KR100696226B1 - Vehicle monitoring method, specific character pattern recognition devicem and vehicle monitoring system - Google Patents

Abstract

The present invention relates to a vehicle monitoring method using a specific character pattern recognition of a vehicle, a specific character pattern recognition device, and a vehicle monitoring system, and aims to control the amount of data to be transmitted according to a recognition result of a specific character pattern.

Recognizing apparatus 7 which processes the image | photographed image data by a photographing part, and recognizes the specific character pattern of a vehicle, and the center 1 connected with the some recognition apparatus and the line 6, The recognition apparatus 7 ) Performs recognition processing of the vehicle specific character pattern based on the captured image data, and when the character pattern cannot be recognized, the vehicle region is captured from the captured image data to be compressed at a low compression rate, and only a part of the character pattern is recognized. When it is possible to capture a specific character pattern area and compress it at a low compression rate, and when it is possible to recognize all the character patterns, it is possible to capture a specific character pattern area and compress it at a high compression rate to record or send it out, Has a management table 4 for receiving and storing compressed data from the recognition device via the line 6 and a display section 3 for displaying it.

Description

Vehicle monitoring method, specific character pattern recognition device and vehicle monitoring system {VEHICLE MONITORING METHOD, SPECIFIC CHARACTER PATTERN RECOGNITION DEVICEM AND VEHICLE MONITORING SYSTEM}

BRIEF DESCRIPTION OF THE DRAWINGS Explanatory drawing of Embodiment 1 of this invention.

2 is a system explanatory diagram of Embodiment 1 of the present invention;

3 is a flowchart of Embodiment 1 of the present invention;

4 is an explanatory diagram of a compression range.

5 is a system explanatory diagram of a second embodiment of the present invention;

6 is a system explanatory diagram of a third embodiment of the present invention;

7 is an explanatory diagram of a main part of a conventional example.

<Explanation of symbols for main parts of drawing>

1: Center

2: control processing unit

3: display unit

4: data management table

5: switching network

6: line

7: specific character pattern recognition device

8: camera

9: vehicle

The present invention relates to a vehicle monitoring method for recognizing and monitoring a specific character pattern of a vehicle, a specific character pattern recognition device, and a vehicle monitoring system.

Specific character patterns are given to various vehicles so as not to overlap each other. Therefore, by automatically reading a specific character pattern and recognizing the vehicle specific character pattern, it can be applied to automation of a toll payment station of a toll road, determination of whether a parking vehicle of a parking lot is a contractor, or detection of a stolen vehicle or escape vehicle. Various systems have already been proposed. In this case, it is to process the picked-up image signal of a specific character pattern, and therefore, it is desired to process this image signal efficiently.

7 is an explanatory diagram of a main part of the conventional example, and the vehicle detecting unit 70 detects that the passing vehicle has reached the shooting position, and inputs the detected signal to the recognition processing unit 72. The recognition processing unit 72 makes an image capturing instruction of the passing vehicle to the image capturing unit 71. The photographing unit 71 photographs the vehicle according to the photographing instruction, and transmits the image signal to the recognition processing unit 72 and the image transmitting unit 74. The recognition processing unit 72 extracts a specific character pattern region from the captured image of the vehicle, and recognizes a vehicle specific character pattern based on letters and numbers in the specific character pattern region. In the vehicle specific character pattern recognition processing, various means are known, such as capturing for one character, pattern matching for the captured character, and matching by feature extraction. In this conventional example, only when the vehicle passes the photographing position, the vehicle is photographed by the photographing unit 71.

In addition, the matching unit 73 registers the specific vehicle specific character pattern in advance, transmits the vehicle specific character pattern recognized by the recognition processing unit 72 to the matching unit 73, and compares it with the registered vehicle specific character pattern, The verification result is transmitted to the recognition processing unit 72. The recognition processing unit 72 transmits the matching and matching vehicle specific character pattern to the image transmitting unit 74 when receiving the matching and matching signal from the matching unit 73. The image transmission unit 74 transmits this vehicle specific character pattern and the captured image signal to the image recording / display unit 75. The image recording / display unit 75 adds and records the date and time information and the shooting point information. If necessary, the image recording / display unit 75 retrieves and reads the information based on information such as the vehicle specific character pattern, the date and time, the shooting point, and displays it on the monitor. It is possible to confirm (see Patent Document 1, for example).

The vehicle specific character pattern on the specific character pattern is recognized from the captured image signal, the captured image signal is compressed, and the recognized vehicle specific character pattern is added and recorded. Means for reading this recorded content based on the vehicle specific character pattern, decompressing the read compressed image signal, and displaying it on the monitor are also known (see Patent Document 2, for example).

In addition, a remote monitoring means for selecting one monitoring range from among a plurality of monitoring ranges and switching the compression rate and transmission time of an image signal in response to the monitoring range is known. For example, in the case of the selected monitoring range in which the monitored object moves at high speed, the compression rate is increased to make high speed transmission, and the monitor screen is changed according to the monitored object moving at high speed. In the case of the selected monitoring range in which the object to be monitored moves at a slow speed, the compression rate is lowered to transmit at a lower speed, and the monitor screen is displayed at a higher resolution (see Patent Document 3, for example).

[Patent Document 1] Japanese Patent Application Laid-Open No. 9-282590

[Patent Document 2] Japanese Unexamined Patent Application Publication No. 9-261620

[Patent Document 3] Japanese Patent Application Laid-Open No. 9-37232

As described above, it is possible to photograph the character pattern specifying the vehicle, extract the specific character pattern by image processing, perform character recognition processing, and perform vehicle monitoring based on the recognized character pattern. However, the shooting conditions vary greatly depending on the attachment angle of the specific character pattern, the soiled state and the weather. Therefore, in the case of a bad condition, recognition of the character pattern by image processing becomes difficult. If it is difficult to process automatic recognition of a specific character pattern of such a vehicle, means for inputting and displaying a captured image signal on a monitor, and visually identifying an area of the specific character pattern based on the display screen to recognize the vehicle specific character pattern Can be used.

However, in the case where the monitor installation place and the image transmission unit 74 shown in FIG. 7, for example, are provided at a position apart from each other, image data is transmitted via a line, even if the image data is compressed. Because of the large amount of data for the screen, a high-speed transmission path is required. Therefore, it is difficult to remotely monitor the vehicle by connecting the center and the distributed photographing processing unit via a low-rate network.

An object of the present invention is to reduce a transmission data by controlling a compression range and a compression ratio according to a recognition result of a specific character pattern of a vehicle.

The vehicle monitoring method of the present invention is a method of extracting a specific character pattern region of a vehicle based on photographed image data to perform character pattern recognition processing, and performing vehicle monitoring based on the recognized character pattern. When the recognition processing result indicates that the character pattern cannot be recognized, a vehicle area including almost the entire vehicle is captured from the captured image data, compressed at a low compression rate, and recorded or transmitted. When indicating that only a part of the vehicle specific character pattern can be recognized, the specific character pattern region is captured from the captured image data, compressed at a low compression rate, and recorded or transmitted. In addition, when indicating that all of the vehicle specific character patterns can be recognized, the method includes capturing a specific character pattern region from the captured image data, compressing it at a high compression rate, and recording or transmitting it. Therefore, when all the vehicle specific character patterns can be recognized, the specific character pattern area having a relatively small area is transmitted as image data compressed at a high compression ratio, so that even low-rate lines can be easily transmitted.

In addition, the specific character pattern recognition apparatus of the present invention captures a vehicle region including a vehicle from the frame memory temporarily storing the captured image data by the photographing unit and the captured image data, and captures the specific character pattern region from the vehicle region. A recognition processing unit including an image processing function for ringing, a character recognition processing function for recognizing a character pattern in a specific character pattern area, and a result of recognition processing of the character pattern by the recognition processing unit indicates that the character pattern cannot be recognized. When the compression range is a vehicle region, the compression ratio is a low compression rate, and only a part of the character pattern can be recognized, the compression range is a specific character pattern area, the compression rate is a low compression rate, and all the character patterns are recognized. When indicating that it is possible, determine the compression range as a specific character pattern area and the compression rate as a high compression rate. A compression range / compression rate judging section, an image compression section which captures an area of the compression range from the frame memory in accordance with the judgment result of the compression range / compression rate judging section, and compresses it according to the compression rate; And a transmission / reception section for transmitting the image data.

In addition, a data storage unit for storing the image data compressed by the image compression unit together with the recognition result of the vehicle specific character pattern may be provided.

A matching processing unit may be provided which compares the vehicle-specific character pattern instructed to be searched against the vehicle-specific character pattern of the recognition result stored in the data storage unit, and controls to read and send data stored in the data storage unit when matching is performed. have.

In addition, the vehicle monitoring system of the present invention processes the captured image data by the photographing unit to recognize a recognition device 7 that recognizes a vehicle specific character pattern, and a center 1 connected through a plurality of recognition devices and a line 6. As a vehicular monitoring system, the recognition device 7 performs a recognition process of a vehicle specific character pattern based on the captured image data, and when the character pattern cannot be recognized, it captures the vehicle area from the captured image data. When compressing at a compression rate and only a part of a character pattern could be recognized, a specific character pattern area was captured and compressed at a low compression rate. When all of the character patterns could be recognized, a specific character pattern area was captured to obtain a high compression rate. And a recording, transmitting, or transmitting structure, and the center 1 receives and stores compressed data from the recognition device through the line 6 and stores it. Block to have a 4 and the display unit 3 for displaying.

In the vehicle monitoring method of the present invention, when the recognition process result of the vehicle specific character pattern indicates that the character pattern cannot be recognized, the vehicle area including almost the entire vehicle is captured from the captured image data, compressed at a low compression rate, and recorded. Or transmit. When indicating that only a part of the vehicle specific character pattern can be recognized, the specific character pattern region is captured from the captured image data, compressed at a low compression rate, and recorded or transmitted. In addition, when indicating that all of the vehicle specific character patterns can be recognized, the method includes capturing a specific character pattern region from the captured image data, compressing it at a high compression ratio, and recording or transmitting the same.

The specific character pattern recognition apparatus of the present invention captures a vehicle region including a vehicle from a frame memory temporarily storing the captured image data by the photographing unit, and the captured image data, and captures the specific character pattern region from the vehicle region. A recognition processing unit including an image processing function to be performed, a character recognition processing function for recognizing a character pattern of a specific character pattern area, and a result of the recognition processing of the character pattern by the recognition processing unit indicates that the character pattern cannot be recognized. When the compression range is set to the vehicle area, the compression rate is set to a low compression rate, and when only a part of the character pattern can be recognized, the compression range is set to a specific character pattern area, and the compression rate is set to a low compression rate. Also, to indicate that all of the character patterns can be recognized, the compression range can be changed to a specific character pattern area. And a compression range / compression rate determining unit that sets the compression ratio as a high compression rate, and an image compression for compressing the compression range corresponding to the compression rate by capturing an area of the compression range from the frame memory according to the determination result of the compression range / compression rate determining unit. And a transmission / reception section for transmitting the image data compressed by the image compression section.

The vehicle monitoring system of the present invention includes a recognition device 7 for processing captured image data by the photographing unit to recognize a vehicle specific character pattern, and a center 1 connected through a plurality of recognition devices and lines 6. The recognition device 7 performs recognition processing of the vehicle specific character pattern based on the captured image data. When the character pattern cannot be recognized, the recognition device 7 captures the vehicle area from the captured image data and compresses it to a low compression rate. When only part of the pattern could be recognized, the specific character pattern area was captured and compressed at low compression rate. When all of the character patterns could be recognized, the specific character pattern area was captured and compressed at high compression rate, and recorded or transmitted. The center 1 comprises a management table 4 for receiving and storing compressed data from the recognition device via the line 6 and a display unit 3 for displaying it. It is raining.

Example 1

1 is a schematic diagram of a first embodiment of the present invention, where 1 is a center, 2 is a control processing unit, 3 is a display unit, 4 is a data management table, 5 is a switching network (network), 6 is a line such as a telephone line, 7 Is a recognition device, 8 is a camera, and 9 is a vehicle. The case where the vehicle monitoring system is comprised by connecting the center 1 and the recognition device 7 via the line 6 accommodated in the switching network 5 is shown. In addition, the recognition device 7 may be distributed in a highway, a general road, a parking lot, or the like, and may be connected to the center 10 via a line to configure a vehicle monitoring system.

Moreover, the camera 8 is arrange | positioned in the position which image | photographs the vehicle which drives on a highway or a general road, the vehicle which enters and exits a parking lot, or the position which photographs the vehicle in parking. In addition, the recognition device 7 has an image processing function, a character pattern recognition processing function, a data transmission / reception function, and the like. The image data generated by the camera 8 is processed by the image processing function to identify a specific character pattern of the vehicle 9. Extracts the area, recognizes the vehicle specific character pattern by the character recognition processing function, and captures the area or the specific character pattern area including the whole of the vehicle 9 from the captured image data in response to the recognition processing result in this case. While selecting the compression rate, it transmits to the center 1 via the line 6 by the transmission / reception function.

As shown in the drawing, the transmission data includes specific character pattern information and image compression data. For example, the specific character pattern information includes, for example, header information, point information, time information, and the vehicle specific character pattern of the recognition result. 12345 ", and the image compression data includes the compression range of the vehicle area or the specific character pattern area, the image quality, the compressed data length, and the compressed data.

Moreover, the control processing part 2 of the center 1 is provided with the data management table 4, This data management table 4 which stores the transmission data transmitted through the line 6 from the recognition apparatus 7 It includes the vehicle specific character pattern, which is partially omitted, and the image data, the image quality, and the time within the compression range.

For example, "12345" in the specific character pattern column of the item number 1 indicates the case where all of the vehicle specific character patterns can be recognized, and the image data indicates that the plate portion and the image quality are low. In other words, the compression range is set to a specific character pattern area, and the compression ratio is increased so that the reproduction quality is low. In addition, "?" In the specific character pattern column of the item number 3 shows the case where all the vehicle specific character patterns could not be recognized, and the image data in that case is set as the whole vehicle, and shows that image quality is high. In other words, the compression range is set to the vehicle area, and the compression ratio is made low so that the reproduction quality is improved. In addition, "12-45" in the specific character pattern column of the item number 4 shows that a specific character pattern part and image quality are high, when the character of the "?" Of a vehicle specific character pattern is not recognized. In other words, the compression range is set to a specific character pattern area, and the compression rate is lowered so that the reproduction quality is improved.

When the image data of, for example, item 3 of the data management table 4 is read out and displayed on the display unit 3 under the control of the control processing unit 2, since the compressed data of the low-compression vehicle region is restored and displayed, The vehicle can be displayed in high quality. Therefore, it is possible to visually identify the specific character pattern region on the display screen and read the character in the specific character pattern region. In that case, the specific character pattern field can be corrected to the vehicle specific character pattern which was visually confirmed. In addition, since only the vehicle area is compressed as compared with the case where the entire screen is compressed, the data amount can be reduced.

When the image data of item No. 4 is read out and displayed on the display unit 3, the specific character pattern portion can be displayed in high quality. Therefore, it becomes easy to visually confirm the character of "?" Which was not automatically recognized. Also in this case, the specific character pattern column of the data management table 4 can be corrected according to the confirmed content. In this case, since only a specific character pattern area is compressed and transmitted, data can be reduced compared with the case where the entire screen or the vehicle area is compressed.

In addition, when all vehicle specific character patterns can be automatically recognized as shown in Item No. 1, 2, and 6, since the specific character pattern area is compressed so that image quality may be low, the data amount can be further reduced. In this case, when the specific character pattern which has already been automatically recognized is displayed on the display unit 3, even if the image quality is low, reconfirmation becomes easy.

2 is a system explanatory diagram of Embodiment 1 of the present invention, where 10 is a center, 11 is a transceiver, 12 is a control processor, 13 is a display unit, 14 is a management table, 20 is a specific character pattern recognition device, and 21 is a recognition processor. 22 denotes a frame memory, 23 denotes a compression range / compression rate determination unit, 24 denotes an image compression unit, 25 denotes a transmission / reception unit, 30 denotes a photographing unit, and 40 denotes a line such as a telephone line. The center 10 corresponds to the center 1 in FIG. 1, the specific character pattern recognition device 20 corresponds to the center recognition device 7 in FIG. 1, and the photographing unit 30 is shown in FIG. 1. Corresponding to the camera 8 in FIG. 1, the line 40 corresponds to the line 6 in FIG. 1. The control processing unit 12 corresponds to the control processing unit 2 in FIG. 1, the display unit 13 corresponds to the display unit 3 in FIG. 1, and the management table 14 is illustrated in FIG. 1. It corresponds to the data management table 4. In addition, illustration is abbreviate | omitted about the network 5 in FIG.

The photographing unit 30 can continuously set the passing position or the parking position of the vehicle as a photographing range in a predetermined frame period like a TV camera. In addition, of course, it is also possible to set it as the structure which image | photographs only when a vehicle exists in the photography range. The image signal by the photographing unit 30 is digitized and stored in the frame memory 22 of the recognition processing unit 21. As described above, in the case of continuous shooting, since the recognition processing unit 21 can distinguish the background portion such as the road and the moving vehicle portion by the interframe difference at a predetermined time interval, the vehicle includes the vehicle. You can capture an area. Then, the specific character pattern area in the vehicle area is captured to perform character recognition processing in the specific character pattern area.

The compression range and compression rate determination unit 23 controls the compression range and the compression rate in accordance with the recognition processing result of the vehicle specific character pattern in the recognition processing unit 21. As described above, when the vehicle specific character pattern cannot be recognized, the compression range is set to the vehicle area, and the compression rate is lowered. When all the vehicle specific character patterns can be recognized, the compression range is set to the specific character pattern area, and the compression rate is increased. When a part of the vehicle specific character pattern can be recognized and the other cannot be recognized, the compression range is set to the specific character pattern area, and the compression rate is lowered.

The image compression unit 24 performs capturing and compression processing of the area of the image data of the frame memory 22 in accordance with the determination signal from the compression range and compression ratio determination unit 23, and compresses the compressed image data into the compression range and compression ratio. It transmits to the transmission / reception part 25 through the determination part 23 or directly, and transmits to the center 10 via the line 40. FIG.

In the center 10, the vehicle which once stored the compressed image data received by the transmission / reception unit 11 in the management table 14 under the control of the control processing unit 12, could not automatically recognize the vehicle specific character pattern. Is read out from the management table 14 automatically or in response to an operator's instruction, and decompression processing corresponding to the compression rate is displayed on the display unit 13. In this case, since the vehicle area can be displayed in high quality, the possibility of being recognized by visually confirming the vehicle specific character pattern by the display screen increases.

3 is a flowchart of Embodiment 1 of the present invention, in which the photographed image signal from the photographing section 30 (see FIG. 2) is digitized and recorded in the frame memory 22 (A1), and the background image data and this captured image data. And difference data (outline of the vehicle) are extracted (A2). As described above, the difference data indicates the difference between the background screen that becomes the same screen and the background screen such as a vehicle and another screen as time elapses, such as a road, and thus the difference data including the moved vehicle is Therefore, the area including the vehicle is captured from this difference data (A3).

Then, it is determined whether the vehicle can be recognized (A4). That is, the vehicle has various shapes, but has a different size and shape than a pedestrian or the like, so that the vehicle can be distinguished from other moving objects. If the vehicle cannot be recognized from the difference data, the process proceeds to step A1. If the vehicle can be recognized, the process proceeds to step A5.

In step (A5), by extracting a specific character pattern region, for example, a bar graph for a horizontal direction and a vertical direction can be created, and an area of a rectangular specific character pattern can be extracted based on this bar graph. have. Alternatively, if the background color of the specific character pattern is made white, for example, an area of which the background color other than the letter is almost rectangular and white is extracted as the area of the specific character pattern.

Then, it is determined whether or not the specific character pattern can be recognized (A6). When the determination is made, the character is captured, and the specific character pattern is digitized (A7). That is, character recognition is performed on the captured character area by pattern matching, feature point extraction, or the like. Next, it is determined whether all of the specific character patterns can be digitized, that is, whether all of the vehicle specific character patterns can be recognized (A8), and if so, the captured vehicle specific character pattern area. Is compressed at high compression ratio, that is, high compression ratio (A9).

If all the specific character patterns cannot be quantized, that is, only a part of the vehicle specific character patterns can be recognized, the recognized specific character patterns are digitized (A12), and the captured specific character pattern area is imaged. Important, that is, it compresses at low compression rate (A13). When the specific character pattern cannot be recognized or when the vehicle specific character pattern cannot be recognized at all, the area including the captured vehicle is focused on image quality, that is, it is compressed at low compression rate (A11). Then, transmission data as shown in FIG. 1 is created, and the compressed image data is transmitted from the specific character pattern recognition device 20 to the center 10 (A10).

4 is an explanatory diagram of the compression range, in which (a) shows a captured image by the photographing unit 30 (see FIG. 2), and shows a screen by image data stored in the example VS frame and the frame memory 22. . If the extraction of the specific character pattern cannot be performed or the automatic recognition of the vehicle specific character pattern is not possible at all, as shown in (b), the image compression is performed to capture the vehicle area and focus on the image quality. The section 24 compresses at low compression rate.

Therefore, when the compressed image data in this case is received at the center 10, restored, and displayed on the display unit 13, an image of a vehicle having good image quality is displayed, and the specific character pattern is visually confirmed to identify the specific character pattern. Can increase the likelihood of recognition.

When only a part of the vehicle specific character pattern can be automatically recognized, the specific character pattern area is compressed at a low compression rate. Therefore, when the center 10 receives image data obtained by compressing the specific character pattern region shown in (c) or (d) at a low compression rate, restores it, and displays it on the display unit 13, the specific character pattern with good image quality is obtained. Since it becomes a display screen of an area, the possibility of recognizing the vehicle specific character pattern with the naked eye can be made high.

Example 2

Fig. 5 is a system explanatory diagram of Embodiment 2 of the present invention, in which the same symbols as in Fig. 2 denote the same parts, and 26 is a data storage unit. This data storage section 26 has a configuration for storing image data such as a semiconductor integrated circuit memory, a hard disk device, etc., and is compressed by the result of determination of the compression range / compression ratio determination section 23 in the image compression section 24. The result of recognizing the vehicle specific character pattern in the data and recognition processing unit 21 is accumulated. For example, the compressed data is stored in the data storage unit 26 in the format of the transmission data shown in FIG. 1 or in a format corresponding to the data management table 4.

Then, the data storage unit 26 is retrieved from the center 10 according to the time designation or the vehicle specific character pattern designation, and the retrieved and extracted compressed data is read, for example, in the format of the transmission data shown in FIG. Is sent to the line 40. Therefore, in the second embodiment, the vehicle specific character pattern and the compressed image data which are automatically recognized can be collected from the specific character pattern recognition device 20 only when needed by the center 10.

6 is a system explanatory diagram of Embodiment 3 of the present invention, in which the same symbols as in FIG. 2 or 5 denote the same parts, and 27 is a control processing unit. When the matching processing unit 27 designates the specific vehicle specific character pattern from the center 10, the matching processing unit 27 searches for the vehicle specific character pattern stored in the data storage unit 26, and selects the specified vehicle specific character pattern and the recognition vehicle specific character pattern. In the case of matching in contrast, in the case of matching matching, image compressed data is read out from the data storage section 26, for example, according to the format of the transmission data shown in Fig. 1, and the center 10 via the line 6 from the transmission and reception section 25. Send to

The present invention is not limited to each of the above-described embodiments, but various additions can be made. For example, the camera 8 or the photographing unit 30 is a digital camera and is configured to photograph at regular time intervals. It is also possible to. It is also possible to facilitate the processing in the case of obtaining difference data by using the frame memory 22 in a two-sided configuration. It is also possible to control the compression ratio to switch to a multi-layered layer corresponding to the recognized number of vehicle specific character patterns.

By selecting the area and the compression ratio of the photographed image data corresponding to the recognition result in the automatic recognition of the vehicle specific character pattern, even if the vehicle specific character pattern cannot be recognized, the vehicle area is compressed instead of the full screen. The amount of data can be reduced. In addition, since the vehicle portion can be displayed in high quality when displayed on the display unit 3 of the center 1, the possibility of recognizing the vehicle specific character pattern can be increased by visually confirming. In addition, when the vehicle specific character pattern can be recognized, the specific character pattern area having a smaller area is further compressed, so that the data amount can be further reduced, and the transmission can be easily performed even through a low-rate line. In addition, since the recognition rate of the vehicle-specific character pattern is relatively high, even in the case of continuously transmitting compressed data, most of the data is compressed data of the specific character pattern area, and even if data including the recognized vehicle-specific character pattern is included, the amount of transmission data is small. Therefore, even a low speed line can be easily transmitted.

Claims (5)

A method of extracting a specific character pattern region of a vehicle based on photographed image data to perform character pattern recognition processing, and performing vehicle monitoring based on the recognized character pattern, When the character pattern recognition processing result indicates that the character pattern of the vehicle cannot be recognized, capturing and recording or transmitting a vehicle area including almost the entire vehicle from the photographed image data and compressing at a low compression rate; , When indicating that only a part of the specific character pattern of the vehicle can be recognized, capturing and recording or transmitting a specific character pattern region from the photographed image data at a low compression rate, and recording or transmitting the specific character pattern of the vehicle. When you indicate that you could recognize everything, And capturing a specific character pattern region from the photographed image data, compressing at a high compression ratio, and recording or transmitting the same. A frame memory for temporarily storing the captured image data by the photographing unit, an image processing function for capturing a vehicle region including a vehicle from the captured image data, and capturing a specific character pattern region from the vehicle region, and the specific character A recognition processing unit including a character recognition processing function for recognizing a character pattern of a pattern area; When the recognition processing result of the character pattern by the recognition processing unit indicates that the character pattern cannot be recognized, the compression range is set to the vehicle area, the compression ratio is set to the low compression rate, and the compression is set to indicate that only a part of the character pattern can be recognized. A compression range / compression rate determination unit for determining a specific character pattern area and a compression ratio as a high compression rate when indicating that the range is a specific character pattern area and a compression ratio as a low compression rate, and that all of the character patterns can be recognized; An image compression unit which captures an area of a compression range from the frame memory according to a determination result of the compression range / compression rate determination unit, and compresses the compression range according to a compression ratio; And a transmitting / receiving unit which transmits the image data compressed by the image compression unit. The specific character pattern recognition apparatus according to claim 2, further comprising a data storage section for storing the image data compressed by the image compression section together with the recognition result of the vehicle specific character pattern. The method according to claim 3, wherein the vehicle-specific character pattern instructed to be searched is matched with the vehicle-specific character pattern of the recognition result stored in the data storage unit, and when data is matched, the data stored in the data storage unit is read out and transmitted. And a matching processing unit. A vehicle monitoring system comprising a specific character pattern recognition device according to claim 2 which processes photographed image data by a photographing unit to recognize a vehicle specific character pattern, and a center connected through a line with a plurality of specific character pattern recognition devices. In the system, The specific character pattern recognition apparatus performs character pattern recognition processing on the basis of the photographed image data, and when the specific character pattern of the vehicle cannot be recognized, the vehicle region is captured from the photographed image data and compressed at a low compression rate. When only a part of the character pattern could be recognized, the specific character pattern area was captured and compressed at a low compression rate. When all the character patterns could be recognized, the specific character pattern area was captured and compressed and compressed at a high compression rate. Has a configuration to send out, And said center comprises a management table for receiving and storing compressed data from said specific character pattern recognition apparatus over a line and a display portion for displaying.

Images