JPH11296797A - Parking lot picture monitor device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To obtain a monitor device which is a picture processor to manage the parking space of a parking lot and automatically monitors the abnormality of a running path. SOLUTION: A picture obtained by photographing at a field angle including plural automobile cabin is inputted to a picture input means 8, and it is discriminated whether a vehicle exists on the running path or not based on this picture; and if any vehicle doesn't exist on the running path, an automobile cabin monitor means 12 is started to discriminate the existence of plural automobile cabin. Since the running path is also monitored by this constitution, monitor which has been manually executed is automated to considerably reduce the labor.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a technique for monitoring the vacancy of a parking space (vehicle compartment) in a parking lot, and more particularly to measuring the occupied state of the vehicle compartment and monitoring the abnormality of a traveling path using a television camera. The present invention relates to a parking lot image monitoring device.

[0002]

2. Description of the Related Art In the management of a parking lot, the presence of a vehicle in a vehicle compartment is managed, and if there is an empty space, guidance is given to a parking lot user (user). As described in Japanese Patent Application Laid-Open No. 4-363800, a sensor such as an ultrasonic sensor is installed in each vehicle compartment to determine whether a vehicle is present in each vehicle compartment. In addition, the parking lot manager monitors the image of the TV camera installed in the aisle to monitor the condition of the vehicles running on the road, and constantly monitors the monitor screen for abnormalities such as accidents on the road. Watching by watching. On the other hand, Japanese Patent Laid-Open No. 4-290199 discloses a parking lot management by image processing, in which the entire parking lot is photographed by a camera, and a vehicle is extracted by inter-frame difference processing of the camera image. There is one that calculates a moving locus of a car in association with data for which a map is created, and manages a parking position and an empty position in a parking lot. According to the invention described in Japanese Patent Application Laid-Open No. 9-16897, a parking lot is photographed from directly above with a camera, and a vehicle is extracted by a difference process between this image and a background image of the parking lot photographed in advance. The management of the vacant position is performed to manage the presence of the vehicle.

[0003]

While such sensors such as ultrasonic sensors are inexpensive, there is a problem that the installation cost is considerable when installing a large number of sensors, including the construction cost. When the vehicle stands above or below the sensor, there is a problem that the result of the vehicle presence determination is output even when the vehicle does not exist. In addition, since the parking lot manager needs to constantly monitor the monitor screen and check for the presence or absence of an abnormality, the operation becomes very difficult. On the other hand, the problem of the prior art by image processing is that the image processing according to Japanese Patent Laid-Open No. 4-290199 does not consider that the angle of view of the camera becomes invisible due to the overlapping of vehicles, so that accurate processing cannot be performed. In addition, there is a problem that all vehicles cannot be detected only by the inter-frame difference processing (a stopped vehicle cannot be detected). Japanese Patent Application Laid-Open No. Hei 9-16897 is an effective method in a place where a camera can photograph a parking space from directly above. However, in a case where the ceiling is low such as an underground parking lot, such an image is used. There is a problem that it cannot be set at the corner.

[0004]

According to the present invention, in order to solve the above-mentioned problems, a parking lot image monitoring apparatus according to the present invention comprises:
A parking lot image monitoring device comprising: a television camera that simultaneously captures a plurality of passenger compartments, which are parking spaces of a parking lot, and a traveling path; and an image processing device that inputs an image of the television camera and performs image processing. An image input unit for inputting an image, an image memory for storing an image input by the image input unit, and a processing area for a traveling road area and a processing room area for a camera image input from the image input means. An area setting means to be set and monitoring means for monitoring the running of the vehicle or the presence of the vehicle in each area set by the area setting means. In this way, a plurality of compartments of the parking lot are photographed from behind the front by one television camera, and the video is automatically determined by the image processing technology in each compartment. is there. As a camera installation condition at this time, of the plurality of cabin arranged in a line, one of the cabin sides is to be photographed from the front rear with a panoramic view across a passage. With such an angle of view, it is possible to determine whether or not the vehicle is concealed by the presence or absence of the vehicle on the traveling road, so that it is possible to accurately determine the presence of the vehicle in the vehicle. Also, since the road is also photographed at the same time,
Abnormality monitoring of the traveling path can also be executed. The monitoring of the abnormality of the traveling path is a function of outputting an alarm when the vehicle is stopped in the area of the traveling path for a long time. That is,
When processing a single image, by dividing the monitoring of the traveling path and the monitoring of the passenger compartment, it is possible to solve the point that accurate cabin Monitoring can be realized at the same time.

[0005]

DESCRIPTION OF THE PREFERRED EMBODIMENTS One embodiment of the present invention will be described below with reference to the drawings.

FIG. 1 shows a photographing state of the television camera of the present invention.

[0007] The television camera is one in which a plurality of passenger compartments lined up facing each other are installed behind the front across a passage, and images are taken from this location. Cabin 2 in video 1 of the TV camera
1 to 2-6 are shown, and the traveling path 3 is shown in front of it. A parked vehicle 4 enters the cabin, and a passing vehicle 5 is reflected in the traveling path. By setting such a field of view, management of the presence of vehicles in a plurality of vehicle compartments can be measured by one camera, and abnormality monitoring of a traveling path can be executed simultaneously.

FIG. 2 shows a system configuration of the present invention.

Image input means 8 for inputting a camera image
An image storage means 9 for storing the input image; an area setting means 10 for setting a processing area on the image memory; a traveling path monitoring means 11 for monitoring the traveling path; It comprises a cabin monitoring means 12 and a communication means 13 for transmitting a measurement result.

First, the cabin monitoring means 12 will be described. In the case of monitoring each vehicle compartment area, if a vehicle is present on the traveling path, the vehicle may be hidden by the vehicle, which may cause an error in the vehicle presence determination in the vehicle compartment. Therefore, a function of determining whether a vehicle is present on the traveling path is provided before the vehicle presence determination in the vehicle compartment, and the vehicle presence determination in the vehicle compartment is performed when the vehicle is not present on the traveling path. ing. That is, as shown in FIG. 1, a processing area 6 for monitoring the traveling road is determined in advance, and a measurement area 7 is determined in a predetermined area of each vehicle compartment. As shown in FIG. 3, the processing is performed by inputting an image 14, setting a processing area in a travel path area of the image 15, determining whether or not a vehicle exists on the travel path 16; The cabin monitoring unit 12 that measures the state of each cabin is executed. By separating the monitoring of the traveling path and the monitoring of the vehicle interior in this way, the vehicle in the traveling path does not make a mistake in determining the presence of the vehicle in the vehicle interior. The determination as to whether or not a vehicle exists on the traveling path will be described later. The vehicle interior monitoring means 12 of FIG. 3 has a flow as shown in FIG. First, the number of compartments loop processing 18 is performed, and a processing area is set in a predetermined area of each compartment.
Then, the area is differentiated 20. Since a vehicle has many horizontal stripes, the pattern appears when differentiation processing is performed. If there is no vehicle, almost nothing appears. FIG. 5 shows the concept of the differentiation process. The differential image is further binarized with a predetermined threshold value 21 and the binary area is calculated 22. If the binary area is larger than the set value, it is determined that the vehicle is in the occupied state 24, and if the binary area is smaller, it is determined that the vehicle is empty. 25. In such a process,
It is possible to determine the presence of a vehicle in each compartment. Here, the presence / absence determination is made using the differential processing, but in addition to this, there is also a light and shade pattern matching method.

FIGS. 6 and 7 show the principle.

As shown in FIG. 6, an area for pattern matching with a predetermined area of the vehicle cabin 2 is set as 26-1, 26-2, and an image when no car exists is stored in advance for that area. This is called a template image.
When pattern matching is performed at the same place between the template image and the input image, the similarity is high because the image is almost the same as the stored image in the case of an empty vehicle, and the similarity decreases significantly when a vehicle enters as shown in FIG. Due to such a difference, it is possible to determine the presence of a vehicle in a vehicle. In the present embodiment, two pattern matching areas are set. However, the same effect can be obtained by setting one large area and performing pattern matching processing on that area. In the two-place method, when the similarity is different between the two regions, it is possible to grasp that the car is moving, so that the similarity is reduced at both places. Thus, the pattern matching method is 2
Since the binarization process is not used, there is an advantage that the accuracy of the determination is high. However, since it is necessary to store the state of the empty vehicle in advance, there is a drawback that when the system is started, if a vehicle is present, an erroneous determination is made. Therefore, a process combining two methods, a differential method and a pattern matching method, as shown in FIG. 8, is conceivable. The cabin monitoring means 17 judges whether or not there is an empty state in each vehicle in the past 28, and if there is no empty state in the state of the relevant vehicle in the past, no background image (template image) has been created.
If the vehicle is determined to be empty, the empty state flag is turned on 41 and a background image (template image) for pattern matching is created 42. Also, if there was an empty state in the past,
Since a background image (template image) has already been created, pattern matching 29 is performed between the background image (template image) and the input image to determine whether or not the similarity is low 30. If the similarity is low, a vehicle exists. It is determined 31 and
If it is high, it is determined that the vehicle is empty 32. If it is determined that the vehicle is empty, the stored background image is updated 33. This updating process is performed in such a way that the brightness of the image in the empty state changes due to the influence of illumination, dirt on the camera lens, and the like. The averaging with the input image is executed to update the stored background image. Here, it is optimal to use a normalized correlation process or the like which is a basic function of the image processing for the pattern matching process. By the way, although the vehicle presence can be determined by the pattern matching processing and the differentiation processing, there is also a method in which both functions are executed simultaneously to make the determination. FIG. 9 shows the flow. The difference from FIG. 8 is that
The point is that pattern matching is executed when there is an empty state in the past, and differentiation processing is always executed regardless of whether there is an empty state. As a result, two judgment results are obtained. If both judgment results are the same, they are output as they are, and if they are different, the pattern matching processing is prioritized (when the pattern matching processing is executed) and output. It was done. With such processing, the accuracy of the determination can be improved. FIG. 10 shows a hardware configuration of the present invention. In the image monitoring device 47, the video signal of the television camera 48 is taken into the image memory 50 via the A / D converter 49. An image processor 51 for reading the contents of the image memory 50 and executing various image processing, a D / A converter 52 for displaying the contents of the image memory 50 on a monitor or the like, and a CPU 53 for executing various controls
And a program storage memory RAM / ROM 54 and an image processing parameter file 55 for storing various processing areas and the like
And a communication unit 56 of the recognition result. Such a configuration is not particularly different from general image processing hardware. Next, the traveling path monitoring means will be described. The traveling path monitoring means 11 has two functions. That is, the function of determining whether or not the vehicle is present on the traveling path for determining whether to operate the vehicle interior monitoring means 12 and the function of monitoring the abnormality of the traveling path. First, the traveling road vehicle presence determination function will be described. In order to determine whether or not a vehicle is present on the traveling road, the processing area 6 in FIG. 1 is differentiated in the same manner as in FIG. 5, and the differentiated image is binarized with a predetermined threshold value to determine the area of the binary image. Is larger than a predetermined value, it can be determined that the vehicle exists on the traveling road. In addition, if the inter-frame difference processing (images are taken at predetermined time intervals and the difference processing is performed between the images) is performed, a moving object can be detected. However, since it cannot be detected when the vehicle is stopped, the cabin monitoring means may be activated by mistake. Further, there is a method in which an image in which no vehicle exists on the traveling path is input in advance, and the vehicle is extracted by a difference process between the background image and the input image. Normally, at the start of business, there is no vehicle running in the aisle (in the case of a passenger compartment, there is a possibility that there is a vehicle that has been up at night). Therefore, the background image can be stored before the business operation of the parking lot starts. As described above, when the background image can be stored, the pattern matching process is performed between the input image and the background image as in the case of the cabin monitoring unit. When the similarity is low, it is determined that the vehicle exists. You can also. By such processing,
It is possible to execute vehicle presence confirmation on the traveling path. On the other hand, the abnormality monitoring function of the traveling path monitoring means monitors a state where the vehicle is stopped for a long time on the traveling path, and is realized by the processing shown in FIG. Since it is a determination as to whether or not the vehicle is stopped, two images are input at a predetermined time interval, and the difference processing of the images is executed. Since the portion where the difference in brightness is small is a non-moving region, this image is created, and a vehicle is extracted by a difference process between this image, a background image stored in advance, and the input image. By executing an AND process with an area having a small difference between the frames, it is possible to obtain an image of a stopped vehicle. The coordinates (xc, yc) of the center position of this image are calculated, the time is measured when the coordinates do not move from within a predetermined range, and an alarm signal is notified when the predetermined time has elapsed. it can. Alternatively, a similar output can be obtained by using only the background difference image and simply managing the center coordinates of the extracted image. By such processing, the abnormality monitoring function of the traveling path can be realized. Further, by extracting vehicles on the traveling road by the background subtraction processing and sending the center coordinates to the host computer, it is possible to grasp the state of the traveling road in the entire parking lot.
FIG. 12 shows a conceptual diagram thereof. The host computer 57 receives the coordinates of the vehicle on the travel path from a plurality of image processing devices (parking lot image monitoring devices) 47, converts this data into a map of the entire parking lot in advance, and associates this data with the received data. By plotting the data on a map 58 of the entire parking lot, it is possible to grasp the state of the vehicle on the entire traveling road. The image monitoring apparatus and the host computer are connected by a network 59. Also, as shown in FIG. 13, each image processing apparatus is provided with an image compression transmission function, and in response to a request from a host computer, compresses and transmits a video of a TV camera that is shooting, and the host computer decompresses the received data. This can be displayed as a designated image on the map 58 of the entire parking lot. The compression method is selected according to the transmission time and the required image quality. Accordingly, when an abnormality such as a traveling path occurs, the image can be instantly viewed by the administrator, and the management operation becomes very smooth. As described above, the traveling path monitoring means and the vehicle interior monitoring means have been mainly described. However, by performing image processing separately for the traveling path monitoring means and the vehicle interior monitoring means, it is possible to accurately determine the presence of the vehicle in the vehicle interior.

[0013]

According to the present invention, a plurality of passenger compartments and traveling paths are photographed by one television camera, and the traveling path monitoring means and the passenger compartment monitoring means are provided, thereby realizing the low cost management of the parking lot. The traveling path monitoring means can detect an abnormality in the traveling path. In addition, by sending these data to the host computer, it is possible to collectively grasp the on-board management and the vehicle status on the traveling road. Furthermore, by providing an image compression and transmission function in the image processing device and an image decompression function and a display function in the host computer, if an abnormality occurs on the road, the administrator can immediately check the video in the vicinity and manage There is an effect that operation can be performed smoothly.

[Brief description of the drawings]

FIG. 1 is a diagram illustrating an example of a shooting angle of view according to the present invention and names of respective units.

FIG. 2 is a diagram showing a system configuration of the image monitoring apparatus of the present invention.

FIG. 3 is a diagram showing a vehicle presence determination flow of the present invention.

FIG. 4 is a diagram showing a flow of one embodiment of a vehicle interior monitoring means.

FIG. 5 is a diagram showing a concept of a differentiation process for detecting a vehicle.

FIG. 6 is a diagram showing an example of area setting when a vehicle is detected by a pattern matching method.

FIG. 7 is a diagram illustrating an example of a case where a vehicle exists in a pattern matching area.

FIG. 8 is a diagram showing a flow of an embodiment of a vehicle cabin monitoring unit when a differential system and a pattern matching system are used together.

FIG. 9 is a diagram showing a flow of an embodiment of a vehicle cabin monitoring unit when a differential system and a pattern matching system are simultaneously executed.

FIG. 10 is a diagram showing a hardware configuration of the image monitoring apparatus of the present invention.

FIG. 11 is a processing conceptual diagram of an abnormality monitoring function of a traveling path monitoring unit.

FIG. 12 shows a connection between the host computer and the image monitoring device,
It is an example of a system configuration diagram in a case of grasping the situation of the entire parking lot.

FIG. 13 shows a connection between the host computer and the image monitoring device,
FIG. 2 is an example of a system configuration diagram in a case of grasping the situation of the entire parking lot to which an image transmission function is added.

[Explanation of symbols]

8 image input means, 11 running path monitoring means, 12 vehicle interior monitoring means, 13 communication means, 47 image monitoring device.

Continued on the front page (72) Inventor Toru Nagai 7-1-1, Omika-cho, Hitachi City, Ibaraki Prefecture Inside Hitachi Research Laboratory, Hitachi, Ltd. (72) Inventor Noboru Ebiko 5-2-1 Omika-cho, Hitachi City, Ibaraki Prefecture Hitachi Computer Engineering Co., Ltd. (72) Inventor Kentaro Onose 5-2-1 Omika-cho, Hitachi City, Ibaraki Prefecture Inside Hitachi, Ltd.

Claims (8)

[Claims] 1. A parking lot image monitoring apparatus comprising: a television camera for simultaneously photographing a plurality of passenger compartments, which are parking spaces of a parking lot, and a traveling path; and an image processing device for inputting an image of the television camera and performing image processing. Image input means for inputting an image of a camera; an image memory for storing an image input by the image input means; a camera road input from the image input means; A parking lot image monitoring apparatus comprising: an area setting unit that sets a processing area of each of the areas; and a monitoring unit that monitors the traveling of the vehicle or the presence of the vehicle in each area set by the area setting unit. 2. The parking lot image monitoring device according to claim 1, wherein the television camera is installed in a rear side of the vehicle compartment across a traveling path, and at least a plurality of vehicle compartments in front of the vehicle have a view range. Parking image monitoring device that shoots overhead. 3. The parking lot image monitoring apparatus according to claim 1, wherein the monitoring means performs a differentiation process on the set travel path area to determine whether the vehicle is present on the travel path. A parking lot image monitoring device having a function of determining running or presence of a vehicle. 4. A parking lot image monitoring apparatus according to claim 1, wherein said monitoring means determines whether or not a vehicle is present on the travel path, and when it is determined that no vehicle is present on the travel path, a vehicle compartment is provided. Parking image monitoring device that determines whether or not a vehicle is present in the parking lot. 5. The parking lot monitoring device according to claim 1, wherein the monitoring means performs a differentiation process on the set vehicle compartment region to determine whether the vehicle is present, and stores the preset vehicle compartment region in advance. 2. Performing a pattern matching process between the vacant cabin image and the input image to determine whether the vehicle is present 2
A parking lot image monitoring device that determines based on street functions. 6. A parking lot image monitoring apparatus according to claim 3, wherein said monitoring means extracts a vehicle in a set traveling road area and outputs coordinates of the object. 7. A plurality of television cameras for photographing a plurality of compartments, which are parking spaces of a parking lot, a plurality of image processing devices for inputting images of the television cameras and performing image processing, and counting recognition results of the image processing devices. The image processing apparatus comprises: an image input means for inputting an image of a camera; an image memory for storing an image; and a traveling road area and a vehicle compartment with respect to a target image memory. Area setting means for setting the processing area of each area,
A travel path monitoring means for monitoring the travel path for the set travel path area, a cabin monitoring means for determining the presence of the vehicle in the set compartment area, and a communication means for transmitting the determination result; A parking state in which information on the presence of a vehicle compartment, vehicle trajectory data on a traveling path, and abnormal data on a traveling path are transmitted from each image processing device to a host computer, and the host computer collectively displays the received information on a parking lot map. A parking lot control device provided with a display means and a parking lot overall management means. 8. A parking lot image monitoring apparatus according to claim 7, wherein the parking state display means correlates data of the entire interior of the parking lot in advance with vehicle locus data sent from each image processing apparatus. This is a parking lot image monitoring device that uses one screen to grasp the usage status of vehicles in the entire parking lot.