Image processing device and method for detecting pedestrians

An image processing and pedestrian technology, applied in image data processing, image analysis, instruments, etc., can solve the problems of slow processing speed and low pedestrian recognition accuracy, and achieve the effect of improving the recognition rate and shortening the processing time.

Active Publication Date: 2018-12-14
HYUNDAI MOBIS CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method must analyze the motion direction of the entire input image based on the motion detection analysis described above. Therefore, the processing speed is the same as the pedestrian detection method using the global retrieval method above.
In addition, this method has low accuracy of pedestrian recognition when the pedestrian is not moving

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image processing device and method for detecting pedestrians
  • Image processing device and method for detecting pedestrians
  • Image processing device and method for detecting pedestrians

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] In the present invention, a pedestrian detection method capable of judging the presence of a pedestrian and the possibility of a collision using an image sensor mounted on a vehicle is proposed.

[0019] In addition, in the present invention, a pedestrian detection method is provided, which utilizes lane line information to select a candidate pedestrian area where pedestrians actually exist, so that the detection processing time required for pedestrian detection can be shortened.

[0020] In addition, in the present invention, a pedestrian detection method is provided, which separates the candidate pedestrian area into an upper body area and a lower body area, and if pedestrian features are detected in both the upper body area and the lower body area, then the corresponding candidate pedestrian area is determined as a pedestrian area for noise immunity.

[0021] In the following, before describing an embodiment of the present invention in detail with reference to the ac...

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

No PUM Login to view more

Abstract

An image processing device for detecting pedestrians is provided. The image processing device includes: a lane line extraction module, which extracts lane line coordinate values ​​from an input image; and a pedestrian detection module, which uses the extracted lane line coordinate values ​​to pass through the first left and right lane line ends. The area between one line and the second line passing through the ends of the second left and right lane lines located above the left and right lane lines is selected as a pedestrian concern area, and the pedestrian concern area is searched using a preset window, Detect pedestrian areas with pedestrian features.

Description

technical field [0001] The invention relates to a pedestrian detection device and a method thereof, in particular to a pedestrian detection device used in a vehicle and a method thereof. Background technique [0002] Recently, as part of research on pedestrian protection, devices that detect pedestrians have been put on the market. This pedestrian detection device can identify pedestrians suddenly appearing in front of the vehicle, and prevent pedestrian accidents by issuing an alarm to the driver or controlling the brakes of the vehicle. [0003] In the past, a method was proposed to obtain images from a digital imaging device, block the search window, and detect pedestrians using a global search method such as an SVM classifier (Support Vector Machine Classifier, Support Vector Machine Classifier). After removing a large number of search windows, this method uses a high-precision secondary classifier to detect pedestrians, so it has high accuracy and can reduce the power ...

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
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62G08G1/16G06V10/50
CPCG06V40/103G06V20/588G06V10/50G06T7/00G06V10/40
Inventor 柳东规姜柄準赵埈范
Owner HYUNDAI MOBIS CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap