Passenger flow counting detection method based on depth images
A technology of depth image and detection method, which is applied in the direction of image data processing, counting of randomly distributed items, and counting objects, etc., can solve the problems of accuracy rate decline, application environment restrictions, impact, etc., and achieve accurate passenger traffic statistics, accurate The effect of customer flow statistics
Active Publication Date: 2015-01-07
ZHENGZHOU TIAMAES TECH
View PDF4 Cites 39 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The traditional passenger flow counting system mainly uses pressure sensors and infrared devices. In the case of crowded passenger flow, the accuracy rate drops significantly; at present, the passenger flow counting method using image processing technology is a new development direction. The purpose of passenger flow counting is achieved by identifying people. Although it is accurate The accuracy has been improved, but traditional images are easily affected by light, which limits the application environment
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0030] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0031] Such as figure 1 Shown, the present invention comprises the following steps:
[0032] Step 1. Set up a somatosensory camera above the bus door to collect depth image videos of passengers getting on and off the bus.
[0033] Step 2, preprocessing the obtained depth image, filling the outlier points of the depth image, and converting the data format of the depth image to obtain a depth image of 0-255.
[0034] Step 3, denoising the depth image preprocessed in step 2, and then performing multiple layered processing to obtain multiple binary images, and merging these binary images to obtain a binary image of this frame; the specific steps are:
[0035] Step 31, denoising the depth image, performing an opening operation to remove small bright details;
[0036] Open operation: ,in is the image, is a structural element;
[0037] Step 32, obtai...
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
Login to View More Abstract
The invention discloses a passenger flow counting detection method based on depth images. The method includes the steps that (1) a motion sensing camera is arranged above a door of a bus and is used for collecting depth image videos of passengers getting on and off the bus; (2) the obtained depth images are pre-processed; (3) denoising is carried out on the depth images pre-processed in the second step, then laying processing is carried out many times to obtain multiple binary images, and the binary images are combined to obtain the frame of binary images; (4) head detection judgment is carried out; (5) heat trajectory tracking is carried out; (6) whether the passengers get on the bus or get off the bus is judged; (7) the passengers getting on and off the bus are calculated and passenger flow counting is achieved. Detection analysis is carried out by means of the depth images, the defect that counting accuracy of a traditional passenger flow counting method is poor when the passengers are crowded and light rays change is overcome, the crowdedness of the passenger flow volume can be well learnt about, the aim of accurately counting the passenger flow volume is achieved, and real-time, clear and accurate passenger traffic statistical data are provided for an intelligent public transit system.
Description
technical field [0001] The invention relates to the field of digital image processing and recognition, in particular to a method for counting and detecting passenger flow based on a depth image. Background technique [0002] In recent years, as the government has increased its investment in smart public transport, my country's smart public transport system APTS has begun to emerge. The passenger flow counting system is an important part of APTS. This system can provide real-time, clear and accurate information to bus companies. Passenger traffic statistics, which can bring economic and social benefits. [0003] The traditional passenger flow counting system mainly uses pressure sensors and infrared devices. In the case of crowded passenger flow, the accuracy rate drops significantly; at present, the passenger flow counting method using image processing technology is a new development direction, and the purpose of passenger flow statistics is achieved by identifying people. Al...
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
Login to View More IPC IPC(8): G06K9/00G06K9/46G06T7/00
CPCG06M11/00G06T7/246G06T2207/10016G06T2207/30196G06T2207/30242G06T5/70
Inventor 郭建国方志乾王树茂丁智辉王兴中
Owner ZHENGZHOU TIAMAES TECH