CN112308193A - Station ticket checking entrance people flow data collection device - Google Patents
Station ticket checking entrance people flow data collection device Download PDFInfo
- Publication number
- CN112308193A CN112308193A CN202011179043.2A CN202011179043A CN112308193A CN 112308193 A CN112308193 A CN 112308193A CN 202011179043 A CN202011179043 A CN 202011179043A CN 112308193 A CN112308193 A CN 112308193A
- Authority
- CN
- China
- Prior art keywords
- data
- pedestrian
- flow
- processing system
- collection device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06M—COUNTING MECHANISMS; COUNTING OF OBJECTS NOT OTHERWISE PROVIDED FOR
- G06M1/00—Design features of general application
- G06M1/27—Design features of general application for representing the result of count in the form of electric signals, e.g. by sensing markings on the counter drum
- G06M1/272—Design features of general application for representing the result of count in the form of electric signals, e.g. by sensing markings on the counter drum using photoelectric means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Image Processing (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention belongs to the field of intelligent monitoring and intelligent transportation, and particularly relates to a passenger flow data collection device for a ticket checking entrance of a station. Aiming at the problems that the prior statistical method cannot be fed back in time when being used for a station ticket gate, the statistical result has larger error and lacks effectiveness, accuracy and comprehensiveness, the invention provides a pedestrian flow data collection device for the station ticket gate, which comprises a pedestrian flow collection device based on an infrared sensor, a pedestrian flow collection device based on video pedestrian counting, a data processing system, a database and an LED digital display tube.
Description
Technical Field
The invention belongs to the field of intelligent monitoring and intelligent transportation, and particularly relates to a passenger flow data collection device for a ticket checking entrance of a station.
Background
When collecting passenger flow data of a railway station, the passenger flow data is generally determined by means of the amount of ticketing, the collected data lacks real-time performance and accuracy, and information of the passenger flow data needs to be collected in real time in order to achieve scientific management of a manager on the station, more effectively distribute management and maintenance personnel and collect the passenger flow data of a short period.
Common passenger flow volume statistical methods include manual passenger flow volume statistics, three-roller gate passenger flow volume statistics, gravity sensing passenger flow volume statistics, infrared sensor passenger flow volume statistics, face recognition passenger flow volume statistics and the like.
When the passenger flow volume is counted manually, equipment does not need to be installed, the single cost is relatively low, and the short-time reliability is high. However, the statistical personnel can not keep highly centralized for a long time, can not count continuously for a long time and possibly miss the number of people, the salary cost belongs to continuous investment, the manual counting error is large, the data arrangement time is long, and the defects are great.
When the three-roller gate counts passenger flow, the rolling gate rolls once when each passenger enters the entrance, the counting result is accurate but the convenience is lacked, and the passengers can not enter the station quickly. When the passenger flow is counted by gravity sensing, a gravity sensing device is arranged on the floor of the station entrance, and when passengers trample on the device, the number of passengers is counted, but the cost is high and the stability is poor.
The infrared sensor is not contacted with the detected object, when the passenger passes through the detection area, the infrared signal at the body temperature radiation position of the human body is collected, but the passenger flow detection method of the infrared sensor is easily interfered by various heat sources and light sources, the infrared radiation of the human body is easily shielded and is not easily received by the probe, and when the ambient temperature and the human body temperature are close, the detection sensitivity is obviously reduced, short-time failure can be caused, and the unicity of data collection influences the result of passenger flow analysis.
The video pedestrian counting is characterized in that the information of the image is extracted, the image is matched with the selected human body characteristic reference vector, and the image is further stored in a people counting system, but the video pedestrian counting detection passenger flow cannot be identified and counted under the conditions that an optical head is blank, a child is carried, an umbrella is supported and the like, and a passenger cannot meet the human face identification principle because the passenger does not necessarily enter the station from the face direction identification system and the height of the passenger is inconsistent, so that certain defects exist. If the statistical methods are used for the station ticket checking entrance, the feedback cannot be carried out in time, and the statistical results have large errors (lack of effectiveness, accuracy and comprehensiveness).
Disclosure of Invention
The invention provides a flow data collection device for a ticket checking entrance of a station.
In order to achieve the purpose, the invention adopts the following technical scheme:
a passenger flow data collection device for a ticket entrance of a station comprises a passenger flow collection device based on an infrared sensor, a passenger flow collection device based on video pedestrian counting, a data processing system, a database and an LED digital display tube;
the pedestrian flow collecting device based on the infrared sensor comprises a sensor detection assembly, a 51 single chip microcomputer and a data transmission unit; the sensor detection assembly is used for collecting people flow data information, transmitting the collected people flow data information to the 51 single chip microcomputer to complete control coding and modulation of the people flow collected data information on baseband signals, and the 51 single chip microcomputer transmits the people flow data information to the data processing system through the data transmission unit;
the pedestrian flow collecting device based on the video pedestrian counting comprises a high-definition camera, an information processing system and a pedestrian number counting system; the high-definition camera is used for acquiring the pedestrian flow image information, primary characteristic screening of the foreground and accurate identification of pedestrians are realized through programming, the influence of ambient light, the color and the wearing of the hair of a passenger on the image acquisition is reduced, the accuracy of the passenger flow data acquisition is ensured, and the high-definition camera is connected with the information processing system and is used for transmitting the acquired pedestrian flow image information to the information processing system; the information processing system is used for the preliminary statistics of passenger flow data and transmitting the data to the people counting system; the people counting system is connected with the data processing system;
the data processing system is used for fusing data obtained by the infrared sensor pedestrian flow acquisition device and data obtained by the video pedestrian counting pedestrian flow acquisition device by using a CI covariance algorithm to realize staged data acquisition, displaying the processed data on an LED digital display tube, and outputting the processed data to a database for storage. The data processing system is directly connected with the database to realize the final collection of the data, thereby not only ensuring the independence of the data, but also reducing the redundancy of the data and realizing the centralized control of the data. Through programming of machine language, short-period passenger flow data of 10 minutes, 30 minutes, 1 hour and the like can be acquired. The LED digital display tube can directly display the real-time data of the passenger flow and reduce the energy consumption at the same time.
Further, the sensor detection assembly comprises an infrared sensor, an infrared transmitting device, an infrared receiving device, a signal amplifier and a processing circuit using a Schmitt trigger. The sensor detection assembly is connected to the 51 single chip microcomputer, so that not only can the sensitivity be improved, but also the reaction speed can be enhanced. Furthermore, a better detection effect is obtained for collecting passenger flow data at a ticket gate of a station. The Schmitt trigger is realized by level triggering, converts slowly-changing waveform pulses into rectangular pulses and has hysteresis property, so that the occurrence of some false actions can be avoided, and certain anti-interference effect is achieved.
Further, the 51 single chip microcomputer comprises a central processing unit, a random access memory, a read-only memory, a computer interface, two timing counters, an interrupt control system with five interrupt sources, a serial I/O port of a full-duplex UART, an on-chip oscillator and a clock generating circuit.
Furthermore, the data transmission unit is a data communication product developed based on a GPRS/CDMA/3G network, and realizes the remote data communication between the substation field device and the monitoring center. The Data Transmission Unit (DTU) provides remote data communication between the field equipment of the ticket gate and the monitoring center, reduces interference of uncertain factors, ensures real-time performance and stability of people flow data, and can protect and automatically switch into a standby power supply.
Further, the information processing system comprises an image input system, a foreground screening system, an accurate identification system, a human body feature identification algorithm for determining feature vectors based on Hog features, and a mode identification algorithm based on SVM classification to finish preliminary feature screening of the foreground and accurate identification of pedestrians by the information processing system.
Further, the CI covariance algorithm specifically includes:
selecting the pedestrian flow rate a acquired by the infrared sensor at the fixed time period of n weeks continuously, the pedestrian flow rate b acquired by the video pedestrian counting device at the fixed time period of n weeks continuously, and marking the pedestrian flow rate c when only one of the two devices counts or both counts through machine language programming;
wherein the content of the first and second substances,
the data fusion result is:
in the formula Wa+Wb+WcSelecting weight W as 1a、WbAnd WcLet PddThe trace of (2) is minimal;
the definition of covariance is obtained by following the definition of variance:
obtaining a correlation matrix:
likewise to obtain Paa,Pbb,Pcc,Pba,Pac,Pca,Pbc,Pcb。
Compared with the prior art, the invention has the following advantages:
the invention has simple structure, can effectively improve the real-time property and the accuracy of data transmission by simultaneously combining the infrared inductor and the video pedestrian counting method and programming through machine language, not only has easy realization mode, but also can effectively resist the interference brought by the outside.
The invention realizes the functions of reversible infrared people flow statistics, counting and the like. The design innovation point is that the programmable logic device replaces the traditional comprehensive function which can be realized by a plurality of modules such as an integrated circuit counter, a decoder, time delay, alarm and the like, so that the development of the modern electronic design technology and process is met, the volume and the power consumption of a circuit are reduced, the production cost of a product is reduced, and the real-time reliability of a system is improved. The method is suitable for automatic management of open teaching places such as schools and the like, and has wide application prospects.
Drawings
FIG. 1 is a working scene of the flow data collecting device for ticket checking entrance of a station of the present invention;
FIG. 2 is an internal block diagram of the sensor test assembly of the present invention;
FIG. 3 is a process of preprocessing a video image acquired by a high definition camera according to the present invention;
FIG. 4 is a diagram of feature vector selection using low-dimensional HOG features;
FIG. 5 is a flow chart of the operational states of the integrated infrared sensor pedestrian flow collection unit and the video pedestrian counting pedestrian flow collection unit;
in the working state flow chart of fig. 5, the upper half is a working state flow chart of the infrared sensor device, the lower half is a working state flow chart of the video pedestrian counting, and the third part is a data processing system programmed by using machine language and storage and display of data.
Detailed Description
In order to further illustrate the technical solution of the present invention, the present invention is further illustrated by the following examples.
A passenger flow data collection device for a ticket entrance of a station comprises a passenger flow collection device based on an infrared sensor, a passenger flow collection device based on video pedestrian counting, a data processing system, a database and an LED digital display tube;
the pedestrian flow collecting device based on the infrared sensor comprises a sensor detection assembly, a 51 single chip microcomputer and a data transmission unit; the sensor detection assembly is used for collecting people flow data information, transmitting the collected people flow data information to the 51 single chip microcomputer to complete control coding and modulation of the people flow collected data information on baseband signals, and the 51 single chip microcomputer transmits the people flow data information to the data processing system through the data transmission unit;
the pedestrian flow collecting device based on the video pedestrian counting comprises a high-definition camera, an information processing system and a pedestrian number counting system; the high-definition camera is used for collecting the people flow image information, and is connected with the information processing system and used for transmitting the collected people flow image information to the information processing system; the information processing system is used for the preliminary statistics of passenger flow data and transmitting the data to the people counting system; the people counting system is connected with the data processing system;
the data processing system is used for fusing data obtained by the infrared sensor pedestrian flow acquisition device and data obtained by the video pedestrian counting pedestrian flow acquisition device by using a CI covariance algorithm to realize staged data acquisition, displaying the processed data on an LED digital display tube, and outputting the processed data to a database for storage.
The sensor detection assembly includes an infrared sensor, an infrared emitting device, an infrared receiving device, a signal amplifier, and a processing circuit using a schmitt trigger (as shown in fig. 2).
The 51 single chip microcomputer comprises a central processing unit, a random access memory, a read-only memory, a computer interface, two timing counters, an interrupt control system with five interrupt sources, a serial I/O port of a full-duplex UART, an on-chip oscillator and a clock generating circuit.
The data transmission unit is a data communication product developed based on a GPRS/CDMA/3G network, and realizes remote data communication between the substation field equipment and the monitoring center.
The information processing system comprises an image input system, a foreground screening system, an accurate identification system, a human body feature identification algorithm for determining feature vectors based on Hog features, and a mode identification algorithm based on SVM classification, and the information processing system completes preliminary feature screening of the foreground and accurate identification of pedestrians.
The CI covariance algorithm specifically comprises:
selecting the pedestrian flow rate a acquired by the infrared sensor at the fixed time period of n weeks continuously, the pedestrian flow rate b acquired by the video pedestrian counting device at the fixed time period of n weeks continuously, and marking the pedestrian flow rate c when only one of the two devices counts or both counts through machine language programming;
wherein the content of the first and second substances,
the data fusion result is:
in the formula Wa+Wb+WcSelecting weight W as 1a、WbAnd WcLet PddThe trace of (2) is minimal;
the definition of covariance is obtained by following the definition of variance:
obtaining a correlation matrix:
likewise to obtain Paa,Pbb,Pcc,Pba,Pac,Pca,Pbc,Pcb。
The specific working principle is as follows:
a people flow collecting device based on an infrared sensor is characterized in that through the reflection principle of infrared rays, when no person passes through an infrared detection area, light beams emitted by the infrared rays are directly received by an infrared receiving device 1; when a person passes through the infrared detection area, light beams emitted by infrared rays can be reflected to the infrared receiving device 2 due to the shielding of the human body, signals processed by the central processing unit are sent to the pulse electromagnetic valve, the electromagnetic valve is controlled by opening the valve core according to a specified instruction after receiving the signals, and when the rectangular pulse changes in the transmission process, the Schmitt trigger can enable the rectangular pulse to return to an ideal state; when the human body leaves the infrared sensing range, the electromagnetic valve does not receive signals, the valve core of the electromagnetic valve resets through the internal spring, and the corresponding counter is increased by one.
A pedestrian flow collecting device based on video pedestrian counting detects human body images in video images through a high-definition camera, determines characteristics of the selected human body images, and matches the determined characteristics with the characteristics in the human body images collected by the high-definition camera; and if the matching is successful, the determined characteristics are used as a reference, the pedestrians in the video are further accurately identified, the identified characteristics and the position information of the detected human body image are stored in a file together, the detected human body image and the reference characteristics which are successfully matched are stored in a people counting system, and then a corresponding counter is increased by one.
The specific operation method comprises the following steps:
before the pedestrian flow is collected, the infrared sensor and the high-definition camera are respectively placed at a position 1.2 meters away from the ground horizontally at the security inspection door and vertically above a pedestrian, the height of the high-definition camera is adjusted to be about 3 meters away from the ground, and the high-definition camera is connected with a power supply.
After the infrared sensor is arranged, a pin (middle part) of the infrared receiver is directly connected with a pin of the single chip microcomputer, then the level change of the pin is scanned to count, the pin can also be directly connected with an interrupt interface of the single chip microcomputer, and an interrupt program can be directly executed when a signal exists.
Schmitt triggers have two threshold voltages at the gate, namely a positive threshold voltage and a negative threshold voltage. A positive threshold voltage is a change in circuit state when an input signal rises from a low level to a high level, and a negative threshold voltage is a change in circuit state when an input signal falls from a high level to a low level. The return-difference voltage is the difference between the positive-going threshold voltage and the negative-going threshold voltage. The Schmitt reverse trigger can shape the distorted rectangular pulse obtained by the sensor to obtain an ideal rectangular pulse. Case of distorted rectangular pulse: when the capacitance on the transmission line is large, the rising edge of the waveform is deteriorated; when the transmission line is long and the impedance of the transmission line and the receiving end is not matched, oscillation phenomena can be generated at the rising edge and the falling edge of the waveform, and when other pulses are superposed on the rectangular pulse through the distributed capacitance between the wires or the common power line, noise is added to the signal.
The method comprises the steps of simply programming a single chip microcomputer, enabling the single chip microcomputer to automatically recognize and perform count control of adding one, respectively performing hardware debugging and software debugging through a check circuit during debugging, and further uploading data through a Data Transmission Unit (DTU).
After the high-definition camera is arranged, the video image acquired by the high-definition camera is uploaded to the memory and then transmitted to the information processing system. Since video images inevitably generate different types and different degrees of distortion in the processes of imaging, storing and transmitting, noise pollution is caused, and the image quality is reduced, some basic preprocessing operations need to be performed on the images to effectively improve the visual effect of the images. The most basic method is still the processing means and techniques of denoising, enhancing, restoring, segmenting, extracting features, identifying and the like.
As shown in fig. 3: firstly, to eliminate the noise of the image, the image is denoised at an early stage because the quality of the original image is reduced due to various random interferences received by the video shot under normal conditions. And then, carrying out operations such as median filtering and the like on the image, filtering high-frequency components to enable the image to achieve the effect of tending to smoothness, and removing redundant useless information in the image to enable the image to approach the real effect. The image binarization process can effectively change the color image of the video into the image in a black-and-white mode, and eliminate useless color information through the effect of only black and white of the image to obtain useful image information, so that the overall or local characteristics of the image can be effectively reflected.
Secondly, obtaining a background image through background modeling to prepare for subsequent target detection, then performing difference operation on a current frame of the video and the background image, obtaining a binary image through image preprocessing, and comparing the binary image with a threshold value to further obtain a foreground image. A foreground target in the loaded video can be obtained by making a difference with the background, and pedestrians in the target are preliminarily screened out by utilizing the shape characteristics (such as aspect ratio and area) of the pedestrians.
Finally, as shown in fig. 4, the final feature vector is further accurately identified by using the SVM pedestrian classifier whose input is the low-dimensional HOG feature and output is the probability value of being subordinate to the pedestrian.
Extracting the Hog characteristics by using the foreground image, wherein the extraction steps are as follows:
(1) converting the obtained foreground image into a gray image due to small color information effect;
(2) the Gamma correction is carried out on the input image to reduce the contrast of the image and the influence caused by local shadow and illumination change, and simultaneously, the interference of noise can be inhibited;
the value RGB gray scale calculation formula of the image pixel is
The exponent of this function is called the Gamma value and is typically 2.2.
(3) The gradient of each pixel is calculated to capture the contour information, and the interference of illumination is weakened. The image gradient calculation formula is as follows:
gradient size:
gradient in horizontal direction: dx (I, j) ═ I (I +1, j) -I (I, j)
Gradient in vertical and horizontal directions: dy (I, j) ═ I (I, j +1) -I (I, j)
Gradient direction:
where I (I, j) is the image pixel RGB value at (I, j), where (I, j) is the pixel's coordinates.
(4) In order to obtain an encoding of the local image area, the gradients of all pixels are projected into the gradient direction of the cell;
(5) in order to compress illumination, shadow and edge further, all cells are normalized on the block, and the block descriptor after normalization is called as HOG descriptor;
(6) HOG characteristics of all overlapped blocks in a detection window are collected and combined into a final characteristic vector;
(7) and classifying the final feature vector by using SVM classification.
Meanwhile, all foreground targets with unclear membership classification are sequentially stored in the queue, and then the pedestrian detection result of the main thread module is output and uploaded. The passenger flow data of the video pedestrian counting device is collected through the people counting system and uploaded to the data processing system.
And the data obtained by the infrared sensor and the video pedestrian counting device are processed by a machine language programming in a data processing system to obtain a final result, and the final result is uploaded to a database and displayed on an LED digital display tube.
While there have been shown and described what are at present considered to be the essential features and advantages of the invention, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing exemplary embodiments, but is capable of other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (6)
1. A passenger flow data collection device for a ticket entrance of a station is characterized by comprising a passenger flow collection device based on an infrared sensor, a passenger flow collection device based on video pedestrian counting, a data processing system, a database and an LED digital display tube;
the pedestrian flow collecting device based on the infrared sensor comprises a sensor detection assembly, a 51 single chip microcomputer and a data transmission unit; the sensor detection assembly is used for collecting people flow data information, transmitting the collected people flow data information to the 51 single chip microcomputer to complete control coding and modulation of the people flow collected data information on baseband signals, and the 51 single chip microcomputer transmits the people flow data information to the data processing system through the data transmission unit;
the pedestrian flow collecting device based on the video pedestrian counting comprises a high-definition camera, an information processing system and a pedestrian number counting system; the high-definition camera is used for collecting the people flow image information, and is connected with the information processing system and used for transmitting the collected people flow image information to the information processing system; the information processing system is used for the preliminary statistics of passenger flow data and transmitting the data to the people counting system; the people counting system is connected with the data processing system;
the data processing system is used for fusing data obtained by the infrared sensor pedestrian flow acquisition device and data obtained by the video pedestrian counting pedestrian flow acquisition device by using a CI covariance algorithm to realize staged data acquisition, displaying the processed data on an LED digital display tube, and outputting the processed data to a database for storage.
2. The station entrance ticket flow data collection device of claim 1, wherein the sensor detection component comprises an infrared sensor, an infrared emitting device, an infrared receiving device, a signal amplifier and a processing circuit using a Schmidt trigger.
3. The device as claimed in claim 1, wherein the 51-chip microcomputer includes a central processing unit, a random access memory, a read only memory, a computer interface, two timing counters, an interrupt control system with five interrupt sources, a serial I/O port of a full-duplex UART, an on-chip oscillator, and a clock generation circuit.
4. The station ticket gate people flow data collection device of claim 1, wherein the data transmission unit is a data communication product developed based on GPRS/CDMA/3G network, implementing remote data communication between substation field devices and monitoring center.
5. The station ticket entrance people flow data collection device of claim 1, wherein the information processing system comprises an image input system, a foreground screening system, an accurate recognition system, a human body feature recognition algorithm for determining feature vectors based on the Hog features, and a pattern recognition algorithm based on SVM classification to complete preliminary feature screening of the foreground and accurate recognition of pedestrians by the information processing system.
6. The station ticket gate people flow data collection device according to claim 1, wherein the CI covariance algorithm specifically is:
selecting the pedestrian flow rate a acquired by the infrared sensor at the fixed time period of n weeks continuously, the pedestrian flow rate b acquired by the video pedestrian counting device at the fixed time period of n weeks continuously, and marking the pedestrian flow rate c when only one of the two devices counts or both counts through machine language programming;
wherein the content of the first and second substances,
the data fusion result is:
in the formula Wa+Wb+WcSelecting weight W as 1a、WbAnd WcLet PddThe trace of (2) is minimal;
the definition of covariance is obtained by following the definition of variance:
obtaining a correlation matrix:
likewise to obtain Paa,Pbb,Pcc,Pba,Pac,Pca,Pbc,Pcb。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011179043.2A CN112308193B (en) | 2020-10-29 | 2020-10-29 | Station ticket checking entrance people flow data collection device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011179043.2A CN112308193B (en) | 2020-10-29 | 2020-10-29 | Station ticket checking entrance people flow data collection device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112308193A true CN112308193A (en) | 2021-02-02 |
| CN112308193B CN112308193B (en) | 2023-04-07 |
Family
ID=74330766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011179043.2A Active CN112308193B (en) | 2020-10-29 | 2020-10-29 | Station ticket checking entrance people flow data collection device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112308193B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113486747A (en) * | 2021-06-25 | 2021-10-08 | 深圳市易成自动驾驶技术有限公司 | People flow rate display method, device, equipment, readable storage medium and program product |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102054167A (en) * | 2010-12-14 | 2011-05-11 | 浙江工业大学 | All-weather multipath channel pedestrian flow monitoring system based on wireless infrared monitoring |
| CN104182958A (en) * | 2013-05-21 | 2014-12-03 | 索尼公司 | Target detection method and device |
| CN105224911A (en) * | 2015-08-27 | 2016-01-06 | 湖北文理学院 | A kind of various visual angles pedestrian detection method and system in real time |
| CN105404850A (en) * | 2015-10-21 | 2016-03-16 | 中南大学 | Station passenger flow monitoring system, station passenger flow monitoring method, station passenger flow control system and station passenger flow control method |
| CN106296951A (en) * | 2016-08-17 | 2017-01-04 | 成都仁通融合信息技术有限公司 | A kind of system for subway station people's flow monitoring |
| CN108270994A (en) * | 2016-12-30 | 2018-07-10 | 河南辉煌信通软件有限公司 | Railway passenger station Pedestrian flow detection early warning system based on ticketing data |
| CN108416254A (en) * | 2018-01-17 | 2018-08-17 | 上海鹰觉科技有限公司 | A kind of statistical system and method for stream of people's Activity recognition and demographics |
| CN108460864A (en) * | 2017-02-22 | 2018-08-28 | 开利公司 | Flow of the people estimating system and fault handling method for it |
| CN108769595A (en) * | 2018-06-06 | 2018-11-06 | 合肥信亚达智能科技有限公司 | A kind of intelligence is personal to identify monitoring tracking transmission method and system |
| CN109934977A (en) * | 2019-02-12 | 2019-06-25 | 山西省河道与水库技术中心 | A kind of intelligent entrance guard recognition methods suitable for unit of opening to the outside world |
| CN110647855A (en) * | 2019-09-29 | 2020-01-03 | 常州大学 | Subway station passenger flow statistical method based on face recognition |
| US20200029013A1 (en) * | 2018-04-16 | 2020-01-23 | Government Of The United States, As Represented By The Secretary Of The Air Force | Human-Automation Collaborative Tracker of Fused Object |
-
2020
- 2020-10-29 CN CN202011179043.2A patent/CN112308193B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102054167A (en) * | 2010-12-14 | 2011-05-11 | 浙江工业大学 | All-weather multipath channel pedestrian flow monitoring system based on wireless infrared monitoring |
| CN104182958A (en) * | 2013-05-21 | 2014-12-03 | 索尼公司 | Target detection method and device |
| CN105224911A (en) * | 2015-08-27 | 2016-01-06 | 湖北文理学院 | A kind of various visual angles pedestrian detection method and system in real time |
| CN105404850A (en) * | 2015-10-21 | 2016-03-16 | 中南大学 | Station passenger flow monitoring system, station passenger flow monitoring method, station passenger flow control system and station passenger flow control method |
| CN106296951A (en) * | 2016-08-17 | 2017-01-04 | 成都仁通融合信息技术有限公司 | A kind of system for subway station people's flow monitoring |
| CN108270994A (en) * | 2016-12-30 | 2018-07-10 | 河南辉煌信通软件有限公司 | Railway passenger station Pedestrian flow detection early warning system based on ticketing data |
| CN108460864A (en) * | 2017-02-22 | 2018-08-28 | 开利公司 | Flow of the people estimating system and fault handling method for it |
| CN108416254A (en) * | 2018-01-17 | 2018-08-17 | 上海鹰觉科技有限公司 | A kind of statistical system and method for stream of people's Activity recognition and demographics |
| US20200029013A1 (en) * | 2018-04-16 | 2020-01-23 | Government Of The United States, As Represented By The Secretary Of The Air Force | Human-Automation Collaborative Tracker of Fused Object |
| CN108769595A (en) * | 2018-06-06 | 2018-11-06 | 合肥信亚达智能科技有限公司 | A kind of intelligence is personal to identify monitoring tracking transmission method and system |
| CN109934977A (en) * | 2019-02-12 | 2019-06-25 | 山西省河道与水库技术中心 | A kind of intelligent entrance guard recognition methods suitable for unit of opening to the outside world |
| CN110647855A (en) * | 2019-09-29 | 2020-01-03 | 常州大学 | Subway station passenger flow statistical method based on face recognition |
Non-Patent Citations (2)
| Title |
|---|
| 从金亮 等: ""快速协方差交叉融合算法及应用"", 《自动化学报》 * |
| 陈坚 等: ""城市轨道交通车站乘客聚散行为仿真及优化"", 《交叉创新与转型重构——2017 年中国城市交通规划年会论文集》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113486747A (en) * | 2021-06-25 | 2021-10-08 | 深圳市易成自动驾驶技术有限公司 | People flow rate display method, device, equipment, readable storage medium and program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112308193B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105373135B (en) | A kind of method and system of aircraft docking guidance and plane type recognition based on machine vision | |
| WO2020253308A1 (en) | Human-machine interaction behavior security monitoring and forewarning method for underground belt transportation-related personnel | |
| CN112132119B (en) | Passenger flow statistical method and device, electronic equipment and storage medium | |
| CN103714325B (en) | Left object and lost object real-time detection method based on embedded system | |
| CN109819208A (en) | A kind of dense population security monitoring management method based on artificial intelligence dynamic monitoring | |
| CN102915638A (en) | Surveillance video-based intelligent parking lot management system | |
| CN111414887A (en) | Secondary detection mask face recognition method based on YO L OV3 algorithm | |
| CN112381075B (en) | Method and system for carrying out face recognition under specific scene of machine room | |
| CN106875381A (en) | A kind of phone housing defect inspection method based on deep learning | |
| CN110728252B (en) | Face detection method applied to regional personnel motion trail monitoring | |
| CN110119680A (en) | A kind of electrical cabinet wiring automatic errordetecting system based on image recognition | |
| CN110276265A (en) | Pedestrian monitoring method and device based on intelligent three-dimensional solid monitoring device | |
| CN103530648A (en) | Face recognition method based on multi-frame images | |
| CN104239905A (en) | Moving target recognition method and intelligent elevator billing system having moving target recognition function | |
| CN112183472A (en) | Method for detecting whether test field personnel wear work clothes or not based on improved RetinaNet | |
| CN112308193B (en) | Station ticket checking entrance people flow data collection device | |
| CN115841651A (en) | Constructor intelligent monitoring system based on computer vision and deep learning | |
| CN115620090A (en) | Model training method, low-illumination target re-recognition method and device and terminal equipment | |
| CN103456123B (en) | A kind of video smoke detection method based on flowing with diffusion characteristic | |
| Zhang et al. | AGVS: A new change detection dataset for airport ground video surveillance | |
| CN108073873A (en) | Human face detection and tracing system based on high-definition intelligent video camera | |
| CN202121706U (en) | Intelligent personnel monitoring system | |
| CN109815784A (en) | A kind of intelligent method for classifying based on thermal infrared imager, system and storage medium | |
| CN108960169A (en) | Instrument and equipment state on_line monitoring method and system based on computer vision | |
| CN112183287A (en) | People counting method of mobile robot under complex background |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |