Automatic parking system and method

Abstract

The invention relates to the field of intelligent driving, in particular to an automatic parking system and an automatic parking method. The method comprises the steps of inputting a to-be-detected image into a road image model to obtain semantic information of a road image, and performing real-time map construction and high-precision positioning according to semantic features in the semantic information. Meanwhile, blank parking space detection is conducted through visual information and ultrasonic waves, and a vehicle parking path is accurately controlled through the high-precision positioning technology to complete the parking process. In addition, in order to further achieve high practical positioning precision, a method for obtaining an overlooking spliced image by adopting a plurality of target images shot at the same moment is adopted. Image semantic features in the overlooking spliced image are recognized, and positioning is carried out based on the image semantic features anda wheel speed meter. According to the method, a direct method of looking around the spliced graph is adopted, and the wheel speed meter is fused, so that the positioning precision can be effectively improved while the algorithm robustness is ensured.

Description

technical field [0001] The invention relates to the field of intelligent driving, in particular to an automatic parking assistance detection system, automatic parking and positioning system and method. Background technique [0002] With the development of science and technology, emerging concepts such as autonomous driving and unmanned vehicles have emerged as the times require. The automatic parking system is an integral part of the automatic driving technology, and the interest in the development of the automatic parking system in the automotive industry is gradually increasing. In fact, the intelligent parking assistance system was first applied to some vehicles in 2003, and related technologies have continued to develop in recent years. Specifically, the vehicle's camera or ultrasonic sensors can perceive the current environment of the vehicle, and the parking space detection technology is used to process the surrounding environment information of the vehicle acquired b...

AI Technical Summary

Problems solved by technology

Method 1) has the advantage of high positioning accuracy, but the main problem is that the feature point extraction and feature point matching are very dependent on the application scene, and the algorithm has poor robustness; the advantage of method 2) is that it is more robust to the scene, and the disadvantage is that it often gets Local optimal results lead to lower positioning accuracy

The above problems in positioning will lead to the accuracy of the parking process

Images