmentation is performed on an input image on three scales using a superpixel segmentation algorithm, and the superpixel segmentation algorithm is to aggregate adjacent and similar pixel points into different sizes of image areas according to low-level characteristics such as a color, a texture and a brightness, such that the complexity of saliency detection can be effectively reduced; and by taking different scales of segmented images as a layer of cells and performing fusion on the different scales of superpixel segmented images using the MCA, theconsistency of an image saliency detection result is guaranteed.

Description

technical field [0001] The invention belongs to the field of saliency detection of images in computer vision, and specifically refers to a saliency detection method for a specific class by deep learning. Background technique [0002] In recent years, with the rapid development of computer, Internet and multimedia technologies, people are exposed to a large amount of image and video information every day in their work and life. Because images and videos contain rich and intuitive content, they are effective channels for people to receive information and are one of the important sources of information, such as online video, video chat, mechanical parts inspection, webcast, intelligent monitoring, etc. Both digital images and videos are growing exponentially, and only using manual processing and analysis of images or videos often has great limitations. As an interdisciplinary subject integrating intelligent information processing and digital analysis, computer vision simulates...

AI Technical Summary

Problems solved by technology

[0004] The present invention is a salient object detection method based on Faster R-CNN, which aims to solve the problem that the deep semantic features of the image cannot be extracted by using the underlying features in the existing saliency detection model, which leads to the unsatisfactory effect of saliency detection

Images