Target detection method based on SSD improvement

Abstract

The invention provides a target detection method based on SSD improvement, and the method selects ResNet-101 to replace VGG-16 as a basic network of a whole model, and provides richer feature map information. A feature fusion strategy is adopted, so that the detection effect of multi-scale prediction of a network prediction layer on a small target is improved to a certain extent; an SE-block module is added to a classification branch and used for capturing global environment information of the feature map and outputting the feature map with channel weight, so that classification is more accurate; and a Centerness parallel to the classification prediction layer is added to suppress a low-quality bounding box so as to improve the detection precision. According to the method, anchor-frame-free detection is adopted, all hyper-parameters related to the anchor frame are avoided, the hyper-parameter amount is greatly reduced through the adopted prediction bounding box strategy, the network design complexity is reduced, and the training stage becomes very simple. According to the method, a loss function adopts a focalloss function, so that the model detection precision is improved while the detection speed is kept.

Description

Technical field: [0001] The present invention relates to the field of computer vision, and more specifically relates to an improved target detection method based on SSD, which can be applied to target detection tasks in daily life and can detect targets in real time. Background technique: [0002] With the advancement of society and the development of science and technology, artificial intelligence has become an indispensable part of people's lives. Technologies such as drones and unmanned vehicles are becoming more and more mature. Computer vision is the core of unmanned driving technology. With the rise of learning and the advent of the era of big data, the development of computer vision has reached a new height. At present, most target detection algorithms are based on deep learning. Traditional detection algorithms cannot meet the real-time and accuracy of technology required by modern society because of their poor robustness and slow detection speed. Detection algorithm...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems of poor detection effect on small targets, high complexity of network frame design and low detection accuracy in the original SSD algorithm, the pr

Images