A target detection method based on a dense connection convolutional neural network

Abstract

The invention discloses a target detection method based on a dense connection convolutional neural network, and the method employs a network structure in which a plurality of dense connection blocks and conversion layers are alternately connected to replace a conventional overall structure in order to reduce the parameter quantity and improve the feature reuse effect, and achieves the feature extraction, and can achieve the discrimination feature mapping in an image. The global attention module fuses the feature maps of the four different receptive fields to solve the problem that the sizes ofsingle-layer receptive fields are the same in the past; And meanwhile, the last three convolutional layers of each branch enable the feature map of the bottom layer to have enough excellent feature expression on the premise of ensuring the resolution. The image target detection model provided by the invention can effectively extract the features of the image and extract the feature map which hasdifferent size receptive fields and is fused with multi-level information; Meanwhile, the detection effect of the small object is improved through combination of the semantic information and the spatial information; Meanwhile, the whole network can achieve end-to-end training, the real-time detection speed is kept, and meanwhile the target detection effect is improved.

Description

technical field [0001] The present invention relates to the field of computer vision, and more specifically, relates to a target detection method based on a densely connected convolutional neural network. Background technique [0002] The rapidly evolving convolutional neural network (CNN) has significantly improved the field of computer vision. As a rapidly developing but challenging field, object detection has also achieved many outstanding results through the high abstraction and robustness of deep neural networks. Convolutional neural networks are invariant to the detection of features. At present, the main solution methods are divided into two branches, one is the one-step detection method, all of these methods first select a series of candidate regions, and then transform it into a classification problem. For example, R-CNN, Fast-RCNN, Faster RCNN, R-FPN, etc., deep and complex networks make them famous for better detection performance. The other is a one-step detec...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem that the neural network in the prior art has poor detection effect on small targets, the present invention provides a target detection method based on a densely connected convolutional neural network, which effectively integrates different receptive fields and increases the utilization effect of feature maps to Perform target detection, so that the convolutional neural network has better detection results for small target objects that the network front-end pays attention to

Images