Small target detection method based on feature fusion and depth learning

Abstract

The invention discloses a small target detection method based on feature fusion and depth learning, which solves the problems of poor detection accuracy and real-time performance for small targets. The implementation scheme is as follows: extracting high-resolution feature map through deeper and better network model of ResNet 101; extracting Five successively reduced low resolution feature maps from the auxiliary convolution layer to expand the scale of feature maps. Obtaining The multi-scale feature map by the feature pyramid network. In the structure of feature pyramid network, adopting deconvolution to fuse the feature map information of high-level semantic layer and the feature map information of shallow layer; performing Target prediction using feature maps with different scales and fusion characteristics; adopting A non-maximum value to suppress the scores of multiple predicted borders and categories, so as to obtain the border position and category information of the final target. The invention has the advantages of ensuring high precision of small target detection under the requirement of ensuring real-time detection, can quickly and accurately detect small targets in images, and can be used for real-time detection of targets in aerial photographs of unmanned aerial vehicles.

Description

technical field [0001] The invention belongs to the technical field of image information processing, and mainly relates to deep learning target detection, specifically a small target detection method based on feature fusion and deep learning, which can be used for real-time positioning and classification of small targets. Background technique [0002] Target detection is a challenging topic in the field of computer vision. At present, target detection methods based on deep learning are mainly divided into two categories, one is the convolutional neural network model based on the candidate area, and the other is the convolutional neural network model based on regression. network model. A deep convolutional neural network model based on candidate regions: R-CNN network and various optimized networks of R-CNN. The R-CNN network model first extracts candidate borders through a selective search algorithm, then uses a deep convolutional neural network (DCNN) to extract features f...

AI Technical Summary

Problems solved by technology

[0003] At present, these two types of network models have their own advantages. The detection accuracy of the convolutional neural network model based on the candidate area is generally high, but the real-time performance is poor; It has a lot to do with it. To detect small targets, it often requires a larger number of meshes, and the real-time performance will decrease accordingly.

The above two mainstream models still cannot achieve high detection accuracy for small targets in the image while ensuring real-time detection

Images