NL2025140B1 - Green signal control method and apparatus dedicated for old person crossing the street - Google Patents
Green signal control method and apparatus dedicated for old person crossing the street Download PDFInfo
- Publication number
- NL2025140B1 NL2025140B1 NL2025140A NL2025140A NL2025140B1 NL 2025140 B1 NL2025140 B1 NL 2025140B1 NL 2025140 A NL2025140 A NL 2025140A NL 2025140 A NL2025140 A NL 2025140A NL 2025140 B1 NL2025140 B1 NL 2025140B1
- Authority
- NL
- Netherlands
- Prior art keywords
- elderly person
- crossing
- pedestrian
- old person
- street
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000001815 facial effect Effects 0.000 claims abstract description 55
- 238000005259 measurement Methods 0.000 claims abstract description 24
- 238000012544 monitoring process Methods 0.000 claims abstract description 24
- 238000005516 engineering process Methods 0.000 claims description 29
- 238000000605 extraction Methods 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims 2
- 238000012512 characterization method Methods 0.000 claims 1
- 230000002035 prolonged effect Effects 0.000 abstract description 19
- 239000002245 particle Substances 0.000 description 8
- 238000001514 detection method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000010606 normalization Methods 0.000 description 3
- 230000007704 transition Effects 0.000 description 3
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000000392 somatic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- 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
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- 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
-
- 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
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
- G06V40/173—Classification, e.g. identification face re-identification, e.g. recognising unknown faces across different face tracks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
CROSSING Discloses a green signal time prolonging method, system, and apparatus dedicated for an old person. Includes: collecting facial information of an old person by using a face identification method; obtaining facial information of all pedestrians within a sidewalk monitoring range, conducting similarity measurement on the facial information , determining the old person whose identity has been verified, and marking the old person, conducting real-time tracking on the marked old person to obtain a street-crossing track, calculating, according to the street-crossing track of the old person, an average speed for crossing a street by the old person, obtaining a distance between the old person and an end point of a sidewalk, recording the distance as a remaining distance; determining a shortest safe street-crossing time according to the average speed and the remaining distance; and setting a countdown of a prolonged green signal time according to the shortest safe street-crossing time.
Description
TECHNICAL FIELD The present invention relates to the field of pedestrian re-identification technologies, and in particular, to a green signal time prolonging method, system, and apparatus dedicated for an old person.
BACKGROUND As China gradually enters an aging society, travel safety of the elderly is gradually getting more attention. Due to somatic functions of the elderly, a street-crossing behavior of an old person is very different from that of an average person. An existing street-crossing facility has very great drawback, and when a pedestrian crosses a street, a speed designed for crossing a street is excessively high, and a green light time is relatively short, and therefore the old person cannot cross the street safely. To resolve a street-crossing safety problem of the elderly, it is necessary to design a green signal time prolonging method and apparatus suitable for an old person. A green signal time prolonging apparatus suitable for an old person that is more studied in the current field is to use a card swiping control manner. After an old person places a magcard in a card-swiping area, a computer or an intelligent signal control machine calculates a control signal, and control a green light time of a traffic signal light of a sidewalk to be prolonged by a fixed time and a red light time of a corresponding motor vehicle lane to be prolonged, so that a special group has enough time to pass an intersection and their personal safety is ensured. However, this type of apparatus requires that an old person carries around a dedicated magnetic card. The dedicated magnetic card has relatively poor reliability and cannot prevent other people from using identity information of the old person. In addition, the prolonged time is a fixed passing time, and consequently it is impossible to ensure whether the old person can pass safely within the fixed time, and there may be an excessive prolonged green signal time, thereby delaying passing of motor vehicles and leading to relatively poor self-adaptability.
SUMMARY An objective of the present invention is to provide a green signal time prolonging apparatus, system, and apparatus dedicated for an old person, so as to resolve a street-crossing safety problem of the elderly and furthest reduce a delay caused to motor vehicles. To achieve the above purpose, the present invention provides the following technical solutions. A green signal time prolonging method dedicated for an old person based on a pedestrian re-identification technology includes:
collecting facial information of an old person by using a face identification method; obtaining facial information of all pedestrians within a sidewalk monitoring range; conducting similarity measurement on the facial information of the old person and the facial information of the pedestrians, determining the old person whose identity has been verified, and marking the old person; conducting real-time tracking on the marked old person to obtain a street-crossing track; calculating, according to the street-crossing track of the old person, an average speed for crossing a street by the old person; obtaining a distance between the old person and an end point of a sidewalk, and recording the distance as a remaining distance; determining a shortest safe street-crossing time according to the average speed and the remaining distance; and setting a countdown of a prolonged green signal time according to the shortest safe street-crossing time.
Optionally, the conducting similarity measurement on the facial information of the old person and the facial information of the pedestrians, determining the old person whose identity has been verified, and marking the old person specifically includes: extracting feature information from the facial information of the old person; conducting similarity measurement on the feature information and the facial information of the pedestrians, to obtain multiple similarities; determining whether each similarity reaches a specified similarity threshold; if yes, sorting similarities that satisfy the condition, determining an old person corresponding to a maximum similarity as the old person whose identity has been verified, and marking the old person; and triggering a touch signal light to start a green signal time prolonging function; or if no, returning to the step of conducting similarity measurement on the feature information and the facial information of the pedestrians, to obtain similarities.
Optionally, the conducting real-time tracking on the marked old person to obtain a street-crossing track specifically includes: conducting effective extraction of a feature point of each frame of the marked old person to obtain multiple effective feature points; tracking each feature point by using a Kalman filtering method to obtain a feature point track; and characterizing the street-crossing track of the old person by using the multiple effective feature points.
Optionally, the calculating, according to the street-crossing track of the old person, an average speed for crossing a street by the old person specifically includes: obtaining a time at which the old person walks into the sidewalk monitoring area and a distance the old person has walked; and calculating, according to the time and the distance, the average speed for crossing the street by the old person.
To achieve the above purpose, the present invention further provides the following technical solution.
A green signal time prolonging system dedicated for an old person based on a pedestrian re-identification technology includes: a face identification module, configured to collect facial information of an old person by using a face identification method, an obtaining module, configured to obtain facial information of all pedestrians within a sidewalk monitoring range; an old person identity determining module, configured to conduct similarity measurement on the facial information of the old person and the facial information of the pedestrians, determine the old person whose identity has been verified, and mark the old person; a street-crossing track determining module, configured to conduct real-time tracking on the marked old person to obtain a street-crossing track; an average speed determining module, configured to calculate, according to the street-crossing track of the old person, an average speed for crossing a street by the old person; a remaining distance determining module, configured to obtain a distance between the old person and an end point of a sidewalk, and record the distance as a remaining distance; a shortest safe street-crossing time determining module, configured to determine a shortest safe street-crossing time according to the average speed and the remaining distance; and a prolonged green signal time determining module, configured to set a countdown of a prolonged green signal time according to the shortest safe street-crossing time.
Optionally, the old person identity determining module specifically includes: a feature information extraction unit, configured to extract feature information from the facial information of the old person; a similarity comparison unit, configured to conduct similarity measurement on the feature information and the facial information of the pedestrians, to obtain multiple similarities; a determining unit, configured to determine whether each similarity reaches a specified similarity threshold; an old person identity determining unit, configured to: when the similarity reaches the specified similarity threshold, sort similarities that satisfy the condition, determine an old person corresponding to a maximum similarity as the old person whose identity has been verified, and mark the old person; a triggering unit, configured to trigger a touch signal light to start a green signal time prolonging function; and a returning unit, configured to: when the similarity does not reach the specified similarity threshold, return to the step of conducting similarity measurement on the feature information and the facial information of the pedestrians, to obtain similarities.
Optionally, the street-crossing track determining module specifically includes: a feature point extraction unit, configured to conduct effective extraction of a feature point of each frame of the marked old person to obtain multiple effective feature points; a tracking unit, configured to track each feature point by using a Kalman filtering method to obtain a feature point track; and a street-crossing track determining unit, configured to characterize the street-crossing track ofthe old person by using the multiple effective feature points.
Optionally, the average speed determining module specifically includes: an obtaining unit, configured to obtain a time at which the old person walks into the sidewalk monitoring area and a distance the old person has walked; and an average speed determining unit, configured to calculate, according to the time and the distance, the average speed for crossing the street by the old person.
To achieve the above purpose, the present invention further provides the following technical solution.
A green signal time prolonging apparatus dedicated for an old person based on a pedestrian re-identification technology includes a face identification module, a camera, a touch control signal light, a communications module, a pedestrian re-identification module, a controller, and a display, wherein the touch control signal light is configured to be triggered when an old person crosses a street, the camera is configured to acquire images of all pedestrians within a sidewalk monitoring range and a position image of a street-crossing old person; the face identification module is configured to collect image information of an old person; the communications module is connected to both the face identification module, the controller, and the camera; the communications module is configured to send, to the controller, the image information collected by the face identification module and the images of all the pedestrians acquired by the camera within the sidewalk monitoring range; the controller is configured to receive the images of all the pedestrians acquired by the camera within the sidewalk monitoring range and the image information collected by the face identification module, and determine identity information of the street-crossing old person from the images of all the pedestrians according to the image information collected by the face identification module; the camera is connected to the pedestrian re-identification module; the pedestrian re-identification module is configured to obtain a street-crossing track of the old person according to the location image of the street-crossing old 5 person acquired by the camera; the controller is connected to both the pedestrian re-identification module and the display; and the controller is configured to determine a prolonged green signal time according to the street-crossing track of the old person, and send the prolonged green signal time to the display for display.
According to specific embodiments provided in the present invention, the present invention discloses the following technical effects:
1. Information about an old person is collected and confirmed in a face identification manner, and this is more convenient and reliable.
2. A pedestrian re-identification technology and a tracking technology are comprehensively used to monitor a street-crossing situation of an old person in real time, ensuring that the old person safely crosses a street within a monitoring range.
3. Green signal time prolonging has self-adaptability, a countdown function of a prolonged green signal time is appropriately designed, and the prolonged green signal time may be adjusted according to a real-time passing situation of the old person, furthest reducing a traffic delay caused to motor vehicles while ensuring that the old person safely passes.
BRIEF DESCRIPTION OF THE DRAWINGS To describe the technical solutions in the embodiments of the present invention or in the prior art more clearly, the following briefly introduces the accompanying drawings required for describing the embodiments. Apparently, the accompanying drawings in the following description show merely some embodiments of the present invention, and a person of ordinary skill in the art may still derive other drawings from these accompanying drawings without creative efforts.
FIG 1 is a flowchart of a green signal time prolonging method dedicated for an old person based on a pedestrian re-identification technology according to the present invention; FIG 2 is a structure diagram of a green signal time prolonging system dedicated for an old person based on a pedestrian re-identification technology according to the present invention; FIG 3 is a schematic composition diagram of a green signal time prolonging apparatus dedicated for an old person based on a pedestrian re-identification technology according to the present invention; and FIG 4 is a schematic layout diagram of a green signal time prolonging apparatus dedicated for an old person based on a pedestrian re-identification technology according to the present invention.
DETAILED DESCRIPTION The following clearly and completely describes the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are merely a part rather than all of the embodiments of the present invention. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.
An objective of the present invention is to provide a green signal time prolonging apparatus, system, and apparatus dedicated for an old person, so as to resolve a street-crossing safety problem of the elderly and furthest reduce a delay caused to motor vehicles.
To make the foregoing objective, features, and advantages of the present invention clearer and more comprehensible, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.
FIG 1 is a flowchart of a green signal time prolonging method dedicated for an old person based on a pedestrian re-identification technology according to the present invention. As shown in FIG 1, the green signal time prolonging method dedicated for an old person based on a pedestrian re-identification technology includes the following steps: Step 101. Collect facial information of an old person by using a face identification method, where the step specifically includes: obtaining an image by using a face identification module and a camera, where the image may be a stationary or dynamic video sequence; conducting preprocessing on collected image information, where the preprocessing includes image area segmentation, dimension normalization, gray level normalization, and the like; conducting detection on a preprocessed image, to detect whether the image includes a human face, a number of human faces, and an area and a position including a human face; and extracting the facial information of the old person.
Step 102. Obtain facial information of all pedestrians within a sidewalk monitoring range.
Step 103. Conduct similarity measurement on the facial information of the old person and the facial information of the pedestrians, determine the old person whose identity has been verified, and mark the old person, where the step specifically includes: extracting feature information from the facial information of the old person; conducting similarity measurement on the feature information and the facial information of the pedestrians, to obtain multiple similarities; determining whether each similarity reaches a specified similarity threshold; if yes, sorting similarities that satisfy the condition, and determining an old person corresponding to a maximum similarity as the old person whose identity has been verified, and marking the old person, that is, sorting feature information whose similarity reaches a specific degree, marking feature information with a highest similarity, and determining an old person corresponding to the highest similarity as the old person whose identity has been verified; and triggering a touch signal light to start a green signal time prolonging function; or if no, returning to the step of conducting similarity measurement on the feature information and the facial information of the pedestrians, to obtain similarities.
Step 104. Conduct real-time tracking on the marked old person to obtain a street-crossing track, where the step specifically includes: conducting effective extraction of a feature point of each frame of the marked old person to obtain multiple effective feature points; tracking each feature point by using a Kalman filtering method to obtain a feature point track; and characterizing the street-crossing track of the old person by using the multiple effective feature points.
A Kalman filtering method is used to track a target. First, a feature factor that can be used to fully describe the target is found to differentiate a pedestrian target and another object, where a commonly used feature factor is a gray scale, a color, a texture, or even some motion information feature; and a color feature is selected for particle observation for real-time tracking of the target.
Specific steps for pedestrian tracking are as follows:
1. Conduct pedestrian detection in a first frame of a monitoring video sequence to obtain a detection target, calculate a color histogram of the detection target, assume that prior distribution obeys the Gaussian distribution, and initialize particles, where a particle number is N, and each weight is I/N, that is, (akrl/N ba
2. Obtain a particle state (ap wij at a moment k based on a particle state at a moment k-1 according to a system state transition model.
The system state transition model includes state and measurement equations used during track extraction. ak = & (x -DAk -1+ Dk -1 bx = Ika + Fx In the formulas, a; is an nx1-dimensional state vector of a system state, ax; is an n> l-dimensional state vector of the system state at a moment tii; bx is an mx1-dimensional vector of an observed system state; 91 1S an nxn-dimensional state transition matrix from the moment tx-1to a moment ty, Ir 1s an mxn-dimensional measurement matrix at the moment tx; Dig
1s an nx 1-dimensional random vector with random interference at the moment t:1; and Fy is an mx*1-dimensional observation noise vector at the moment tx.
3. For each particle, calculate a similarity Ly, according to an observation model by using the color histogram, where 1 represents 1 to n; and obtain a newest particle weight through similarity normalization: Wo Leal - Ls :
4. Conduct similarity measurement according to the weight, and if n pedestrians are detected, Noi estimate a posteriori probability 2 it according to a weight of each particle in a frame as reliability Tw , and use a pedestrian whose reliability exceeds a threshold To and whose ranking is highest as a target pedestrian for tracking.
5. Repeat the foregoing operation on a next frame, and continue to conduct pedestrian tracking, Because a linear relationship between two states at a moment t and a moment t-1 is described in a Kalman filtering algorithm, a state at the moment t can be obtained only by inputting an observed quantity at the moment t—1 based on space-time information, while the input observed quantity needs to be based on specific space-time information. Therefore, with reference to context space-time information, a position in which a target is marked in a next frame of image is predicted, and two-dimension search is conducted to obtain a foreground with a largest correlation with a contour to which the predicted position point belongs, to implement pedestrian tracking; a feature track is extracted; and after track extraction and tracking, a track feature on the image is converted to a true movement track feature, so as to obtain the street-crossing track of the old person.
Step 105. Calculate, according to the street-crossing track of the old person, an average speed for crossing a street by the old person, where the step specifically includes: obtaining a time at which the old person walks into the sidewalk monitoring area and a distance for which the old person has walked; and calculating, according to the time and the distance, the average speed for crossing the street by the old person.
Step 106. Obtain a distance between the old person and an end point of a sidewalk, and record the distance as a remaining distance.
Step 107. Determine a shortest safe street-crossing time according to the average speed and the remaining distance.
Step 108. Set a countdown of a prolonged green signal time according to the shortest safe street-crossing time.
A yellow line is set in a target position of a video monitoring screen. When a central coordinate of a detection frame of a target old person intersects with any coordinate within the yellow line, a count of a counter is increased by 1. In this case, a countdown of a prolonged green signal time is set by calculating a shortest safe street-crossing time. This step is conducted to furthest reduce a traffic delay caused to motor vehicles while ensuring that the old person safely passes.
In the present invention, based on a pedestrian re-identification technology, pedestrian detection, pedestrian re-identification, pedestrian tracking, video detection, and the like are conducted to implement a green signal time prolonging function dedicated for an old person, implementing the following functions based on existing research:
1. Information about an old person is collected and confirmed in a face identification manner, and this is more convenient and reliable.
2. A pedestrian re-identification technology and a tracking technology are comprehensively used to monitor a street-crossing situation of an old person in real time, ensuring that the old person safely crosses a street within a monitoring range.
3. Green signal time prolonging has self-adaptability, a green signal time prolonging countdown function is appropriately designed, and a prolonged green signal time may be adjusted according to a real-time passing situation of the old person, furthest reducing a traffic delay caused to motor vehicles while ensuring that the old person safely passes.
FIG 2 is a structure diagram of a green signal time prolonging system dedicated for an old person based on a pedestrian re-identification technology according to the present invention. As shown in FIG 2, the green signal time prolonging system dedicated for an old person based on a pedestrian re-identification technology includes: a face identification module 201, configured to collect facial information of an old person by using a face identification method, an obtaining module 202, configured to obtain facial information of all pedestrians within a sidewalk monitoring range; an old person identity determining module 203, configured to conduct similarity measurement on the facial information of the old person and the facial information of the pedestrians, determine the old person whose identity has been verified, and mark the old person; a street-crossing track determining module 204, configured to conduct real-time tracking on the marked old person to obtain a street-crossing track; an average speed determining module 205, configured to calculate, according to the street-crossing track of the old person, an average speed for crossing a street by the old person;
a remaining distance determining module 206, configured to obtain a distance between the old person and an end point of a sidewalk, and record the distance as a remaining distance; a shortest safe street-crossing time determining module 207, configured to determine a shortest safe street-crossing time according to the average speed and the remaining distance; and a prolonged green signal time determining module 208, configured to set a countdown of a prolonged green signal time according to the shortest safe street-crossing time.
The old person identity determining module 203 specifically includes: a feature information extraction unit, configured to extract feature information from the facial information of the old person; a similarity comparison unit, configured to conduct similarity measurement on the feature information and the facial information of the pedestrians, to obtain multiple similarities; a determining unit, configured to determine whether each similarity reaches a specified similarity threshold; an old person identity determining unit, configured to: when the similarity reaches the specified similarity threshold, sort similarities that satisfy the condition, determine an old person corresponding to a maximum similarity as the old person whose identity has been verified, and mark the old person; a triggering unit, configured to trigger a touch signal light to start a green signal time prolonging function; and a returning unit, configured to: when the similarity does not reach the specified similarity threshold, return to the step of conducting similarity measurement on the feature information and the facial information of the pedestrians, to obtain similarities.
The street-crossing track determining module 204 specifically includes: a feature point extraction unit, configured to conduct effective extraction of a feature point of each frame of the marked old person to obtain multiple effective feature points; a tracking unit, configured to track each feature point by using a Kalman filtering method to obtain a feature point track; and a street-crossing track determining unit, configured to characterize the street-crossing track of the old person by using the multiple effective feature points.
The average speed determining module 205 specifically includes: an obtaining unit, configured to obtain a time at which the old person walks into the sidewalk monitoring area and a distance the old person has walked; and an average speed determining unit, configured to calculate, according to the time and the distance, the average speed for crossing the street by the old person.
FIG 3 is a schematic composition diagram of a green signal time prolonging apparatus dedicated for an old person based on a pedestrian re-identification technology according to the present invention.
As shown in FIG 3, the green signal time prolonging apparatus dedicated for an old person based on a pedestrian re-identification technology includes a touch control signal light 1, a face identification module 2, a communications module 3, a camera 4, a pedestrian re-identification module 5, a controller 6, and a display 7, where the touch control signal light 1 is configured to be triggered when an old person crosses a street; the camera 4 is configured to acquire images of all pedestrians within a sidewalk monitoring range and a position image of a street-crossing old person; the face identification module 2 is configured to collect image information of an old person; the communications module 3 is connected to both the face identification module 2, the controller 6, and the camera 4; the communications module 3 is configured to send, to the controller 6, the image information collected by the face identification module 2 and the images of all the pedestrians acquired by the camera 4 within the sidewalk monitoring range; the controller 6 is configured to receive the images of all the pedestrians acquired by the camera 4 within the sidewalk monitoring range and the image information collected by the face identification module 2, and determine identity information of the street-crossing old person from the images of all the pedestrians according to the image information collected by the face identification module 2; the camera 4 is connected to the pedestrian re-identification module 5; the pedestrian re-identification module 5 1s configured to obtain a street-crossing track of the old person according to the position image of the street-crossing old person acquired by the camera 4; the controller 6 is connected to both the pedestrian re-identification module 5 and the display 7; and the controller 6 is configured to determine a prolonged green signal time according to the street-crossing track of the old person, and send the prolonged green signal time to the display 7 for display.
The pedestrian re-identification module 5 specifically includes an aligning unit, a feature extraction unit, and a feature fusion unit that are connected in sequence, where the aligning unit is configured to receive a video image sequence, and complete space alignment of the video image sequence through two-dimensional space affine transformation; the feature extraction unit is configured to extract global features of multiple frames of the video image sequence that has undergone the two-dimensional space affine transformation; and the feature fusion unit is configured to fuse the global features of the multiple frames of the video image sequence, to obtain image features of an equal length at a sequence level to determine the street-crossing track of the old person.
FIG. 4 is a schematic layout diagram of a green signal time prolonging apparatus dedicated for an old person based on a pedestrian re-identification technology according to the present invention.
As shown in FIG. 4, the face identification module 2 is located on one side of the sidewalk, and the touch signal light 1, the camera 4, and the display 7 are located on the other side of the sidewalk.
Each embodiment of the present specification is described in a progressive manner, each embodiment focuses on the difference from other embodiments, and the same and similar parts between the embodiments may refer to each other.
For a system disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and reference can be made to the method description.
Several examples are used for illustration of the principles and implementation methods of the present invention.
The description of the embodiments is used to help illustrate the method and its core principles of the present invention.
In addition, those skilled in the art can make various modifications in terms of specific embodiments and scope of application in accordance with the teachings of the present invention.
In conclusion, the content of this specification shall not be construed as a limitation to the invention.
Claims (9)
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910868606.XA CN110633670B (en) | 2019-09-16 | 2019-09-16 | Special green letter extension method, system and device for old people |
Publications (2)
Publication Number | Publication Date |
---|---|
NL2025140A NL2025140A (en) | 2021-05-17 |
NL2025140B1 true NL2025140B1 (en) | 2022-02-22 |
Family
ID=68972489
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
NL2025140A NL2025140B1 (en) | 2019-09-16 | 2020-03-16 | Green signal control method and apparatus dedicated for old person crossing the street |
Country Status (4)
Country | Link |
---|---|
CN (1) | CN110633670B (en) |
LU (1) | LU102035B1 (en) |
NL (1) | NL2025140B1 (en) |
ZA (1) | ZA201907214B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114973718A (en) * | 2022-05-19 | 2022-08-30 | 重庆捷尔博模具科技有限公司 | Intelligent traffic light device |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102437868A (en) * | 2011-12-06 | 2012-05-02 | 华中科技大学 | Urban internet of things system based on intelligent road lamp |
CN103680142B (en) * | 2013-12-23 | 2016-03-23 | 苏州君立软件有限公司 | A kind of traffic intersection intelligent control method |
CN105262987A (en) * | 2015-09-24 | 2016-01-20 | 北京尚易德科技有限公司 | Road full-covering panoramic intelligent video monitoring system and method based on Internet of Things |
CN106257555A (en) * | 2016-08-23 | 2016-12-28 | 成都亚加斯科技有限公司 | A kind of intelligent traffic light control system based on LED street lamp |
CN108875507B (en) * | 2017-11-22 | 2021-07-23 | 北京旷视科技有限公司 | Pedestrian tracking method, apparatus, system, and computer-readable storage medium |
CN109191870A (en) * | 2018-09-28 | 2019-01-11 | 无锡市政设计研究院有限公司 | A kind of signal lamp green light time adjusting method crossed the street convenient for disabled person, old man |
-
2019
- 2019-09-16 CN CN201910868606.XA patent/CN110633670B/en active Active
- 2019-10-30 ZA ZA201907214A patent/ZA201907214B/en unknown
-
2020
- 2020-03-16 NL NL2025140A patent/NL2025140B1/en not_active IP Right Cessation
- 2020-09-08 LU LU102035A patent/LU102035B1/en active IP Right Grant
Also Published As
Publication number | Publication date |
---|---|
LU102035B1 (en) | 2021-03-17 |
CN110633670B (en) | 2023-08-08 |
ZA201907214B (en) | 2020-11-25 |
CN110633670A (en) | 2019-12-31 |
NL2025140A (en) | 2021-05-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9679203B2 (en) | Traffic violation detection | |
Pai et al. | Pedestrian detection and tracking at crossroads | |
US9685079B2 (en) | Short-time stopping detection from red light camera evidentiary photos | |
Hsieh et al. | Shadow elimination for effective moving object detection by Gaussian shadow modeling | |
CN102765365B (en) | Pedestrian detection method based on machine vision and pedestrian anti-collision warning system based on machine vision | |
Liu et al. | Detecting and counting people in surveillance applications | |
Sivaraman et al. | Combining monocular and stereo-vision for real-time vehicle ranging and tracking on multilane highways | |
CN106448160B (en) | Target person tracking method combining vehicle running track and monitoring video data | |
CN106778655B (en) | Human body skeleton-based entrance trailing entry detection method | |
CN103971380A (en) | Pedestrian trailing detection method based on RGB-D | |
CN104680133B (en) | A kind of violation car allows people's behavior real-time detection method | |
Xia et al. | Integrating 3D structure into traffic scene understanding with RGB-D data | |
KR20160065703A (en) | Method and system for detection of sudden pedestrian crossing for safe driving during night time | |
NL2025140B1 (en) | Green signal control method and apparatus dedicated for old person crossing the street | |
Swathy et al. | Survey on vehicle detection and tracking techniques in video surveillance | |
Nowosielski et al. | Automatic analysis of vehicle trajectory applied to visual surveillance | |
Khan | Estimating Speeds and Directions of Pedestrians in Real-Time Videos: A solution to Road-Safety Problem. | |
Selvi et al. | Automatic video surveillance system for pedestrian crossing using digital image processing | |
Huang et al. | A vehicle flow counting system in rainy environment based on vehicle feature analysis. | |
Mokha et al. | A review of computer vision system for the vehicle identification and classification from online and offline videos | |
Kapileswar et al. | Automatic traffic monitoring system using lane centre edges | |
Tran et al. | Pedestrian activity prediction based on semantic segmentation and hybrid of machines | |
Gao et al. | Crossing road monitoring system based on adaptive decision for illegal situation | |
Singh et al. | Detection of vacant parking spaces through the use of convolutional neural network | |
Tai et al. | Automatic contour initialization for image tracking of multi-lane vehicles and motorcycles |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
MM | Lapsed because of non-payment of the annual fee |
Effective date: 20230401 |