Image detection method and device

A technology in image detection and image processing, which is applied in the field of image processing and can solve the problems of slow detection speed and poor effect

Active Publication Date: 2008-06-11
中星智能系统技术有限公司
View PDF0 Cites 54 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Embodiments of the present invention provide an image detection method and device for determining the position of a car in an image, so as to solve the problems of slow car detection and poor effect in the prior art

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 detection method and device
  • Image detection method and device
  • Image detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] Since the intra-class distance of cars is very large, and the color and shape of different cars are very different, the embodiment of the present invention adopts the edge orientation histogram (HOG) feature that can reflect the edge contour information between the car and the background, and adopts fast and An easy-to-implement Hierarchical Adaptive Boosting (AdaBoost) classifier for fast and accurate car detection and tracking. In order to further improve the speed of vehicle detection, the embodiments of the present invention combine motion information into vehicle detection. At the same time, use the location information and color information of the car to match the car, obtain the car tracking information, and use the car tracking information to count the cars driving on the road to count the traffic flow.

[0034] The technical solutions provided by the embodiments of the present invention will be described in detail below in conjunction with the accompanying draw...

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 invention discloses an image detection method and a device thereof, which is used to solve the problems that the prior art is slow in automobile detection speed and poor in effect. The image detection method provided by the present invention comprises that: a weak feature library is obtained in advance through an edge direction histogram in a set rectangular region in an image, and a rapid automobile classifier based on a hierarchical self-adaptive enhanced classifier and the edge direction histogram is arranged by utilizing the weak feature library; through the edge direction and edge intensity of an input image, the edge direction histogram in the set rectangular region on the input image is calculated; according to the edge direction histogram in the set rectangular region on the input image, an automobile position in the input image is determined by adopting the rapid automobile classifier. The present invention also discloses an image tracking method and a device thereof. The present invention is used to determine automobile positions in images rapidly and accurately.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image detection method and device. Background technique [0002] Car detection refers to the technology of automatically obtaining the number of cars, as well as the position and size of each car from the collected images or videos. [0003] In the prior art, as an important classifier design method in the field of pattern recognition, the adaptive boosting (Adaboost) algorithm has been well applied in many applications including face detection. Voila et al. proposed a face detection technology based on microstructure features (Haar-like Features) and hierarchical (Cascade-based) adaptive enhancement (Adaboost) classifier, which is comparable in performance to support vector machine (SVM) ) and the method of neural network (Neural Network), but the speed is much higher than the method based on support vector machine and neural network, and can basically reach...

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 Applications(China)
IPC IPC(8): G06K9/00G08G1/01
Inventor 邓亚峰黄英
Owner 中星智能系统技术有限公司
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