Deep learning-based complex road condition perception system and apparatus

Abstract

The invention discloses a deep learning-based complex road condition perception system and apparatus. The deep learning-based complex road condition perception system comprises the five steps of 1, collecting data of an image sensor; 2, preprocessing the image data, wherein the preprocessing comprises white balance, gamma correction and denoising processing; 3, performing feature extraction by using a first deep neural network; 4, performing target locating by using features extracted by a second deep neural network; and 5, performing target identification on a locating region by using a thirddeep neural network to obtain a final detection result. The apparatus is used for the deep learning-based complex road condition perception system.

Description

Technical field: [0001] The invention relates to a complex road condition perception system and device based on deep learning. Background technique: [0002] Using deep learning technology, integrate feature extraction, target positioning, target recognition and other technologies into a unified deep neural network, and form a complete set of end-to-end solution prevention, and optimize the model complexity of the deep neural network on the vehicle equipment Based on performance, it can quickly and accurately process vision tasks in vehicle systems. [0003] Traditional methods can only perform single-target detection. If multi-target detection is required, different features and different classifiers need to be used, which increases the design difficulty of the entire system, and different features cannot be shared among different classifiers, resulting in It reduces the repeatability of calculation and cannot improve the efficiency of detection, and the generalization abi...

AI Technical Summary

Problems solved by technology

[0003] Traditional methods can only perform single-target detection. If multi-target detection is required, different features and different classifiers need to be used, which increases the design difficulty of the entire system, and different features cannot be shared among different classifiers, resulting in It reduces the repeatability of calculation and cannot improve the efficiency of detection, and the generalization ability of traditional algorithms in complex scenarios is weak and cannot achieve practical value.

Images