Deep learning image identification method and deep learning image identification system used for intelligent driving, and terminal device

Abstract

The invention provides a deep learning image identification method and a deep learning image identification system used for intelligent driving, and a terminal device. The deep learning image identification system comprises a sharing convolutional network, an area segmentation network, and a target identification network. The area segmentation network is used for area classification processing based on a characteristic graph extracted by the sharing convolutional network, and the target identification network is used for target identification positioning processing based on the characteristic graph extracted by the sharing convolutional network. The sharing convolutional network is monitored by using the area segmentation result acquired by the area segmentation network and the target identification result acquired by the target identification network, and the sharing learning of the area segmentation network and the target identification network is completed. An obvious speed advantage on an aspect of multi-task learning is provided, and by comparing with the two independent networks learning individually, the deep learning image identification system has advantages of less consumed time and high efficiency, and in addition, a convolutional layer repetitive operation problem is effectively prevented, and multi-task detection and multi-task identification are completed.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to an image detection and recognition method, in particular to a deep learning image recognition method, system and terminal equipment for intelligent driving. Background technique [0002] In the field of intelligent vehicles, there are mainly two existing methods for target positioning and recognition, one is based on traditional neural network training classifiers; the other is based on artificially extracted grayscale image features input into multi-class support vector machines recognition algorithm implementation. The traditional neural network classifier needs to train two networks for the two tasks of detection and recognition, and the calculation cost is high; while the artificial feature extraction method has great limitations, and the selection of decision parameters is a heuristic method. If the value is not selected properly, it will directly affect the recognition result...

AI Technical Summary

Problems solved by technology

[0003] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a deep learning image recognition method, system and terminal equipment for intelligent driving, which are used to solve the high computational cost and feature extraction limitations of existing target recognition methods Large, or / and parameter selection is difficult to achieve the optimal value, affecting the recognition results

Images