Unlock instant, AI-driven research and patent intelligence for your innovation.

A vehicle target detection method and device

A target detection and vehicle technology, applied in the field of image processing, to achieve the effect of fast training process

Active Publication Date: 2019-02-15
ZHEJIANG UNIVIEW TECH CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method of improving vehicle target detection indicators and performance in complex scenes is a challenging technical problem

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
  • A vehicle target detection method and device
  • A vehicle target detection method and device
  • A vehicle target detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present application provides a vehicle target detection solution, which can be implemented based on computer software, and of course, can also be implemented in other ways such as hardware or logic devices. Please refer to Figure 1A , taking computer software implementation as an example, the present application provides a vehicle object detection device, which runs on a computer (such as a server). The computer may include a processor, memory, non-volatile storage (such as a hard disk), and an internal bus. The processor can read the computer program instructions corresponding to the vehicle object detection device from the non-volatile memory into the internal memory and then run them to form the vehicle object detection device in a logical sense. please check Figure 1B and figure 2 , on a logical level, the vehicle object detection device includes: a first training unit, a second training unit, an image conversion unit and a classification detection unit. D...

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

The present application provides a vehicle target detection method and device, which are applied to image processing equipment. The method includes: using a plurality of preset positive sample images and a plurality of negative sample images to train and generate a first classifier; wherein the first classifier It is a Haar-like classifier, and multiple Haar-like features including T-shaped Haar-like features are used in the training process; multiple positive sample images and multiple negative sample images are used to train to generate the first classifier which is different from the first classifier Two classifiers; convert the image to be detected into a grayscale image; use the first classifier and the second classifier to detect the vehicle target on the grayscale image and output the detection result. Compared with the prior art, the present application uses features that are more in line with the characteristics of the vehicle to complete the training of the classifier, making the classifier training process faster and the false detection rate of the trained classifier lowered more satisfactorily.

Description

technical field [0001] The present application relates to image processing technology, in particular to a vehicle target detection method and device. Background technique [0002] Video-based vehicle target detection technology is an important part of intelligent transportation systems, providing important information such as vehicle location and size for many applications, such as capturing illegal vehicles, traffic video monitoring systems, and vehicle target extraction. The most primitive vehicle target detection is mainly obtained manually through on-site or video surveillance. This method consumes too much manpower and material resources. Later, the industry proposed to extract moving targets through foreground and background detection, and then combine vehicle light detection and license plate detection to determine vehicle targets. This method The disadvantage is that the amount of information of moving objects extracted from the foreground and background is large, an...

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): G06K9/00G06K9/62
CPCG06V20/584G06V2201/08G06F18/24
Inventor 陈鑫嘉危春波
Owner ZHEJIANG UNIVIEW TECH CO LTD