WO2017158648A1 - 乗車人数計測装置、システム、方法およびプログラム - Google Patents
乗車人数計測装置、システム、方法およびプログラム Download PDFInfo
- Publication number
- WO2017158648A1 WO2017158648A1 PCT/JP2016/001557 JP2016001557W WO2017158648A1 WO 2017158648 A1 WO2017158648 A1 WO 2017158648A1 JP 2016001557 W JP2016001557 W JP 2016001557W WO 2017158648 A1 WO2017158648 A1 WO 2017158648A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- vehicle
- passengers
- photographing
- passenger
- Prior art date
Links
Images
Classifications
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2134—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on separation criteria, e.g. independent component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/143—Sensing or illuminating at different wavelengths
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/147—Details of sensors, e.g. sensor lenses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
-
- 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
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/593—Recognising seat occupancy
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/167—Detection; Localisation; Normalisation using comparisons between temporally consecutive images
-
- 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
- G06T2207/30242—Counting objects in image
-
- 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
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
Definitions
- the present invention relates to a passenger number measuring device, system, method and program for measuring the number of passengers in a vehicle.
- HOV high occupancy vehicle
- a technique is used in which a vehicle is photographed by a camera and the number of passengers is measured by performing face detection on the photographed image.
- Patent Documents 1 to 3 disclose a system for measuring the number of people in a vehicle by detecting a face.
- Patent Document 1 discloses a technique for measuring the number of people on a vehicle by detecting a person's profile.
- Patent Document 2 discloses a technique for measuring the number of passengers by detecting a person and estimating where the person is in the vehicle.
- Patent Document 3 discloses a technique for measuring the number of passengers using a vehicle movement amount and a person detection result.
- an object of the present invention is to provide a passenger number measuring device, system, method and program capable of accurately measuring the number of passengers in a vehicle.
- the passenger counting device is based on a first image obtained by photographing a vehicle and a second image obtained by photographing the vehicle while receiving only light in the first specific wavelength band. And an image separating means for acquiring a plurality of separated images and a passenger number determining means for determining the number of passengers of the vehicle based on the plurality of separated images.
- the passenger number counting system acquires a second image by capturing a vehicle in a state in which only the light of the first specific wavelength band is received, and a first imaging unit that captures the vehicle and acquires the first image.
- the method for measuring the number of passengers according to the present invention is based on a first image obtained by photographing a vehicle and a second image obtained by photographing the vehicle while receiving only light in the first specific wavelength band. A plurality of separated images are acquired, and the number of passengers of the vehicle is determined based on the plurality of separated images.
- the passenger counting program includes a first image obtained by photographing a vehicle on a computer, and a second image obtained by photographing the vehicle while receiving only light in the first specific wavelength band. Based on the above, an image separation process for acquiring a plurality of separated images and a passenger number determination process for determining the number of passengers on the vehicle based on the plurality of separated images are executed.
- FIG. 1 is a block diagram showing a configuration of a passenger number measuring system according to this embodiment.
- the passenger number measuring system includes a first photographing unit 10, a second photographing unit 11, and a passenger number counting device 100.
- the passenger number measuring device 100 includes an image separation unit 12 and a passenger number determination unit 13.
- the first photographing unit 10 photographs a vehicle and acquires a first image.
- the first photographing unit 10 is a general camera and photographs a vehicle that is a subject to generate a digital image.
- the second imaging unit 11 captures the vehicle in a state where only the first specific wavelength band is received and acquires the second image.
- the second photographing unit 11 is a general camera, similar to the first photographing unit 10, and photographs a vehicle that is a subject to generate a digital image.
- the second imaging unit 11 has at least sensitivity of light in the first specific wavelength band.
- the image separation unit 12 performs image separation based on the first image acquired by the first imaging unit 10 and the second image acquired by the second imaging unit 11, and the separation in which the reflection on the glass window is reduced is performed. A plurality of separated images including images are acquired. Specifically, the image separation unit 12 separates two images having different distances from the first photographing unit 10 and the second photographing unit 11 using independent component analysis.
- the number of passengers determination unit 13 determines the number of passengers based on the plurality of separated images output by the image separation unit 12. Specifically, the passenger number determination unit 13 acquires a plurality of separated images output by the image separation unit 12, performs face detection on the separated images with reduced reflection, and determines that the face is a person's face. The number of parts is determined as the number of passengers in the vehicle.
- FIG. 2 is an explanatory diagram showing a hardware configuration of the passenger number measuring system of the present embodiment.
- photography part 11 are installed in the position which can image
- a half mirror 20 is installed in front of the first imaging unit 10 (between the first imaging unit 10 and the vehicle).
- a reflection mirror 21 is installed in front of the second photographing unit 11 (a position where the reflected light from the half mirror 20 is received).
- a band pass filter 22 is installed between the second imaging unit 11 and the reflection mirror 21.
- Bandpass filter 22 is a filter capable of passing only the first specific wavelength band lambda 1 light.
- the half mirror 20 Part of the light incident from the direction of the vehicle passes through the half mirror 20 and enters the first imaging unit 10. Further, the remaining part of the light incident from the direction of the vehicle is reflected by the half mirror 20 and enters the reflection mirror 21. The light incident on the reflection mirror 21 is reflected, passes through the band pass filter 22, and only the light of the first specific wavelength body ⁇ 1 enters the second imaging unit 11.
- each device is installed so that the optical path length from the first imaging unit 10 to the vehicle is the same as the optical path length from the second imaging unit 11 to the vehicle.
- the first photographing unit 10 and the second photographing unit 11 perform photographing so that the photographing range of the first photographing unit 10 and the photographing range of the second photographing unit 11 are the same.
- the illumination 23 which irradiates the light of 1st specific wavelength band (lambda) 1 is installed in the position which can irradiate the vehicle which passes, and irradiates the whole vehicle. As the light passes through the band-pass filter 22, the amount of light is reduced compared to that before the passage. However, since the illumination 23 irradiates the vehicle with light of the first specific wavelength band ⁇ 1 , the second imaging unit 11 can obtain a sufficient amount of light, and thus can acquire a clear vehicle image. it can.
- the first imaging unit 10 can capture a normal vehicle image in a state where the wavelength of incident light is not limited.
- photography part 11 can image
- FIG. 2 is a flowchart showing the operation of the passenger number measuring system of the present embodiment.
- the first photographing unit 10 photographs the vehicle and acquires an image (step S10).
- the first imaging unit 10 is installed on the road side, for example, and images the vehicle from the lateral direction (perpendicular to the traveling direction of the vehicle).
- photographs a vehicle in the state which received only the light of the 1st specific wavelength band, and acquires an image (step S11).
- the second imaging unit 11 is installed on the road side, for example, and images the vehicle from the lateral direction (perpendicular to the traveling direction of the vehicle). Since the bandpass filter 22 in front of the second imaging unit 11 is installed, the second imaging unit 11 photographs the vehicle while entering only the first light of the specific wavelength body lambda 1.
- the installation positions of the first imaging unit 10 and the second imaging unit 11 are not limited to the above positions, and may be set to positions at which imaging can be performed from the front or diagonally forward of the vehicle.
- photography part 11 are installed in the toll booth using the HOV system, for example.
- the first photographing unit 10 and the second photographing unit 11 photograph the vehicle at the same timing.
- the passenger counting device 100 transmits an instruction signal to the first photographing unit 10 and the second photographing unit 11.
- detection means such as an infrared sensor is installed, and the first measurement is performed when the passenger counting device 100 receives a signal indicating that the vehicle has passed from the detection means.
- An instruction signal may be transmitted to the imaging unit 10 and the second imaging unit 11.
- photography part 11 may receive the signal which shows that the vehicle passed from the detection means directly, and may image
- the image separation unit 12 performs image separation based on a first image obtained by photographing the vehicle by the first photographing unit 10 and a second image obtained by photographing the vehicle by the second photographing unit 11. Then, a plurality of separated images including a separated image with reduced reflection on the glass window are acquired (step S12). Specifically, the image separation unit 12 performs independent component analysis on the image data indicating the first image and the second image, and reflects the image showing the inside of the vehicle and the reflection on the glass window (the person or object reflected on the glass window). Etc.) are separated.
- the image data representing the first image represents a x 1, represents the image data representing the second image and x 2. Also, it represents the actual image showing the inside the vehicle s 1 and represents the actual image shows a reflection of the glass window and s 2.
- the image separation unit 12 outputs image data that is an approximate value of s 1 indicating the inside of the vehicle among y 1 and y 2 indicating the image data as a separated image with reduced reflection. For example, the image separation unit 12 analyzes the images y 1 and y 2 and determines whether the image is in the vehicle based on the presence of a person's face and in-vehicle equipment.
- the image separation unit 12 outputs the images indicated by y 1 and y 2 to an external display device, and allows the user to select which image is an in-vehicle image, thereby reducing the reflection of the selected image. You may output as a separated image. Further, the image separation unit 12 may determine which image is an image with reduced reflection by a specific method, and output the determined image as a separated image with reduced reflection. Specifically, the image separation unit 12 applies a face detection algorithm to the images indicated by y 1 and y 2 and acquires the number of faces. Thereafter, the image separation unit 12 may select and output an image having a larger number of faces as a separated image with reduced reflection.
- the number of faces is not particularly limited, and any part of the person that can be detected may be used, and the nose, eyes, arms, neck, and the like can be detected.
- the occupant number measuring device 100 includes a selection unit that selects an image with reduced reflection from a plurality of separated images, and a person identification for the plurality of separated images. You may provide the acquisition means which acquires the number of site
- FIG. 4 is an explanatory diagram showing a first image acquired by the first imaging unit 10.
- FIG. 5 is an explanatory diagram showing a separated image in the present embodiment.
- a tree outside the vehicle is reflected in the glass window of the vehicle, and is displayed overlapping the face of a person in the vehicle.
- the reflection on the glass window is reduced, and the face of the person in the vehicle is clearly displayed.
- the other separated images show the reflection on the glass window. That is, based on the first image and the second image, the images are separated into two images having different distances from the first photographing unit 10 and the second photographing unit 11.
- the number of passengers determination unit 13 determines the number of passengers of the vehicle based on the plurality of separated images output by the image separation unit 12 (step S13). Specifically, the passenger number determination unit 13 acquires a plurality of separated images output by the image separation unit 12, performs face detection on the separated images with reduced reflection, and determines that the face is a person's face. The number of parts is determined as the number of passengers in the vehicle.
- the boarding person number determination unit 13 detects the person using the side face detector.
- the boarding person number determination unit 13 detects the person using the front face detector.
- These detectors are constructed in advance by performing machine learning using a large number of face images photographed from the side or the front, and are stored in a storage unit (for example, an auxiliary storage device 1003 described later).
- the detector used for detection is obtained by, for example, SVM (Support Vector Machine), LDA (Lent Dirichlet Allocation, linear discriminant analysis), or GLVQ (Generalized Learning Vector Quantization, a generalized learning vector quantizer). .
- the passenger counting system of this embodiment can reduce the reflection on the glass window of the vehicle by performing image separation using independent component analysis. It can be measured.
- FIG. 6 is a block diagram showing the configuration of the passenger number measuring system of this embodiment.
- the passenger number measuring system includes a first photographing unit 10, a second photographing unit 11, a third photographing unit 14, and a passenger counting device 100.
- the passenger number measuring device 100 includes an image separation unit 12 and a passenger number determination unit 13.
- the passenger number measuring system of the present embodiment has a configuration in which a third photographing unit 14 is added to the passenger number measuring system of the first embodiment.
- the third imaging unit 14 captures the vehicle in a state where only the second specific wavelength band different from the first specific wavelength band is received, and acquires the third image.
- the third image capturing unit 14 is a general camera, similar to the first image capturing unit 10 and the second image capturing unit 11, and captures a vehicle as a subject to generate a digital image.
- the third imaging unit 14 has at least sensitivity of light in the second specific wavelength band.
- FIG. 7 is an explanatory diagram showing a hardware configuration of the passenger number measuring system of the present embodiment.
- photography part 14 is installed in the position which can image
- a band pass filter 26 is installed in front of the third imaging unit 14.
- Bandpass filter 26 is a filter capable of passing only the second light in a specific wavelength band lambda 2.
- a half mirror 25 is installed in front of the first photographing unit 10. A part of the light incident on the half mirror 25 from the direction of the vehicle is reflected and incident on the reflection mirror 27. The light incident on the reflection mirror 27 is reflected and passes through the bandpass filter 26 and enters the third imaging unit 14.
- the illumination 24 which irradiates the light of 2nd specific wavelength band (lambda) 2 is installed in the position which can irradiate a vehicle, and irradiates the whole vehicle. Since other configurations are the same as those of the first embodiment, description thereof is omitted.
- the optical path length from the first imaging unit 10 to the vehicle, the optical path length from the second imaging unit 11 to the vehicle, and the optical path length from the third imaging unit 14 to the vehicle are the same.
- each device is installed.
- the first imaging unit 10, the second imaging unit 11, and the third imaging unit 10 are configured so that the imaging range of the first imaging unit 10, the imaging range of the second imaging unit 11, and the imaging range of the third imaging unit 14 are the same.
- the photographing unit 14 performs photographing.
- the third imaging unit 14 can capture a vehicle image in a state where only the light of the second specific wavelength body ⁇ 2 is incident. As light passes through the bandpass filter 26, the amount of light decreases. However, since the illumination 24 irradiates the vehicle with light of the second specific wavelength band ⁇ 2 , the third imaging unit 14 can obtain a sufficient amount of light, and thus can obtain a clear vehicle image. .
- FIG. 2 is a flowchart showing the operation of the passenger number measuring system of the present embodiment. Note that the processing in step S10, step S11, and step S13 illustrated in FIG. 2 is the same as that in the first embodiment, and thus description thereof is omitted.
- the third photographing unit 14 photographs the vehicle in a state where only the light in the second specific wavelength band is received, and acquires an image (step S11 ′).
- photography part 14 should just be a position which can image
- the third imaging unit 14 is installed on the road side and images the vehicle from the lateral direction (the vehicle traveling direction and the vertical direction).
- the band-pass filter 26 in front of the third imaging unit 14 is installed, the third imaging unit 14 photographs the vehicle while entering only the second light of the specific wavelength member lambda 2.
- the third photographing unit 14 photographs the vehicle at the same timing as the first photographing unit 10 and the second photographing unit 11.
- the image separation unit 12 includes a first image acquired by the first imaging unit 10 imaging a vehicle, a second image acquired by the second imaging unit 11 imaging the vehicle, and a third imaging unit 14 Image separation is performed based on the third image obtained by photographing the vehicle, and a separated image in which the reflection on the glass window and the density of the vehicle body portion of the vehicle are reduced is obtained (step S12 ′). Specifically, the image separation unit 12 performs independent component analysis on the image data indicating the first image, the second image, and the third image, and reflects the image indicating the inside of the vehicle and the reflection on the glass window (on the glass window). An image showing a person or an object) is separated from a portion excluding a glass window of the vehicle (hereinafter referred to as a vehicle body portion).
- the image data representing the first image represents a x 1
- the image data representing the second image represents a x 2, representing the image data of a third image and x 3.
- the actual image shows the interior of the vehicle and s 1
- the actual image shows a reflection of the glass window expressed as s 2, representing the actual image showing the body portion of the vehicle and s 3.
- the image separation unit 12 calculates the vector Y in Expression (2).
- the vector Y (y 1 , y 2 , y 3 ).
- the image separation unit 12 estimates y 1 , y 2 , and y 3 by calculating a matrix W such that y 1 , y 2 , and y 3 are independent.
- the y 1 , y 2 , and y 3 obtained as described above are approximate values of s 1 , one representing the interior of the vehicle, and the other one is an approximation of s 2 representing the reflection on the glass window. It has a value, other one is the approximation of s 3 showing the body portion of the vehicle.
- the image separation unit 12 reflects image data which is an approximate value of s 1 indicating the inside of the vehicle among y 1 , y 2 and y 3 indicating the image data, and the density of the vehicle body portion of the vehicle is reduced. Output as a separated image.
- the image separation unit 12 analyzes the images y 1 , y 2 , and y 3 and determines whether the image is in the vehicle based on the person's face and the presence / absence of in-vehicle equipment.
- the image separation unit 12 outputs the images indicated by y 1 , y 2 , and y 3 to an external display device, causes the user to select which image is an image in the vehicle, and displays the selected image data. And a separated image in which the density of the body part of the vehicle is reduced.
- FIG. 9 is an explanatory diagram showing a separated image in the present embodiment.
- the reflection on the glass window is reduced, and the face of the person in the vehicle is clearly displayed. Furthermore, the density of the vehicle body is reduced.
- the separated image shows the reflection on the glass window and the main body of the vehicle.
- the vehicle image includes a vehicle body part
- the user performs image processing and excludes the vehicle body part in advance before performing face detection.
- the vehicle body portion of the vehicle has already been removed from the separated image of the present embodiment. Therefore, the number of passengers determination unit 13 can detect the number of passengers with high accuracy in the process of performing face detection and determining the number of passengers in the vehicle.
- the occupant counting system of the present embodiment can reduce the density of the vehicle body part as well as the reflection on the glass window of the vehicle by performing image separation using independent component analysis. it can. Therefore, according to the passenger number measuring system of the present embodiment, the number of passengers in the vehicle can be accurately measured without the user performing image processing for removing the vehicle body part.
- FIG. A passenger number measuring system according to this embodiment will be described with reference to the drawings.
- the function of the passenger number determination unit 13 is different from that of the first embodiment, and the other configurations are the same.
- the configuration and functions that are not particularly described are the same as those in the first embodiment.
- FIG. 10 is a flowchart showing the operation of the passenger counting system of the third embodiment.
- steps S10 to S12 are the same as the processing of the first embodiment (see FIG. 3), and thus the description thereof is omitted.
- the number-of-passengers determination unit 13 acquires a plurality of separated images output by the image separation unit 12, but it may be difficult to determine which separated image is a separated image in which the reflection is reduced. Therefore, the passenger number determination unit 13 performs face detection processing on all acquired separated images, and acquires the number of passengers in each separated image (step S13a).
- the number of passengers determination unit 13 determines the maximum value of the number of passengers in each separated image as the actual number of passengers (step S13b).
- the image separation unit 12 performs processing for determining which of the separated images is reduced in reflection, and causing the user to select. However, in the present embodiment, these processing are performed. It may be omitted.
- the passenger number determination unit 13 of the passenger number measurement system in the first embodiment is changed.
- the passenger number determination of the present embodiment is performed. Part 13 may be applied.
- the passenger counting system of the present embodiment it is possible to determine the number of passengers with high accuracy even when it is difficult to determine which separated image is a separated image with reduced reflection.
- FIG. 11 is a schematic block diagram showing a configuration example of a computer according to the first to third embodiments.
- the computer 1000 includes a CPU 1001, a main storage device 1002, an auxiliary storage device 1003, an interface 1004, a display device 1005, and an input device 1006.
- the passenger counting device 100 of the first to third embodiments is mounted on a computer 1000.
- the passenger counting device 100 is stored in the auxiliary storage device 1003 in the form of a program.
- the CPU 1001 reads out the program from the auxiliary storage device 1003, develops it in the main storage device 1002, and executes the above processing according to the program.
- the auxiliary storage device 1003 is a tangible medium that is not temporary, and is, for example, a magnetic disk, a magneto-optical disk, a CD-ROM, a DVD-ROM, or a semiconductor memory.
- the computer 1000 may be connected to the auxiliary storage device 1003 via the interface 1004. When this program is distributed to the computer 1000 via a communication line, the computer 1000 that has received the distribution may develop the program in the main storage device 1002 and execute the above processing.
- the program may be for realizing a part of the above-described processing.
- the program may be a differential program that realizes the above-described processing in combination with another program already stored in the auxiliary storage device 1003.
- the processor included in the computer 1000 is not limited to the CPU 1001, and may be any processor that can execute a program.
- the computer 1000 includes a circuit.
- FIG. 12 is a block diagram showing the main part of the passenger counting system according to the present invention.
- the passenger counting system according to the present invention captures the vehicle in a state where only the light of the first specific wavelength band is received, and obtains the second image by capturing the vehicle and capturing the first image.
- Second imaging means 31 and a passenger counting device 200 are provided.
- the number-of-passengers measuring device 200 is based on the first image and the second image, the image separation means 42 for acquiring a plurality of separated images, and the number of passengers determined for determining the number of passengers on the vehicle based on the plurality of separated images. Means 43.
- the passenger number measuring system shown in the following (1) to (7) is also disclosed.
- the passenger number determination means acquires the number of passengers for each of the plurality of separated images, and sets the maximum value of the acquired number of passengers to the vehicle. The number of passengers may be determined.
- the passenger counting system may be configured such that the image separation means (for example, the image separation unit 12) performs image separation using independent component analysis. According to such a passenger number measuring system, image separation can be executed only from the first image and the second image.
- image separation means for example, the image separation unit 12
- the image separation means (for example, the image separation section 12) is configured so that the first photographing means (for example, the first photographing section 10) and the second image separation means (for example, the first photographing section 10) are based on the first image and the second image. You may comprise so that it may isolate
- the passenger counting system may be configured to include an irradiating unit (for example, the illumination 23) that irradiates the vehicle with light in the first specific wavelength band. According to such a passenger counting system, it is possible to compensate for a decrease in the amount of light even when only the light in the first specific wavelength band is received.
- an irradiating unit for example, the illumination 23
- the passenger count measuring system may be configured such that the optical path length from the first photographing means to the vehicle is the same as the optical path length from the second photographing means to the vehicle.
- the passenger number measuring system may be configured such that the shooting range of the first shooting unit and the shooting range of the second shooting unit are the same.
- First imaging means e.g., first imaging unit 10 that captures the vehicle and acquires the first image, and captures the vehicle in a state where only the light in the first specific wavelength band is received, and the second image.
- Second imaging means for example, the second imaging unit 11 for acquiring a second image for capturing a third image by capturing the vehicle in a state where only light in a second specific wavelength band different from the first specific wavelength band is received.
- Three image capturing units for example, the third image capturing unit 14
- an image separating unit for example, the image separating unit 12
- a passenger number measuring system comprising passenger number determining means (for example, a passenger number determining unit 13) for determining the number of passengers of a vehicle based on the separated images. According to such a passenger counting system, not only the reflection on the glass window but also the concentration of the vehicle body portion of the vehicle can be reduced, so that it is possible to save the user from having to remove them.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Vascular Medicine (AREA)
- Medical Informatics (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
Description
本実施形態の乗車人数計測システムの構成を、図1および図2を参照して説明する。図1は、本実施形態の乗車人数計測システムの構成を示すブロック図である。乗車人数計測システムは、第1撮影部10と、第2撮影部11と、乗車人数計数装置100とを備える。また、乗車人数計測装置100は、画像分離部12と、乗車人数決定部13とを備える。
本実施形態の乗車人数計測システムを、図面を参照して説明する。なお、以下の説明は、主に第1の実施形態(実施形態1)と異なる構成および機能に関する内容であり、特に説明しない構成および機能は、第1の実施形態と同様であるとする。図6は、本実施形態の乗車人数計測システムの構成を示すブロック図である。乗車人数計測システムは、第1撮影部10、第2撮影部11、第3撮影部14、乗車人数計数装置100を備える。また、乗車人数計測装置100は、画像分離部12、乗車人数決定部13とを備える。本実施形態の乗車人数計測システムは、第1の実施形態における乗車人数計測システムに第3撮影部14を加えた構成となっている。
本実施形態の乗車人数計測システムを、図面を参照して説明する。本実施形態では、乗車人数決定部13の機能のみ第1の実施形態と異なり、他の構成は同じであるため、構成の説明を省略する。特に説明しない構成および機能は、第1の実施形態と同様であるとする。
11 第2撮影部
12 画像分離部
13 乗車人数決定部
14 第3撮影部
30 第1撮影手段
31 第2撮影手段
42 画像分離手段
43 乗車人数決定手段
100、200 乗車人数計測装置
Claims (25)
- 車両が撮影されて取得された第1画像と、第1特定波長帯の光のみを受光した状態で前記車両が撮影されて取得された第2画像とにもとづいて、複数の分離画像を取得する画像分離手段と、
前記複数の分離画像にもとづいて、前記車両の乗車人数を決定する乗車人数決定手段とを備えた
ことを特徴とする乗車人数計測装置。 - 乗車人数決定手段は、複数の分離画像のそれぞれに対して、乗車人数を取得し、取得した前記乗車人数の最大値を車両の乗車人数として決定する
請求項1記載の乗車人数計測装置。 - 画像分離手段は、独立成分分析を用いて画像分離を行う
請求項1または請求項2記載の乗車人数計測装置。 - 画像分離手段は、第1画像と第2画像とにもとづいて、撮影手段からの距離が異なる2つの画像に分離する
請求項1から請求項3のうちのいずれか1項に記載の乗車人数計測装置。 - 車両が撮影されて取得された第1画像と、第1特定波長帯の光のみを受光した状態で前記車両が撮影されて取得された第2画像と、前記第1特定波長帯と異なる第2特定波長帯の光のみを受光した状態で前記車両が撮影されて取得された第3画像とにもとづいて、複数の分離画像を取得する画像分離手段と、
前記複数の分離画像にもとづいて、前記車両の乗車人数を決定する乗車人数決定手段とを備えた
ことを特徴とする乗車人数計測装置。 - 車両を撮影して第1画像を取得する第1撮影手段と、
第1特定波長帯の光のみを受光した状態で前記車両を撮影して第2画像を取得する第2撮影手段と、
前記第1画像と前記第2画像とにもとづいて、複数の分離画像を取得する画像分離手段と、
前記複数の分離画像にもとづいて、前記車両の乗車人数を決定する乗車人数決定手段とを備えた
ことを特徴とする乗車人数計測システム。 - 乗車人数決定手段は、複数の分離画像のそれぞれに対して、乗車人数を取得し、取得した前記乗車人数の最大値を車両の乗車人数として決定する
請求項6記載の乗車人数計測システム。 - 画像分離手段は、独立成分分析を用いて画像分離を行う
請求項6または請求項7記載の乗車人数計測システム。 - 画像分離手段は、第1画像と第2画像とにもとづいて、第1撮影手段および第2撮影手段からの距離が異なる2つの画像に分離する
請求項6から請求項8のうちのいずれか1項に記載の乗車人数計測システム。 - 第1特定波長帯の光を車両に照射する照射手段を備えた
請求項6から請求項9のうちのいずれか1項に記載の乗車人数計測システム。 - 第1撮影手段から車両までの光路長と、第2撮影手段から前記車両までの光路長とが同一である
請求項6から請求項10のうちのいずれか1項に記載の乗車人数計測システム。 - 第1撮影手段の撮影範囲と第2撮影手段の撮影範囲とが同一である
請求項6から請求項11のうちのいずれか1項に記載の乗車人数計測システム。 - 車両を撮影して第1画像を取得する第1撮影手段と、
第1特定波長帯の光のみを受光した状態で前記車両を撮影して第2画像を取得する第2撮影手段と、
前記第1特定波長帯と異なる第2特定波長帯の光のみを受光した状態で前記車両を撮影して第3画像を取得する第3撮影手段と、
第1画像、第2画像および前記第3画像とにもとづいて、複数の分離画像を取得する画像分離手段と、
前記複数の分離画像にもとづいて、前記車両の乗車人数を決定する乗車人数決定手段とを備えた
ことを特徴とする乗車人数計測システム。 - 車両が撮影されて取得された第1画像と、第1特定波長帯の光のみを受光した状態で前記車両が撮影されて取得された第2画像とにもとづいて、複数の分離画像を取得し、
前記複数の分離画像にもとづいて、前記車両の乗車人数を決定する
ことを特徴とする乗車人数計測方法。 - 複数の分離画像のそれぞれに対して、乗車人数を取得し、取得した前記乗車人数の最大値を車両の乗車人数として決定する
請求項14記載の乗車人数計測方法。 - 独立成分分析を用いて画像分離を行う
請求項14または請求項15記載の乗車人数計測方法。 - 第1画像と第2画像とにもとづいて、撮影手段からの距離が異なる2つの画像に分離する
請求項14から請求項16のうちのいずれか1項に記載の乗車人数計測方法。 - 車両が撮影されて取得された第1画像と、第1特定波長帯の光のみを受光した状態で前記車両が撮影されて取得された第2画像と、前記第1特定波長帯と異なる第2特定波長帯の光のみを受光した状態で前記車両が撮影されて取得された第3画像とにもとづいて、複数の分離画像を取得し、
前記複数の分離画像にもとづいて、前記車両の乗車人数を決定する
ことを特徴とする乗車人数計測方法。 - コンピュータに、
車両が撮影されて取得された第1画像と、第1特定波長帯の光のみを受光した状態で前記車両が撮影されて取得された第2画像とにもとづいて、複数の分離画像を取得する画像分離処理と、
前記複数の分離画像にもとづいて、前記車両の乗車人数を決定する乗車人数決定処理とを
実行させるための乗車人数計測プログラム。 - コンピュータに、
乗車人数決定処理で、複数の分離画像のそれぞれに対して、乗車人数を取得し、取得した前記乗車人数の最大値を車両の乗車人数として決定する処理を実行させる
請求項19記載の乗車人数計測プログラム。 - コンピュータに、
画像分離処理で、独立成分分析を用いて画像分離を行わせる
請求項19または請求項20記載の乗車人数計測プログラム。 - コンピュータに、
画像分離処理で、第1画像と第2画像とにもとづいて、撮影手段からの距離が異なる2つの画像に分離させる
請求項19から請求項21のうちのいずれか1項に記載の乗車人数計測プログラム。 - コンピュータに、
車両が撮影されて取得された第1画像と、第1特定波長帯の光のみを受光した状態で前記車両が撮影されて取得された第2画像と、前記第1特定波長帯と異なる第2特定波長帯の光のみを受光した状態で前記車両が撮影されて取得された第3画像とにもとづいて、複数の分離画像を取得する画像分離処理と、
前記複数の分離画像にもとづいて、前記車両の乗車人数を決定する乗車人数決定処理とを
実行させるための乗車人数計測プログラム。 - 車両が撮影されて取得された第1画像と、第1特定波長帯の光のみを受光した状態で前記車両が撮影されて取得された第2画像とにもとづいて、複数の分離画像を取得する画像分離手段と、
前記複数の分離画像の中から、映り込みが低減された画像を選択する選択手段と、
選択された映り込みが低減された画像にもとづいて、前記車両の乗車人数を決定する乗車人数決定手段とを備えた
ことを特徴とする乗車人数計測装置。 - 前記複数の分離画像に対して、人物の特定部位の数を取得する取得手段を備え、
前記選択手段は、前記人物の特定部位の数にもとづいて、前記複数の分離画像の中から、映り込みが低減された画像を選択する
請求項24記載の乗車人数計測装置。
Priority Applications (9)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CA3010922A CA3010922C (en) | 2016-03-17 | 2016-03-17 | Passenger counting device, system, method and program |
PCT/JP2016/001557 WO2017158648A1 (ja) | 2016-03-17 | 2016-03-17 | 乗車人数計測装置、システム、方法およびプログラム |
JP2018505559A JP6607308B2 (ja) | 2016-03-17 | 2016-03-17 | 乗車人数計測装置、システム、方法およびプログラム |
AU2016397318A AU2016397318B2 (en) | 2016-03-17 | 2016-03-17 | Passenger counting device, system, method and program |
EP16894272.0A EP3285231A4 (en) | 2016-03-17 | 2016-03-17 | DEVICE, SYSTEM, METHOD AND PROGRAM FOR COUNTING PASSENGERS |
US15/572,995 US10318830B2 (en) | 2016-03-17 | 2016-03-17 | Passenger counting device, system, method and program |
US16/296,638 US10789494B2 (en) | 2016-03-17 | 2019-03-08 | Passenger counting device, system, method and program |
US16/296,514 US10824887B2 (en) | 2016-03-17 | 2019-03-08 | Passenger counting device, system, method and program |
US16/296,774 US10922565B2 (en) | 2016-03-17 | 2019-03-08 | Passenger counting device, system, method and program |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2016/001557 WO2017158648A1 (ja) | 2016-03-17 | 2016-03-17 | 乗車人数計測装置、システム、方法およびプログラム |
Related Child Applications (4)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US15/572,995 A-371-Of-International US10318830B2 (en) | 2016-03-17 | 2016-03-17 | Passenger counting device, system, method and program |
US16/296,514 Continuation US10824887B2 (en) | 2016-03-17 | 2019-03-08 | Passenger counting device, system, method and program |
US16/296,638 Continuation US10789494B2 (en) | 2016-03-17 | 2019-03-08 | Passenger counting device, system, method and program |
US16/296,774 Continuation US10922565B2 (en) | 2016-03-17 | 2019-03-08 | Passenger counting device, system, method and program |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017158648A1 true WO2017158648A1 (ja) | 2017-09-21 |
Family
ID=59851545
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2016/001557 WO2017158648A1 (ja) | 2016-03-17 | 2016-03-17 | 乗車人数計測装置、システム、方法およびプログラム |
Country Status (6)
Country | Link |
---|---|
US (4) | US10318830B2 (ja) |
EP (1) | EP3285231A4 (ja) |
JP (1) | JP6607308B2 (ja) |
AU (1) | AU2016397318B2 (ja) |
CA (1) | CA3010922C (ja) |
WO (1) | WO2017158648A1 (ja) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6607308B2 (ja) | 2016-03-17 | 2019-11-27 | 日本電気株式会社 | 乗車人数計測装置、システム、方法およびプログラム |
CN112995616A (zh) * | 2016-06-03 | 2021-06-18 | 麦克赛尔株式会社 | 摄像装置和摄像系统 |
US11403865B2 (en) * | 2017-07-25 | 2022-08-02 | Nec Corporation | Number-of-occupants detection system, number-of-occupants detection method, and program |
US11538257B2 (en) * | 2017-12-08 | 2022-12-27 | Gatekeeper Inc. | Detection, counting and identification of occupants in vehicles |
US10699572B2 (en) | 2018-04-20 | 2020-06-30 | Carrier Corporation | Passenger counting for a transportation system |
KR102570058B1 (ko) * | 2018-12-17 | 2023-08-23 | 현대자동차주식회사 | 차량 및 그 제어방법 |
US10867193B1 (en) | 2019-07-10 | 2020-12-15 | Gatekeeper Security, Inc. | Imaging systems for facial detection, license plate reading, vehicle overview and vehicle make, model, and color detection |
US11196965B2 (en) | 2019-10-25 | 2021-12-07 | Gatekeeper Security, Inc. | Image artifact mitigation in scanners for entry control systems |
CN111274973B (zh) * | 2020-01-21 | 2022-02-18 | 同济大学 | 基于自动划分域的人群计数模型训练方法及应用 |
US11308316B1 (en) | 2021-09-02 | 2022-04-19 | Invision Ai, Inc. | Road side vehicle occupancy detection system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003016425A (ja) * | 2001-06-28 | 2003-01-17 | Victor Co Of Japan Ltd | オブジェクト信号作成装置 |
WO2008099146A1 (en) * | 2007-02-15 | 2008-08-21 | Vehicle Occupancy Ltd | Method and apparatus for counting vehicle occupants |
JP2013236962A (ja) * | 2007-08-15 | 2013-11-28 | Fujifilm Corp | 画像成分分離装置、方法、およびプログラム |
WO2014061195A1 (ja) | 2012-10-19 | 2014-04-24 | 日本電気株式会社 | 乗車人数計数システム、乗車人数計数方法および乗車人数計数プログラム |
WO2014064898A1 (ja) | 2012-10-26 | 2014-05-01 | 日本電気株式会社 | 乗車人数計測装置、方法およびプログラム |
WO2015052896A1 (ja) | 2013-10-09 | 2015-04-16 | 日本電気株式会社 | 乗車人数計測装置、乗車人数計測方法およびプログラム記録媒体 |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7602942B2 (en) | 2004-11-12 | 2009-10-13 | Honeywell International Inc. | Infrared and visible fusion face recognition system |
US20150054639A1 (en) | 2006-08-11 | 2015-02-26 | Michael Rosen | Method and apparatus for detecting mobile phone usage |
WO2008127685A1 (en) * | 2007-04-13 | 2008-10-23 | John Kesterson | Filter assembly and image enhancement system for a surveillance camera and method of using the same |
JP5100457B2 (ja) * | 2008-03-10 | 2012-12-19 | オリンパスメディカルシステムズ株式会社 | 内視鏡観察システム |
WO2010044250A1 (ja) | 2008-10-15 | 2010-04-22 | 日本電気株式会社 | パターン照合装置及びパターン照合方法 |
JP2011002718A (ja) | 2009-06-19 | 2011-01-06 | Toshiba Corp | 画像撮像装置 |
US8811664B2 (en) * | 2011-12-06 | 2014-08-19 | Xerox Corporation | Vehicle occupancy detection via single band infrared imaging |
US9202118B2 (en) * | 2011-12-13 | 2015-12-01 | Xerox Corporation | Determining a pixel classification threshold for vehicle occupancy detection |
US8824742B2 (en) * | 2012-06-19 | 2014-09-02 | Xerox Corporation | Occupancy detection for managed lane enforcement based on localization and classification of windshield images |
EP3295298A4 (en) * | 2015-05-14 | 2018-11-21 | Gatekeeper Inc. | Apparatus, systems and methods for enhanced visual inspection of vehicle interiors |
JP6607308B2 (ja) | 2016-03-17 | 2019-11-27 | 日本電気株式会社 | 乗車人数計測装置、システム、方法およびプログラム |
-
2016
- 2016-03-17 JP JP2018505559A patent/JP6607308B2/ja active Active
- 2016-03-17 AU AU2016397318A patent/AU2016397318B2/en active Active
- 2016-03-17 US US15/572,995 patent/US10318830B2/en active Active
- 2016-03-17 CA CA3010922A patent/CA3010922C/en active Active
- 2016-03-17 WO PCT/JP2016/001557 patent/WO2017158648A1/ja active Application Filing
- 2016-03-17 EP EP16894272.0A patent/EP3285231A4/en not_active Withdrawn
-
2019
- 2019-03-08 US US16/296,638 patent/US10789494B2/en active Active
- 2019-03-08 US US16/296,514 patent/US10824887B2/en active Active
- 2019-03-08 US US16/296,774 patent/US10922565B2/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003016425A (ja) * | 2001-06-28 | 2003-01-17 | Victor Co Of Japan Ltd | オブジェクト信号作成装置 |
WO2008099146A1 (en) * | 2007-02-15 | 2008-08-21 | Vehicle Occupancy Ltd | Method and apparatus for counting vehicle occupants |
JP2013236962A (ja) * | 2007-08-15 | 2013-11-28 | Fujifilm Corp | 画像成分分離装置、方法、およびプログラム |
WO2014061195A1 (ja) | 2012-10-19 | 2014-04-24 | 日本電気株式会社 | 乗車人数計数システム、乗車人数計数方法および乗車人数計数プログラム |
WO2014064898A1 (ja) | 2012-10-26 | 2014-05-01 | 日本電気株式会社 | 乗車人数計測装置、方法およびプログラム |
WO2015052896A1 (ja) | 2013-10-09 | 2015-04-16 | 日本電気株式会社 | 乗車人数計測装置、乗車人数計測方法およびプログラム記録媒体 |
Non-Patent Citations (1)
Title |
---|
See also references of EP3285231A4 |
Also Published As
Publication number | Publication date |
---|---|
US10922565B2 (en) | 2021-02-16 |
AU2016397318B2 (en) | 2019-10-24 |
JP6607308B2 (ja) | 2019-11-27 |
US20190205677A1 (en) | 2019-07-04 |
AU2016397318A1 (en) | 2018-07-05 |
US20190205678A1 (en) | 2019-07-04 |
EP3285231A4 (en) | 2019-02-20 |
CA3010922C (en) | 2020-06-30 |
US10318830B2 (en) | 2019-06-11 |
US20180157922A1 (en) | 2018-06-07 |
JPWO2017158648A1 (ja) | 2018-11-15 |
EP3285231A1 (en) | 2018-02-21 |
US10789494B2 (en) | 2020-09-29 |
US20190205679A1 (en) | 2019-07-04 |
US10824887B2 (en) | 2020-11-03 |
CA3010922A1 (en) | 2017-09-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6607308B2 (ja) | 乗車人数計測装置、システム、方法およびプログラム | |
US9760784B2 (en) | Device, method and program for measuring number of passengers | |
JP6458734B2 (ja) | 乗車人数計測装置、乗車人数計測方法および乗車人数計測プログラム | |
JP6354585B2 (ja) | 乗車人数計数システム、乗車人数計数方法および乗車人数計数プログラム | |
US10290162B2 (en) | Information processing apparatus, information processing method, and storage medium | |
KR101411668B1 (ko) | 교정 장치, 거리 측정 시스템, 교정 방법, 및 교정 프로그램을 기록한 컴퓨터 판독 가능한 기록 매체 | |
CA3010997C (en) | Passenger counting device, system, method and program, and vehicle movement amount calculation device, method and program | |
JP2009143722A (ja) | 人物追跡装置、人物追跡方法及び人物追跡プログラム | |
KR20170088692A (ko) | 영상을 이용한 차량속도 산출장치 및 그 방법 | |
JP6089576B2 (ja) | 車両窓検出システム、車両窓検出方法及びプログラム | |
JP2010262527A (ja) | 通行者計数装置、通行者計数方法および通行者計数プログラム | |
KR102211903B1 (ko) | 컴퓨터비전 기술을 이용한 주행차량 내 승차인원을 검지하기 위한 촬영 방법 및 장치 | |
JP2008299787A (ja) | 車両検知装置 | |
US20240070876A1 (en) | Control apparatus, method, and non-transitory computer-readable storage medium | |
JP5279459B2 (ja) | 混雑検知装置 | |
CN113989894A (zh) | 防尾随方法、装置及计算机可读存储介质 | |
JP2010198572A (ja) | 車両判別装置及び車両判別方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 15572995 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 2018505559 Country of ref document: JP Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 2016397318 Country of ref document: AU Date of ref document: 20160317 Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 3010922 Country of ref document: CA |
|
NENP | Non-entry into the national phase |
Ref country code: DE |