WO2001067393A1 - Dispositif et procede de traitement d'images, et support d'enregistrement sur lequel le programme relatif a ce procede de traitement est enregistre - Google Patents

Dispositif et procede de traitement d'images, et support d'enregistrement sur lequel le programme relatif a ce procede de traitement est enregistre Download PDF

Info

Publication number
WO2001067393A1
WO2001067393A1 PCT/JP2000/001486 JP0001486W WO0167393A1 WO 2001067393 A1 WO2001067393 A1 WO 2001067393A1 JP 0001486 W JP0001486 W JP 0001486W WO 0167393 A1 WO0167393 A1 WO 0167393A1
Authority
WO
WIPO (PCT)
Prior art keywords
image data
change
image
background image
predetermined
Prior art date
Application number
PCT/JP2000/001486
Other languages
English (en)
Japanese (ja)
Inventor
Hiromi Horiuchi
Original Assignee
Mkc Stat Corporation
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Mkc Stat Corporation filed Critical Mkc Stat Corporation
Priority to PCT/JP2000/001486 priority Critical patent/WO2001067393A1/fr
Publication of WO2001067393A1 publication Critical patent/WO2001067393A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/254—Analysis of motion involving subtraction of images

Definitions

  • the present invention relates to an image processing device, an image processing method, and a recording medium on which an image processing method program is recorded, and more particularly to an improvement for accurately detecting a change in an image suitable for remote monitoring or the like.
  • a certain location is imaged for remote monitoring of unmanned indoor areas, remote monitoring of traffic conditions at intersections, and automatic recognition of the arrival and departure of cars at unmanned parking lots, and some changes occur in the image data.
  • a system for transmitting the image data when the image data is transmitted is known.
  • an image pickup signal by a video camera is converted into a digital signal, and the converted digital signal is converted into a time signal.
  • the data is sequentially stored in a plurality of memories, and when a change that indicates a change in the image occurs, a digital line is controlled to automatically send a call to the sender and transmit image information. is there.
  • this method automatically transmits the image if any change occurs in the monitoring of the whole image, so it is necessary to ignore the slight change such as the invasion of small animals such as dogs and cats and the brightness of day and night. There is a high possibility of detecting slow changes such as changes in data, and erroneous detection and transmission were inevitable.
  • a “security prevention monitoring device” proposed in Japanese Patent Laid-Open Publication No.
  • the technology described in these publications accumulates images for a certain period of time in the past, creates a background image by weighted averaging, and determines how much the current image has changed with respect to this background image in pixel units. The difference is detected.
  • the conventional technology for creating the background image described above is more advanced than a method of simply detecting a change in the image over time in terms of creating a background image by absorbing changes in the past.
  • the present invention provides an image processing apparatus, an image processing method, and an image processing method that can prevent detection omission and detection delay when there is a considerable change, and can reliably ignore a slight change that should be ignored.
  • An object is to provide a recording medium on which a method program is recorded.
  • the present invention does not simply compare the background image with the current image, but also compares a slightly older image such as a transient image earlier than the current image. That is, a change of a certain degree or more compared with the background image occurs at time t1, and furthermore, at the subsequent time t2, that is, at least at this time, a certain amount of change compared with the background image is in the same place or When it is in the vicinity, the change continues for a predetermined period of time, so it cannot be said that it is a temporary change, and this is detected as a change. .
  • a slight change that can be ignored compared to the background image occurs at time t1, and further, at time t2, that is, a slight change that can be ignored even at the present time at the same time. If it exists at or near one location, the change is continuous for a predetermined period of time, so it is no longer negligible and it is detected as a change smaller than the above change. There is. In other words, the change is not a large change from the background image, but if such a change continuously exists at or near the same location for a predetermined time, the change is detected without ignoring it. . Further, according to the present invention, when a state that does not change continues for a predetermined time, this can be detected.
  • the screen is divided into a plurality of areas in response to an image pickup operation from an image pickup unit that picks up an image of a predetermined location and generates image pickup data, and the luminance and / or luminance of each divided area are divided.
  • a divided image detecting means for detecting a color, and a luminance and / or a color of each of the areas detected by the divided image detecting means absorbs a change with the passage of time due to a change in the background image.
  • First storage means for storing the background image
  • Second storage means for storing a current image data based on luminance and / or color for each of the areas detected by the divided image detection means
  • a third storage means for storing image data older than the present as transient image data
  • the background image data of the first storage means is compared with the current image data of the second storage means, and the background image data and the third image data are compared with each other. Comparing means for comparing the transient image data of the storage means,
  • Determining means for determining that a change has occurred when a difference between the background image data and the current image data is equal to or greater than a predetermined value, and a difference between the background image data and the transient image data is equal to or greater than a predetermined value.
  • An image processing apparatus having the same is provided.
  • the screen is divided into a plurality of areas in response to an image pickup operation from an image pickup means for picking up an image of a predetermined location and generating image pickup data, and the brightness and / or luminance of each divided area are divided.
  • a divided image detecting step of detecting a color, and a background image is generated by absorbing a change with the passage of time based on luminance and / or color data of each area detected by the divided image detecting means.
  • a second storage step for storing the current image data based on the luminance and / or color of each area detected by the divided image detection means, and image data older than the current as transient image data.
  • the background image data of the first storage unit is compared with the current image data of the second storage unit, and the background image data is compared with the transient image data of a third storage unit.
  • a comparison step when the difference between the background image data and the current image data is greater than or equal to a predetermined value, and the difference between the background image data and the transient image data is also greater than or equal to a predetermined value; And the judgment step to judge that
  • An image processing method is provided.
  • an image of a predetermined location is captured to generate imaging data
  • a background image is generated by absorbing a change in the image
  • a change of a predetermined size or more between the background image and the background image is generated. Not the same change in the image
  • an image processing method for detecting, without ignoring, a continuous presence at or near the ⁇ location for a predetermined time.
  • an image of a predetermined location is captured to generate imaging data
  • a background image is generated by absorbing a change in the image
  • a change of a predetermined size or more between the background image and the background image is generated.
  • a predetermined size between the background image and the background image is detected.
  • an image of a predetermined location is captured to generate imaging data
  • a background image is generated by absorbing a change in the image
  • a change of a predetermined size or more between the background image and the background image is generated.
  • a screen is divided into a plurality of regions in response to image data from an imaging unit that generates an image data by capturing an image of a predetermined location, and the brightness and / or luminance of each divided region is determined.
  • a divided image detection step of detecting a color, and a change in the luminance and / or color of each of the areas detected by the divided image detecting means is absorbed by a change over time to thereby extract a background image.
  • a first storage step of storing the background image A second storage step for storing current image data based on luminance and / or color for each of the areas detected by the divided image detecting means; and a third storage step for storing image data older than the present as transient image data.
  • the background image data of the first storage unit is compared with the current image data of the second storage unit, and the background image data is compared with the transient image data of a third storage unit.
  • the difference between the background image data and the current image data is greater than or equal to a predetermined value and the difference between the background image data and the transient image data is also greater than or equal to a predetermined value, it is determined that a change has occurred.
  • a first determining step of performing the processing wherein there is a difference between the background image data and the current image data, but the difference is less than a predetermined value, and the difference between the background image data and the transient image data is When there is a difference, but the difference is also less than a predetermined value, when the area having the difference is the same area or near the current image data and the transient image data, A second determination step of determining a smaller change has been made,
  • a recording medium having an image processing method program stored therein is provided.
  • FIG. 1 is a block diagram of a first embodiment of the image processing apparatus according to the present invention.
  • FIG. 2 is a diagram showing a section of a parking lot captured by the video camera in FIG.
  • FIG. 3 shows how the entire screen to be imaged is divided into multiple small areas (cells).
  • FIG. 4 is a flowchart showing an image processing program for a parking lot.
  • FIG. 5 is a schematic diagram showing an aspect of a change of an image with time in a parking lot used in the description of the first embodiment.
  • FIG. 6 is a schematic diagram illustrating a monitoring system at an intersection as an application example of the second embodiment of the image processing apparatus of the present invention.
  • FIG. 7 is a flowchart showing a process in the system of FIG. BEST MODE FOR CARRYING OUT THE INVENTION
  • FIG. 1 is a block diagram of a first embodiment of the image processing apparatus according to the present invention. It is assumed that four sections in an unmanned parking lot, that is, a parking space for four cars are imaged from above for monitoring. It should be noted that although the actual device can monitor the space of many vehicles at the same time, it is assumed here that the number is four in order to simplify the explanation.
  • the video camera 10 is arranged to capture images of the above four sections A, B, C, and D of the parking lot from above, and continuously or intermittently captures analog video signals. Generate This analog video signal is supplied to the A / D converter 12 and converted into a digital signal. The digital signal generated by the A / D converter 12 is supplied to the signal processing and control circuit 14.
  • imaging is performed once every 10 seconds, and the image data for each imaging is signal processed.
  • the signal processing / control circuit 14 compresses the captured image data for each small area (to be simply referred to as an area or a cell) to be described later.
  • the image data is stored in the image memory 16, and time-integrated processing such as a cumulative averaging operation is performed on the image data over time to absorb a change over time to generate a background image. Rewrite the stored data of 6.
  • the output data of the control circuit 14 is also supplied to the transient image memory 18 and the current image memory 20.
  • the current image memory 20 stores the latest image data
  • the transient image memory 18 Stores past data (transient image data) such as the previous data data, which is older than the latest image data.
  • the transient image data is not limited to the current image 10 seconds before, but may be 30 seconds or 1 minute before in the case of imaging at the above 10 second intervals. Further, as a transient image, data obtained by absorbing a relatively recent change over a predetermined time may be used.
  • the image data is stored in the background image memory 16, the transient image memory 18, and the current image memory 20, respectively, and they are read out and supplied to the comparison circuit 22 for mutual comparison.
  • the storage of the image data in the background image memory 16, the transient image memory 18, and the current image memory 20 does not simply store the entire image, but the 10 ⁇ 10 0
  • the state is divided into 100 cells by the above mesh, and stored for each cell. Therefore, the comparison in the comparison circuit 22 is not performed for the entire image but for each of the divided cells.
  • the transmission control circuit 24 and the transmission circuit 26 transmit the data to a predetermined destination via the digital line 27 or the public line via the Internet or the like. This transmission can be sent as an e-mail attachment to a personal computer.
  • the transmission destination indicated by the dotted line in FIG. 1 has a reception circuit 28 and a display 29.
  • the image data transmitted from the transmission circuit 26 is received and displayed on the display 29.
  • a personal convenience server is provided at the transmission destination, and a video camera can be used if a commercially available camera server that can be controlled based on instructions from the personal computer and can be connected to the network is used. 10 can be operated from a remote location.
  • Fig. 3 shows the above raster, that is, the area of the entire screen to be imaged, is a small area (cell) of 100 x 100, 1 x 1, 0, 1-2, 1-3,-10-8, 1
  • This 100 cells are divided into four sections A, B, C, and D in FIG. 2 and used. That is, the section A corresponds to the cells 11-1 to 11-5, 2-1 to 2-5 ... in FIG.
  • Each cell 1 _ 1 to 10-10 is divided into A 1 to A 25, B 1 to B 25, C 1 to C 25, D 1 to D 25.
  • the block diagram of Fig. 1 is a circuit configuration that includes the signal processing / control circuit 14, background image memory 16, transient image memory 18, current image memory 20, comparison circuit 22, and transmission control circuit 24.
  • These can be constituted by a CPU (Central Processing Unit) which operates according to a predetermined program, a memory device, and a predetermined interface. It can also be realized by installing this program on a normal personal computer.
  • CPU Central Processing Unit
  • FIG. 4 is a flowchart showing such a program.
  • a predetermined initialization operation (not shown) is performed, and the contents of the background image memory 16, the transient image memory 18, and the current image memory 20 are cleared.
  • the background image memory 16 the transient image memory 18, and the current image memory 20
  • a single RAM storage area can be divided and used, or another storage device such as a hard disk can be used.
  • Figure 1 In the following description, each memory is independent.
  • step S1 digital image data is acquired from the A / D converter 12.
  • step S2 the image data is divided into 100 cache cells as shown in FIG. 3, and data compression is performed. Here, it is assumed that JPEG format data is created for each 100 cells.
  • step S3 the current image is stored in the current image memory 20.
  • step S4 read out the data from the background image memory 16, the transient image memory 18, and the current image memory 20, and read the current image data at step S 5 (the current image memory 20 Evening) is the same as the background image data (data in background image memory 16).
  • step S6 determines whether one cell is different, they are not the same. If it is determined in step S5 that they are the same (YES), then in step S6, ⁇ is performed for 10 seconds, and then the image in the current image memory 20 is stored in the transient image memory 18. In step S8, time integration of the image is performed, and in step S9, the result is stored in the background image memory 16.
  • the time integration can be performed by, for example, performing a weighted average of the data stored in the background image memory 16 and the data stored in the transient image memory 18.
  • the difference in the image data means that a predetermined number or more of the pixels in each cell are changed. If there is at least one cell in which the number of pixels has changed by a predetermined number or more, count the number of such cells P in step 10B, and then check in step S11 whether the number of such cells P is a predetermined number m or more. Determine whether or not.
  • the cell in step S12 It is determined whether or not cells whose image data differs to some extent from the background image data are consecutive in position.
  • the predetermined number m is determined in consideration of the size and movement of the object to be determined as the cell size.
  • step S13A, step S13B, step S14, and step S15 are continuous examples. If it is determined that they are continuous, it is determined in step S13A, step S13B, step S14, and step S15 whether or not the transient image data greatly changes with respect to the background image. The determination is made in the same manner as 0 A to step S 1 2 If it is determined in step S15 that they are continuous, it is concluded that there is a large change in step S16.
  • step S12 the continuous state of the area (cell) is determined.
  • the continuous direction is determined in advance such as vertical, vertical, diagonal, etc., and the number of continuous in each direction is determined in advance. It is possible to estimate or judge the shape of the object.
  • steps S10A and S13A the difference between the background image data and the current image data or the transient image data is less than the predetermined threshold T, or in steps S11 and S14 a large change occurs. If the number P or Q of a certain cell is less than m, or if it is determined in steps S12 and S15 that the positions are not continuous, the transient image data (transient image memory 18 The background image data is compared with the background image data for each cell, and if they match, the determination result in step S5 is considered to be noise, and is ignored in step S21. On the other hand, if they do not match, It is determined whether the missing cell is the same cell in the transient image data and the background image data or a nearby cell.
  • step S5 and step S18 are ignored as noise in step S21.
  • the cells that do not match in step S19 are the same cell in the transient image data and the background image data or the neighboring cells, a small change that cannot be ignored in step S20 Conclude that there is. In this case, it is not determined that the car is parked, but it is possible to give a message by voice to illegal intruders and the like.
  • step S22 the current image data is transmitted as an attached file to a predetermined transmission destination by e-mail. For example, by viewing the current image at a remote manned monitoring center, it is possible to easily find out whether or not an abnormality such as illegal activity has occurred in the parking lot. Alternatively, when such a situation occurs, the situation can be recorded to help solve the problem.
  • step S22 or step S21 return and repeat the operation from step S1 again.
  • FIG. 5 schematically shows a mode of a change in an image with time in a parking lot used for the description in the first embodiment.
  • the first (a) is the state 6 minutes and 20 seconds ago, and the last (j) is the current state. Between (c) and (d), 5 minutes are not shown.
  • vehicle 30 is parked in section B.
  • a vehicle 32 for parking entered the section D, and a slight change was observed.
  • the parked vehicle 32 has completely entered the section D.
  • steps S10A, S11-S13A, S14, and S15 are YES, and the process of recognizing the partition and turning on the charging timer for that partition in step S17 is YES.
  • line Is When the time elapses, the vehicle 32 that entered the section D for a long time due to the integration in the step S8 in FIG. 4 described above differs from the initial state (a). The state in which it has been performed is used as the background image.
  • step S1 3 A, S14 and S15 become NO, and the timer does not turn on.
  • step S18 becomes N0, it is ignored in step S21. If you enter the parking lot but leave without parking, it is appropriate to perform the process in which the evening image is not turned on.
  • a small object 36 that moves from section A to section C from (f) to (h) is detected. This object has a small number of change cells, becomes N ⁇ in step S 11, and is ignored since step S 19 also becomes N 0 because it is moving. This is preferable as processing when a small animal such as a cat or a dog temporarily enters.
  • step S10A changes to YES
  • step S12 becomes N0
  • step S18 becomes N0
  • step S19 becomes YES
  • step S10A, S11 to S13A, S14, and SI5 become YS
  • the timer 1 is turned off in step SI7
  • a billing process is performed. That is, the parking time is calculated to calculate the billed amount, and when the billed amount is received, a receipt is issued as necessary and the gate is opened.
  • the threshold T used in steps S10A and S13A in FIG. 4 is common to all cells, but the threshold T depends on the position of the cell. May be changed. That is, the threshold T can be set low near the center of each of the sections A to D, such as a parking lot, and the threshold T can be set high near the section. With such a setting, it is possible to more reliably identify a parked vehicle that should be detected and an object that may enter from the surroundings.
  • the first embodiment has been described with reference to an example of application to a parking lot, the change of an image mainly uses luminance (brightness) data, but the color (chromaticity, saturation) in the image is changed. Or a response to both luminance and color.
  • a vehicle traveling without stopping can be automatically captured, ignoring pedestrians trying to cross with a yellow flag near the crosswalk at the intersection.
  • an object that travels without stopping on a pedestrian crossing within a predetermined time is detected after a predetermined size that turns yellow at a predetermined point at an intersection, the object will Assuming that you are ignoring the vehicle, immediately record the driving situation near the intersection with another video camera and use that data to control traffic. It can be sent by e-mail to institutions.
  • FIG. 6 is a schematic diagram illustrating a configuration of an intersection monitoring system as an application example of the second embodiment of the image processing device according to the present invention.
  • the video camera C1 is arranged to monitor the vicinity of a predetermined pedestrian crossing 44 at the intersection, and corresponds to the video camera 10 in FIG. Now, when the pedestrian 40 tries to cross the pedestrian crossing 44 with the yellow flag 42 for traversing, the state is detected by the processing of the flow chart of FIG.
  • step S31 of FIG. 7 the image data from the video camera C1 is A / D converted and taken in, and divided into a plurality of cells in step S32, and the cells turned yellow in step S33.
  • step S34 it is determined whether or not the size of the cell changed to yellow is within a predetermined size range. If YES, it is concluded in step S35 that there is a crosser.
  • step S36 the presence or absence of a moving object heading for pedestrian crossing 44 is detected. In order to detect a running vehicle, it is too late at an interval of 10 seconds as in the above-mentioned parking lot. If there is such a moving object, it is determined in step S37 whether or not the moving object has stopped.
  • step S38 another video camera C2 uses The object, that is, the passing vehicle 46 is imaged and transmitted to a predetermined traffic control agency in step S39.
  • the characters on the license plate can be automatically read and sent with the image.
  • step S33 The detection of the change to yellow in step S33 is performed by comparing the background image with the current image and comparing the background image with the transient image in the same manner as in the image processing program for the parking lot in FIG. 4 (step S3). 1 ⁇ A to S 15) are combined. Also, since the flag for crossing is several tens of cm square, we will detect those that are less than a certain size to avoid misidentification as yellow clothes or yellow cars. Steps S 1 1 and S 1 4 are changed to exclude extremely small ones. It is changed from the case of FIG. 4 to determine whether the number of cells is equal to or more than a predetermined number and equal to or less than another predetermined number larger than the predetermined number of parentheses.
  • a message in addition to the current image transmitted as an attached file, a message can be attached as the body of the e-mail or other attached files according to the situation of vehicles ignoring pedestrians, etc. it can . It is practical to include the date and time, the location, the direction of travel of the vehicle, and the color of the vehicle as the content of the message. In order to determine the traveling direction and the color of the vehicle, steps for determining these may be added to the flowchart of FIG.
  • a fire detection notification system that detects the occurrence of a fire and automatically notifies the user of the occurrence. Similar to the yellow flag above, using the background image, the transition image, and the current image to accurately detect the color of the flame, transmit the current image, or send an email only when a fire has occurred can do.
  • the change in the image can be detected using one of luminance (brightness), hue (chromaticity), and saturation, or a combination of two or more of them. You can set these parameters. That is, in the present invention, the luminance and / or color refers to any one of luminance (brightness), hue, and saturation, or a combination of two or more of these.
  • the present invention can be applied to crime prevention in vaults, precious metal stores, and the like, and can be applied to bathing monitoring of elderly and sick people.
  • bathing monitoring when the subject in the image does not move for a long period of time, it is determined that an abnormality has occurred and a notification is sent.
  • the flowchart of FIG. 4 can be changed and used to detect that a state where there is no change continues.
  • an image of a predetermined location is captured to generate image data, a change in the image is absorbed to generate a background image, and when there is a change of a predetermined size or more from the background image, If the change exists at or near the same location in the image for a predetermined period of time, it is determined that there is a large change.On the other hand, the change with the background image is not more than the predetermined size, If a change has been present at or near the same point in the image for a predetermined period of time, it is determined that there is a small change.If these large or small changes do not occur for a predetermined period of time, it is detected as an abnormal state. Is what you do. Industrial applicability
  • a slightly older image such as a transient image earlier than the current image
  • a slightly older image is to be compared. If a change more than a certain amount occurs at time tl as compared with the time t2, and furthermore, a change more than a certain amount compared to the background image exists at the same time or in the vicinity at the time t2, Since the change exists continuously for a predetermined period of time, it cannot be said that it is a temporary change, and this is detected as a change, so if there is a considerable change, detection failure In addition, the detection does not become slow, and the slight changes that one wants to ignore can be safely ignored.
  • the difference area is in the same area or near between the current image data and the transient image data, it is determined that a change smaller than the above-mentioned change has occurred. More detailed decisions can be made. In addition, by detecting that there is no change for more than a predetermined time, it is possible to ensure the safety of the elderly and the sick. can do.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Image Analysis (AREA)

Abstract

L'invention concerne un dispositif de traitement d'images pouvant détecter un changement très important sans défaillance ni retard de détection, et pouvant négliger de manière sûre un petit changement qui doit être négligé. Ce dispositif compare non seulement une image actuelle, mais également une image un peu plus ancienne, telle qu'une image éphémère précédant l'image actuelle, avec une image d'arrière-plan. Si un changement d'au moins une certaine importance, par rapport à l'image d'arrière-plan, se produit à un moment t1, et en outre si un changement d'au moins une certaine importance par rapport à l'image d'arrière-plan existe dans le même endroit ou à proximité de cet endroit, à un moment t2 après le moment t1, c'est-à-dire maintenant, il est estimé que le changement existe de manière continue pendant une durée déterminée et que par conséquent ce changement n'est pas un changement temporaire, et l'existence de ce changement est détectée.
PCT/JP2000/001486 2000-03-10 2000-03-10 Dispositif et procede de traitement d'images, et support d'enregistrement sur lequel le programme relatif a ce procede de traitement est enregistre WO2001067393A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2000/001486 WO2001067393A1 (fr) 2000-03-10 2000-03-10 Dispositif et procede de traitement d'images, et support d'enregistrement sur lequel le programme relatif a ce procede de traitement est enregistre

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2000/001486 WO2001067393A1 (fr) 2000-03-10 2000-03-10 Dispositif et procede de traitement d'images, et support d'enregistrement sur lequel le programme relatif a ce procede de traitement est enregistre

Publications (1)

Publication Number Publication Date
WO2001067393A1 true WO2001067393A1 (fr) 2001-09-13

Family

ID=11735784

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2000/001486 WO2001067393A1 (fr) 2000-03-10 2000-03-10 Dispositif et procede de traitement d'images, et support d'enregistrement sur lequel le programme relatif a ce procede de traitement est enregistre

Country Status (1)

Country Link
WO (1) WO2001067393A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002157598A (ja) * 2000-11-16 2002-05-31 Japan Radio Co Ltd 侵入者検知システム
WO2011043350A1 (fr) * 2009-10-06 2011-04-14 国立大学法人東京工業大学 Système de capture d'image

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6261178A (ja) * 1985-09-11 1987-03-17 Hitachi Ltd 移動物体の監視方法および装置
JPH03138595A (ja) * 1989-10-25 1991-06-12 Ikegami Tsushinki Co Ltd 監視システム
JPH04256079A (ja) * 1991-02-07 1992-09-10 Nec Corp 移動ベクトル検出方法及び装置
JPH0568245A (ja) * 1991-09-09 1993-03-19 Nippon Telegr & Teleph Corp <Ntt> 動物体検出および追跡処理方式
JP2000020862A (ja) * 1998-07-03 2000-01-21 Ntt Power & Building Facilities Inc ビル管理システム

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6261178A (ja) * 1985-09-11 1987-03-17 Hitachi Ltd 移動物体の監視方法および装置
JPH03138595A (ja) * 1989-10-25 1991-06-12 Ikegami Tsushinki Co Ltd 監視システム
JPH04256079A (ja) * 1991-02-07 1992-09-10 Nec Corp 移動ベクトル検出方法及び装置
JPH0568245A (ja) * 1991-09-09 1993-03-19 Nippon Telegr & Teleph Corp <Ntt> 動物体検出および追跡処理方式
JP2000020862A (ja) * 1998-07-03 2000-01-21 Ntt Power & Building Facilities Inc ビル管理システム

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002157598A (ja) * 2000-11-16 2002-05-31 Japan Radio Co Ltd 侵入者検知システム
WO2011043350A1 (fr) * 2009-10-06 2011-04-14 国立大学法人東京工業大学 Système de capture d'image

Similar Documents

Publication Publication Date Title
US20180218582A1 (en) Monitoring an Area using Multiple Networked Video Cameras
CN1249635C (zh) 停车场管理系统和停车场管理方法
KR102122859B1 (ko) 교통 영상감시시스템의 멀티 표적 추적 방법
CN106485927A (zh) 一种智能交通违章信息采集装置及采集方法
KR102122850B1 (ko) 딥 러닝 기반의 교통분석 및 차량번호 인식 솔루션
JP2009517740A (ja) ビデオにおけるオブジェクト密度推定
KR101626377B1 (ko) Cctv와 차량내 블랙박스를 활용한 빅데이터 기반의 불법 주정차 단속 시스템
WO2021223665A1 (fr) Procédé et dispositif de diminution d&#39;avertissements non valides
KR102162130B1 (ko) 단일카메라를 이용한 불법주정차 단속시스템
CN103914898A (zh) 车辆进出入管制系统及管制方法
CN105427618A (zh) 车辆占用紧急停车带的警示方法及系统
KR101432111B1 (ko) 불법 주정차 단속 장치 및 그 방법
WO2001067393A1 (fr) Dispositif et procede de traitement d&#39;images, et support d&#39;enregistrement sur lequel le programme relatif a ce procede de traitement est enregistre
US20220214036A1 (en) Synchronized beacon criminal activity deterrent
CN112419774A (zh) 便于急救车通行的道路监控方法、系统及存储介质
KR102533582B1 (ko) 인공지능기반 운행위반 이륜자동차 단속 시스템 및 방법
CN109671291B (zh) 一种基于智能传感器的全景监控方法
CN110070748A (zh) 应用于开放式停车位的停车管理系统
KR100817753B1 (ko) 불법 쓰레기 투기의 감시와 범인 감시 및 차량 감시를연동하는 방범 보안 시스템 및 방법
WO2021149274A1 (fr) Système, dispositif et procédé de surveillance, et programme
JPH09207783A (ja) 踏切道監視装置
KR102434154B1 (ko) 영상감시시스템에서의 고속 이동물체의 위치 및 모션 캡쳐 방법
KR20180024747A (ko) 객체, 영역 및 객체가 유발하는 이벤트의 유기적 관계를 기반으로 한 8가지 기본 행동 패턴 정의를 통한 복합 상황 설정 및 자동 상황 인지가 가능한 지능형 방범 ｃｃｔｖ 시스템 및 그 방법
CN104240506B (zh) 具有视频采集功能的交通事件检测器
JP3962592B2 (ja) 駐車車両特定システム

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref country code: JP

Ref document number: 2001 565134

Kind code of ref document: A

Format of ref document f/p: F

AK Designated states

Kind code of ref document: A1

Designated state(s): JP US

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE

121 Ep: the epo has been informed by wipo that ep was designated in this application
122 Ep: pct application non-entry in european phase