An automatic parking system and method based on visual recognition
An automatic parking and visual recognition technology, applied in character and pattern recognition, vehicle components, instruments, etc., can solve problems such as poor estimation accuracy, inability to accurately identify parking spaces by ultrasonic waves, and inability to handle parking scenarios.
Active Publication Date: 2021-05-04
MONENTA (SUZHOU) TECHNOLOGY CO LTD
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] (1) Relying solely on ultrasonic waves cannot accurately identify the location of the parking space, and cannot handle parking scenarios other than parallel parking and vertical parking; this brings the limitations of parking conditions
[0005] (2) After the entire parking function is activated, the pose estimation accuracy without visual feedback is poor;
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0044] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with the embodiments and accompanying drawings. Here, the exemplary embodiments and descriptions of the present invention are used to explain the present invention, but not to limit the present invention.
[0045] figure 1 The functional block diagram of the deep learning-based automatic parking system provided by the embodiment of the present invention is shown, including the mapping and positioning sub-module and the planning and control sub-module. The details are as follows:
[0046] 1. Mapping and positioning sub-module
[0047] This module is mainly used to perform feature extraction and parking space positioning on the collected images, and obtain obstacle maps and related parameter information. This module is divided into four steps: step 1, firstly perform distortion correction and inve...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention belongs to the field of intelligent driving, and specifically relates to an automatic parking system and a parking method; in the prior art, the automatic parking system is based on a traditional path planning algorithm, and the effect is poor. An automatic parking system, the system includes a map positioning sub-module and a planning control sub-module, since the map used incorporates information maps of local obstacles, the adaptability of the automatic parking system to abnormal conditions is improved; in addition, through deep learning Obtain visual information and call Reeds-Shepp curve planning technology in real time according to the update of the environment. Compared with the technology of pose planning without visual feedback, it improves the pose estimation accuracy and the response speed of the parking system.
Description
technical field [0001] This application belongs to the field of intelligent driving, and specifically relates to an automatic parking system based on visual recognition Background technique [0002] At present, the main technical route for automatic parking technology is based on traditional path planning algorithms, such as RRT, PRM, A*, etc. The basic idea is to identify the approximate location of the parking space through ultrasonic waves, randomly generate a path, and then perform collision detection on the randomly generated path, that is, to detect whether the path will pass through obstacles, or whether the path is within the driving area of the vehicle. Then, among all feasible paths, the Dijkstra algorithm and other methods are used to select the optimal parking path. [0003] But there is following defective in above-mentioned prior art: [0004] (1) Relying solely on ultrasonic waves cannot accurately identify the location of the parking space, and cannot han...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): B60W30/06B60W50/00B60R1/00G06K9/00
CPCB60W30/06B60W50/00B60R1/27
Inventor 姚聪成悠扬张家旺汪路超郑靖陈壹夏炎
Owner MONENTA (SUZHOU) TECHNOLOGY CO LTD