Visual scene recognition system and method based on deep neural network

Abstract

A visual scene recognition system based on a deep neural network, comprises: a vehicle-mounted vision system for acquiring vehicle front view visual images; an offline training module for utilizing adeep convolutional neural network to perform sampling on the vehicle front view visual images acquired by the vehicle-mounted vision system, performing labeling, generating sample labels, and performing neural network parameter step-by-step training, wherein the deep convolutional neural network is composed of a three-branch classification network sharing two layers of shallow convolution features, and the network parameters are trained through samples and a training task; and an online analysis module for adopting a network compression and time-sharing parallel analysis strategy to perform real-time scene analysis on the samples trained by an offline training module, and outputs the weather time and the weather of a road scene in which the vehicle vision system is located and a scene abnormal state.

Description

technical field [0001] The invention relates to the field of vehicle safety, in particular to a visual scene recognition system and method based on a deep neural network. Background technique [0002] Intelligentization has now become an important development direction of the automotive industry. The perception technology based on visual sensors is becoming more and more mature, and its application in the field of vehicle active safety is becoming more and more extensive. For the vision system, for different road environments, from image acquisition to application layer algorithms, corresponding adjustments will be made from the parameters and strategy levels. Therefore, accurate recognition of scene information in visual input has strong application value and significance, and, The anomaly diagnosis of the visual scene can further enhance the robustness and fault tolerance of the system. [0003] Most of the existing vision systems do not have such perfect basic algorithms...

AI Technical Summary

Problems solved by technology

[0004] An object of the present invention is to solve the existing weather judgments in the above-mentioned prior art mostly based on the system clock, and weather judgments based on auxiliary sensors such as rainfall. Such methods do not have strong correlation with the visual system input itself, so in some boundary In order to solve the problem of poor situation effect, a visual scene recognition system and method based on deep neural network is provided

Images