Image saliency detection method based on feature selection and feature fusion

Abstract

The invention discloses an image saliency detection method based on feature selection and feature fusion, and the method comprises the following steps: carrying out the feature extraction of an inputimage, and adding features to a feature pyramid set; performing feature selection on the feature pyramid set to obtain a new feature pyramid set; performing feature fusion on features in the new feature pyramid set from bottom to top to obtain a mixed feature pyramid set; and training the saliency prediction network model by using features in the mixed feature pyramid set, and performing saliencydetection on a to-be-detected image by using the trained model. According to the invention, feature selection is carried out on features of an image by using an attention model; according to the method, the characteristics related to the image target are enhanced, so that the characteristics are more effective, detail characteristics of a bottom layer and semantic characteristics of a high layer are effectively fused by adopting a bottom-up characteristic fusion structure, the characterization capability of the characteristics is greatly improved, and the detection accuracy is higher than thatof a common saliency model network.

Description

technical field [0001] The invention belongs to the field of image saliency detection, in particular to an image saliency detection method based on feature selection and feature fusion. Background technique [0002] Image saliency is the object or object that attracts attention in the image. The result of saliency detection in images or videos is often the objects in images or videos. In neuroscience, saliency detection is described as an attention mechanism, which aims to focus or Zooming out on important parts of the scene where objects are seen, saliency detection can automatically handle object representations in images. Saliency detection can improve the efficiency of algorithms such as object detection and image segmentation. [0003] Currently the most effective saliency detection methods are implemented based on fully convolutional neural networks. The fully convolutional neural network superimposes multiple convolutional layers and pooling layers to gradually incr...

AI Technical Summary

Problems solved by technology

These methods fuse features at different scales but do not consider their different contributions to saliency, which leads to poor saliency detection results.

In order to overcome these problems, the existing technology proposes to introduce the attention model and gate function into the saliency detection network. However, this method ignores the different characteristics of high-level and low-level features, which may affect the extraction of effective features, thereby reducing the efficiency of saliency detection. precision

Images