Improved real-time vehicle detection and filtering method and system

A technology for vehicle detection and filtering methods, which is applied in the directions of instruments, character and pattern recognition, computer parts, etc. to achieve the effects of high speed, good adaptability, and easy parallelism

Active Publication Date: 2016-12-14
开易(北京)科技有限公司
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The technical problem to be solved by the present invention is to complete real-time vehicle detection and filtering by reducing manual parameter adjustment and self-adaptive sample adjustment.

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
  • Improved real-time vehicle detection and filtering method and system
  • Improved real-time vehicle detection and filtering method and system
  • Improved real-time vehicle detection and filtering method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0053] figure 1 It is a schematic flow chart of an improved real-time vehicle detection and filtering method in an embodiment of the present invention.

[0054] An improved real-time vehicle detection and filtering method in this embodiment includes the following steps:

[0055] Step S100 performs vehicle detection on the input image to obtain a vehicle rectangular frame; in step S100, those skilled in the art can understand that the specific vehicle detection is to use Aggregated Channel Features algorithm (ACF, Aggregated Channel Features) for vehicle detection. The algorithm for aggregating channel features includes, but is not limited to, inputting an image, performing windowing according to the image, aggregating chan...

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 invention discloses an improved real-time vehicle detection and filtering method and system. The method comprises: vehicle detection is carried out on an inputted image to obtain a vehicle rectangular frame; according to the vehicle rectangular frame, feature extraction is carried out on a vehicle target, wherein the feature extraction at least includes extraction of a confidence coefficient and geometric constraint information of the vehicle; on the basis of the extracted feature, model training is carried out to obtain a filter model; and if a new vehicle rectangular frame target is inputted, false target and correct vehicle target determination is carried out by using the filter model and a filter result is outputted. According to the invention, the model-learning-based method is applied to the vehicle filtering field for the first time. Moreover, on the basis of the feature extraction method for vehicle filter model description, real-time vehicle detection and filtering are completed.

Description

technical field [0001] The invention relates to the fields of image processing and artificial intelligence, in particular to an improved real-time vehicle detection and filtering method and system. Background technique [0002] After the vehicle detector detects and outputs all the vehicle results in the current image, no matter how high the performance of the classifier is, false detection is hard to avoid. In order to effectively suppress and filter out falsely detected vehicle targets, there are generally two methods: [0003] Method 1: Threshold judgment is made on the confidence of the output box of the vehicle detection classifier. If it is greater than a certain threshold, the detection box is retained as the vehicle output result; if it is less than the threshold, it is judged as a false detection target and deleted. The selection of the threshold is very critical. Generally, the performance of the training sample set under each threshold is calculated by performing...

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): G06K9/00G06K9/62
CPCG06V20/584G06F18/2411
Inventor 刘鹏
Owner 开易(北京)科技有限公司
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