Salient object detection method based on bidirectional message link convolutional network

Abstract

The invention provides a salient object detection method based on a bidirectional message link convolutional network. Firstly, an attention mechanism is used for guiding a feature extraction module toextract entity effective features, and contextual information between multiple levels is selected and integrated in a progressive mode; and fusing the high-level semantic information with the shallowcontour information by using a bidirectional information link consisting of a network with a skipping connection structure and a message transmission link with a gating function. Finally, a multi-scale fusion strategy is used to encode the multi-layer effective convolution features so as to generate a final saliency map. Qualitative and quantitative experiments of six data sets show that the method provided by the invention can obtain better performance under different indexes.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to the field of image salient object detection, and extracts salient regions (that is, regions of human interest) in images. Background technique [0002] Visual saliency is used to characterize parts of an image that stand out more than their neighbors. Saliency models can be divided into data-driven bottom-up models and task-driven top-down models. Convolutional neural network-based saliency detection methods eliminate the need for manual features and gradually become the mainstream direction of saliency detection. Salient object detection is used to highlight the most important part of an image, and is often used as an image preprocessing step in computer vision tasks, including image segmentation, visual tracking, scene classification, object detection, image retrieval, image recognition, etc. [0003] Salient object detection can be divided into saliency detection methods usin...

AI Technical Summary

Problems solved by technology

In the task of using deep neural networks to solve salient object detection, there are still many problems to be solved, such as the lack of boundary detail information, background suppression and entity mirroring, etc.

Images