Significant target detection method based on FCN (fully convolutional network) and CNN (convolutional neural network)

Abstract

The invention relates to a significant target detection method based on an FCN (fully convolutional network) and a CNN (convolutional neural network). The method comprises the following steps: firstly, extracting the deep semantic information by use of the FCN, wherein a fixed size of an input image is not needed, end-to-end prediction is performed, and the training complexity is reduced. Accuracy optimization is performed by adopting the CNN and extracting local features to obtain a rough detection result of the FCN. In the invention, the semantic information in an image can be extracted accurately and efficiently, and the improvement of significant target detection accuracy in a complex scene is promoted.

Description

technical field [0001] The invention belongs to the technical field of salient target detection, and in particular relates to a salient target detection method based on global and local convolutional networks. Background technique [0002] Existing saliency object detection methods are mainly local or global bottom-up data-driven methods, which use color contrast, background prior information, texture information, etc. to calculate saliency maps. These methods mainly have two shortcomings: one is that they rely on artificially selected features, which often leads to a lot of information contained in the image itself being ignored; the other is that the salient prior information is only combined through simple heuristics, and there is no clear optimal The optimal combination method makes the detection results in complex scenes not accurate enough. [0003] Using deep neural network to autonomously extract image features can effectively solve the above problems. In the docum...

AI Technical Summary

Problems solved by technology

These methods mainly have two shortcomings: one is that they rely on artificially selected features, which often leads to a lot of information contained in the image itself being ignored; the other is that the salient prior information is only combined through simple heuristics, and there is no clear optimal The optimal combination method makes the detection results in complex scenes not accurate enough

In the document "DeepNetworks for Saliency Detection via Local Estimate and Global Search", a deep convolutional network is used to extract features for saliency detection, and local evaluation uses a 51*51 image block centered on each superpixel block as input for image block level Classification, the amount of training data is large; the global evaluation is based on artificially selected features, so the obtained global features cannot fully represent the deep information of the data, and the effect is not good in complex scenes

Images