A driving scene vehicle detection method based on an SSD neural network

Abstract

The invention discloses a driving scene vehicle detection method based on an SSD neural network, comprising the following steps: constructing a data set and dividing the data set into a training set and a test set; based on Caffe's deep learning framework, using a SqueezeNet as a feature extraction network; selecting and merging six convolution layers of SqueezeNet network to be detected; after merging the six convolution layers of SqueezeNet network to be detected, adding a position regression layer and a class confidence discrimination layer to complete the construction of the training network model; obtaining a network pre-training model by initializing the training network model; using the network pre-training model, and obtaining the final training model by using the DSD method to carry out multiple rounds of training on the produced data set; capturing the forward image and inputting the image into the final training model, then using the non-maximum suppression algorithm to remove the redundant detection box so as to the detection results. The invention can quickly and accurately detect the vehicle target in front of the vehicle, and is a powerful measure for improving the environment perception ability of the intelligent driving vehicle.

Description

technical field [0001] The invention relates to the field of vehicle detection, in particular to a method for detecting a vehicle in a driving scene based on an SSD neural network. Background technique [0002] The rapid development of artificial intelligence technology has provided more assistance for the development of the automobile industry. In the automobile industry, intelligent driving vehicles have received people's attention. In the environmental perception of intelligent driving cars, camera perception plays an important role, and object detection technology has also become a key technology. When the vehicle is driving fast, more requirements are placed on the speed of the target detection algorithm. [0003] In the field of target detection, how to improve the detection speed as much as possible while maintaining good accuracy has always been a research hotspot. Traditional machine learning methods mainly perform accelerated calculations during the calculation o...

AI Technical Summary

Problems solved by technology

This method can achieve high detection accuracy, but the running speed is too slow and the memory consumption is relatively large, which limits its application scenarios

The YOLO (You Look Only Once) network uses a 7×7 grid for regression calculation based on the end-to-end idea. Its detection speed is fast but the detection accuracy is difficult to improve

Images