A method for identifying parameters of vehicles ahead based on multi-task convolutional neural network

Abstract

The invention discloses a vehicle multi-parameter identification method based on a multi-task convolutional neural network, comprising the following steps: designing and training a convolutional neural network structure; and identifying vehicle parameters based on a convolutional neural network. The invention adopts a convolutional neural network to transform the original data into a more abstract high-level expression through a simple and non-linear model. Therefore, the convolutional neural network can learn the hidden features that reflect the nature of the target to be identified from a large number of training samples; compared with the shallow learning classifier, it has stronger scalability and meets the needs of multiple types of targets in the traffic environment. recognition, the recognition accuracy is also higher. Especially when used in complex traffic environments, the present invention exhibits strong anti-environmental interference capability. The present invention extends the application of the convolutional neural network to the multi-parameter identification of the vehicle, uses the trained convolutional neural network to identify the type characteristics, pose information and the status of the vehicle lights in the image, and enhances the predictability of the potential behavior of the vehicle .

Description

technical field [0001] The invention belongs to the field of vehicle intelligence, and in particular relates to a method for identifying parameters of a vehicle in front. Background technique [0002] Vehicle recognition in traffic scenes belongs to the category of vehicle intelligence. Accurate and effective identification of vehicle parameter information is a key factor for improving the intelligence of intelligent vehicles and driver assistance systems (ADAS) and realizing collision avoidance between vehicles, and it is also a key prerequisite for judging and preventing collisions. [0003] The identification of vehicle parameters refers to the process of identifying vehicle targets in traffic scene images and obtaining information that can reflect the possible impact of the preceding vehicle on the vehicle, so that the driver can predict the information and prevent collisions. At present, the recognition method of vehicle parameters in front usually only recognizes a ce...

AI Technical Summary

Problems solved by technology

The limited hierarchical depth of the shallow learning model makes it limited to solving binary classification problems, and it is difficult to deal with the problem of target multi-parameter identification, which has limitations that are not easy to expand

[0004] Most of the existing technologies described above only identify at the level of whether the target vehicle exists, and there is a problem of simplification of vehicle parameter identification, so that it is difficult to achieve simultaneous acquisition of multiple parameters

Images