Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Passenger target detecting method combining infrared and visible light images

A target detection and infrared image technology, which is applied in the field of passenger target detection combining infrared and visible light images, can solve the problems of difficult passenger target image and background area separation, uncontrollable, and attitude variations

Inactive Publication Date: 2009-03-11
SHANGHAI YAO WEI GROUP IND
View PDF1 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the extremely complex external working environment faced by the camera, the behaviors and postures of people getting on and off the car vary widely and are uncontrollable.
If only the above method is used to perform image recognition on the images of passengers getting on and off the bus captured in complex situations, it is difficult to efficiently and accurately separate the passenger target image from the background area

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
  • Passenger target detecting method combining infrared and visible light images
  • Passenger target detecting method combining infrared and visible light images
  • Passenger target detecting method combining infrared and visible light images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] Such as figure 1 As shown, in a passenger target detection method that combines infrared and visible light images, step 1 is the initial step, receiving a collected visible light image and infrared image respectively; in step 2, check whether the reception is successful, if If the detection result is no, return to step 1; if the detection result in step 2 is yes, then in step 3, perform infrared and visible light image preprocessing; in step 4, check whether the processing is successful, if the detection result is no, Then return to step 1; if the result of detection in step 4 is yes, then in step 5, perform local peak detection in the infrared image area; in step 6, check whether the detection is successful, if the detection result is no, then return to step 1; If the result of detection in step 6 is yes, then in step 7, extract the motion peak area; in step 8, detect whether the extraction is successful, if the detection result is no, then return to step 1; if the res...

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 relates to a method for detecting a passenger target by combining an infrared image with a visible light image. The method comprises the following steps of receiving a newly-acquired infrared image and a visible light image respectively; following the pre-processing of the infrared image and the visible light image if the images are detected to be successfully received; detecting the local peak value in an infrared image area if the processing is detected to be successful; capturing a motion peak value area if the detection is detected to be successful; following the initial cutting of the visible light image if the capturing is detected to be successful; following the fine cutting of a human body area by combining the visible light image and the infrared image if the initial cutting is detected to be successful; and outputting the result of the separation of the human body area from a background area if the cutting is detected to be successful. Compared with the prior art, the method can better solve the problem of the separation of a targeted image from a background image of the human body under the circumstances of complex acts and different postures in getting on / off by the human body and the like.

Description

technical field [0001] The invention relates to a passenger target image and a background separation method, in particular to a passenger target detection method combining infrared and visible light images. Background technique [0002] Passenger vehicles often need to count the number of passengers boarding and disembarking passengers at a certain point in time or within a certain period of time, so as to optimize operations and improve management levels based on passenger statistics. [0003] In the process of counting the number of passengers getting on and off the passenger vehicle, a very critical step is to detect whether there are passengers at any point in time, and the position of each passenger at that point in time during the process of getting on and off the bus. [0004] The invention patent "Moving Object Tracking and Number Counting Method" with application number 200710036809.X discloses a method that is mainly used in passenger vehicles to count the number o...

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
IPC IPC(8): G06K9/34G06K9/46G06K9/62G06T7/20H04N1/46
Inventor 万长明姚薇
Owner SHANGHAI YAO WEI GROUP IND
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products