Video monitoring method, video monitoring system, and video monitoring terminal

Abstract

To allow business support to be appropriately performed.SOLUTION: An image processing system according to one aspect of the present invention includes: a terminal comprising image storage means for recording an image and identification information on the image, transmission means for transmitting the identification information on the image and a partial image of the image to a server, and output means for outputting additional information based on the identification information received from the server; and the server comprising image matching means for matching the partial image received from the terminal with stored candidate images, and transmission means for transmitting the identification information corresponding to the matched image to the terminal.SELECTED DRAWING: Figure 17

Description

[Technical Field]

[0001] The present invention relates to image processing technology. [Background technology]

[0002] In recent years, surveillance cameras have been installed everywhere to deter crime and to monitor the situation when a crime occurs. However, fixed surveillance cameras alone have blind spots, so wearable surveillance camera systems have been proposed to easily compensate for these blind spots. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-148842 [Patent Document 2] Patent No. 4104577 Summary of the Invention [Problem to be solved by the invention]

[0004] According to the technology of Patent Document 1, the wearable surveillance camera system allows the camera direction and position to be freely controlled by the wearer's movements. However, as described in Patent Document 2, when camera image data is transmitted to a center side, the amount of data is usually reduced by high-compression encoding.

[0005] For example, there are known methods for reducing the amount of image data from surveillance cameras using image compression methods such as the Moving Picture Experts Group (MPEG2) method or the H.264 method, and then collecting the data via Ethernet (registered trademark) or wirelessly. However, image compression processing can cause compression distortion, which can make it difficult to obtain the clear image data required for business operations. As a result, it may not be possible to properly support business operations. An object of the present invention is to provide an image processing system, an image processing device, an image processing method, and a recording medium for storing a program, which are capable of appropriately providing business support. [Means for solving the problem]

[0006] In order to achieve this object, an image processing system according to one aspect of the present invention includes a terminal having an image storage means for storing an image and identification information for the image or a partial image of the image, a transmission means for transmitting the identification information and the partial image to a server, and an output means for outputting additional information based on the identification information received from the server, and a server having an image matching means for matching the partial image received from the terminal with stored candidate images, and a transmission means for transmitting the identification information corresponding to the matched image to the terminal.

[0007] Furthermore, an image processing system according to one aspect of the present invention includes a terminal having an image storage means for storing an image and identification information for the image or a partial image of the image, a transmission means for transmitting the identification information for the image and the partial image to a server and transmitting the image identified by the identification information received from the server to the server, and a server having an image matching means for matching the partial image received from the terminal with stored candidate images and a transmission means for transmitting the identification information corresponding to the matched image to the terminal.

[0008] In addition, an image processing device according to one aspect of the present invention includes an output means for outputting an image of an object area in an image captured by the imaging means if the value indicating the size of the object area is greater than a threshold value, or an image of a predetermined area including the object area if the value is not greater than a threshold value. In one aspect of the image processing method of the present invention, a terminal stores an image and identification information of the image or a partial image of the image in an image storage means, transmits the identification information and the partial image to a server, outputs additional information based on the identification information received from the server, and the server compares the partial image received from the terminal with stored candidate images and transmits the identification information corresponding to the compared image to the terminal. A computer-readable recording medium according to one aspect of the present invention stores a program that causes a computer to operate as an output means that outputs an image of an object area in an image captured by an imaging means if a value indicating the size of the object area is greater than a threshold value, or an image of a specified area including the object area if the value is not greater than a threshold value. [Effects of the Invention]

[0009] According to the present invention, an image processing system, an image processing device, an image processing method, and a recording medium storing a program are provided that are capable of appropriately providing business support. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 shows a configuration of an image processing system according to a first embodiment of the present invention. [Figure 2] FIG. 2 shows a configuration of the image processing unit A according to the first embodiment of the present invention. [Figure 3] FIG. 3 shows an example of an operation flow of the first embodiment of the present invention. [Figure 4] FIG. 4 shows an example of an operation flow of the first embodiment of the present invention. [Figure 5] FIG. 5 shows a configuration of an image processing system according to the second embodiment of the present invention. [Figure 6] FIG. 6 shows an example of an operation flow according to the second embodiment of the present invention. [Figure 7] FIG. 7 shows a configuration of an image processing system according to the third embodiment of the present invention. [Figure 8] FIG. 8 shows an example of an image display according to the third embodiment of the present invention. [Figure 9] FIG. 9 shows an example of an operation flow of the third embodiment of the present invention. [Figure 10] FIG. 10 shows a configuration of an image processing system according to the fourth embodiment of the present invention. [Figure 11] FIG. 11 shows a configuration of an image processing system according to the fifth embodiment of the present invention. [Figure 12] FIG. 12 shows a configuration of an image processing system according to the sixth embodiment of the present invention. [Figure 13] FIG. 13 shows a configuration of an image processing system according to the seventh embodiment of the present invention. [Figure 14] FIG. 14 shows a configuration of an image processing system according to the eighth embodiment of the present invention. [Figure 15] FIG. 15 shows a configuration of an image processing system according to the ninth embodiment of the present invention. [Figure 16] FIG. 16 shows an example of an image cutting method according to the first and twelfth embodiments of the present invention. [Figure 17] FIG. 17 shows a configuration of an image processing system according to the tenth embodiment of the present invention. [Figure 18] FIG. 18 shows an example of an operation flow of the tenth embodiment of the present invention. [Figure 19] FIG. 19 shows a configuration of an image processing system according to the eleventh embodiment of the present invention. [Figure 20] FIG. 20 shows an example of an operation flow of the eleventh embodiment of the present invention. [Figure 21] FIG. 21 shows one configuration of a terminal according to the twelfth embodiment of the present invention. [Figure 22] FIG. 22 shows an example of an image extraction method according to the twelfth embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all drawings, similar components are designated by similar reference numerals, and descriptions thereof will be omitted where appropriate. Note that each component constituting an apparatus, etc., in the following description is configured with hardware such as a logic circuit. Furthermore, each component may be configured with a computer control unit, memory, a program loaded into the memory, a storage unit such as a hard disk for storing the program, an interface for network connection, etc., and may be realized by any combination of hardware and software. Furthermore, unless otherwise specified, the implementation method and device are not limited.

[0012] First Embodiment FIG. 1 is a diagram showing an example of the overall configuration of an image processing system according to a first embodiment of the present invention.

[0013] The image processing system includes a first monitoring information terminal unit 1 and a first monitoring server unit 2. The first monitoring information terminal unit 1 and the first monitoring server unit 2 are connected by wired or wireless communication C1.

[0014] The first monitoring information terminal unit 1 comprises a camera unit 11, an image processing unit A 12, an image storage unit 13, and a transmission / reception unit .

[0015] Image data A11 captured by the camera unit 11 is input to the image processing unit A12.

[0016] When an object is included in image data A11, image processing unit A12 detects an object region including the object based on preset detection parameters. Image processing unit A12 also has a function of cutting out an image of the object region. The cut-out image is also referred to as partial image data A13. An object detected by image processing unit A12 is, for example, a person's face, a bag, or a car.

[0017] The image processing A unit 12 outputs an image ID (IDentification) such as a frame number input from the camera unit 11 and partial image data A13 to the transmission / reception A unit 14.

[0018] The image processing A unit 12 records the image data A11 together with the image ID in the image storage unit 13. The combination of the image data A11 and the image ID is also called recording data A12. The image ID may be a frame number, but since there may be multiple objects on the screen, it may also be an ID assigned to each object area. In that case, the ID may be the position information (coordinate information) of the object, the size of the object, etc.

[0019] The recording data A12 may be subjected to image compression using a video compression method based on the relationship with the recording capacity and recording time of the image storage unit 13. The video compression method is, for example, a coding method that uses inter-frame differences, such as the MPEG-2 coding method or the MPEG-4 AVC (Advanced Video Coding) method. The MPEG-2 coding method is ISO (International Organization for Standardization) / IEC (International Electrotechnical Commission) 13818-2. The MPEG-4 AVC method is ISO / IEC 14496-10.

[0020] When image data is requested by the first monitoring server unit 2, the image processing A unit 12 transmits the requested image data to the first monitoring server unit 2 via the transmission / reception A unit 14. The detailed operation will be described later.

[0021] The transmission / reception A unit 14 transmits the partial image data A13 and the image ID output from the image processing A unit 12 to the first monitoring server unit 2. The transmission / reception A unit 14 also transmits the image data to the first monitoring server unit 2.

[0022] The first monitoring server unit 2 includes a transmission / reception B unit 21, an image processing B unit 22, a database unit 23, and an image display unit 24.

[0023] The partial image data A13 and the image ID input from the first monitoring information terminal unit 1 are input to the image processing unit B22.

[0024] The image processing B unit 22 performs a comparison between the partial image data A13 and image data registered in the database unit 23. The image comparison method is appropriately set according to the object to be compared.

[0025] If the partial image data A13 is matched with an image stored in the database unit 23, the image processing unit B 22 requests the image data having the image ID recorded therein from the first monitoring information terminal unit 1 via the transmission / reception unit B 21. Specifically, the image processing unit B 22 may extract the corresponding image ID and transmit it to the first monitoring information terminal unit 1, or may transmit image data including the image ID to the first monitoring information terminal unit 1. In this case, for example, if the image data is recorded in the image storage unit 13 using an uncompressed or intra-frame compression method, the image processing unit B 22 may transmit the corresponding frame image data. Alternatively, if the image data is recorded in the image storage unit 13 using a video compression method, the image processing unit B 22 may transmit an image stream including the frame image data having the image ID. Note that the intra-frame compression method is, for example, ISO / IEC 10918-1 (JPEG (Joint Photographic Experts Group) compression method). Furthermore, for example, the image stream transmitted using the video compression method is transmitted in units of GOPs (Group of Pictures) in the MPEG-2 encoding method.

[0026] The image processing B unit 22 superimposes information about the matching result of the matched object image on the image data transmitted to the first monitoring server unit 2 and displays the superimposed information about the matching result on the image display unit 24. The superimposed display of information about the matching result will be described below. For example, if the object is a human face, the image processing B unit 22 superimposes and displays a frame at a position corresponding to the matched face area, as shown in FIG. 8. The thing that is superimposed and displayed does not have to be a frame, and an image ID or the like may also be superimposed and displayed in addition to the frame.

[0027] Next, an example of operation of this embodiment will be described. The image processing A unit 12 is composed of an image IO (Input Output) unit 121, a CPU (Central Processing Unit) unit 122, a memory unit 123, and an external IO unit 124, as shown in Fig. 2. The CPU unit 122 operates as shown in the flow charts of Figs. 3 and 4.

[0028] The operation of the image processing A unit 12 will be described in detail with reference to Figures 2, 3, and 4. Figure 3 is a flow chart showing the operation in a normal monitoring state, for example. When the power is turned on, the CPU unit 122 initializes each parameter (step S1) and accepts image input from the camera unit 11 (step S2).

[0029] The CPU unit 122 ends the process when there is no more image input from the image IO unit 121 (YES in step S3). On the other hand, if there is an image input (NO in step S3), the CPU unit 122 counts the frame number (FrameNum) (step S4) and reads parameters for object detection from the memory unit 123 (step S5). The CPU unit 122 detects an object from the image input data based on the read parameters (step S6).

[0030] If an object is detected (YES in step S7), the CPU unit 122 extracts the coordinate position information (ObjectCoord) of the detected object in the image and the image data area (ObjectXsize, ObjectYsize) that includes the detected object (step S8).The CPU unit 122 also adds a unique object detection number (ObjectNum) (step S9).

[0031] The CPU unit 122 associates the object detection number, coordinate position information, and image data area (partial image data A13) and manages them in a table. The CPU unit 122 further calculates an image ID from the object detection number and frame number (step S10). However, to reduce processing load, the image ID may be substituted with the frame number.

[0032] The CPU unit 122 outputs the image ID and the partial image data A13 to the transmission / reception A unit 14 (step S11) and performs the next object detection. The transmission / reception A unit 14 transmits the image ID and the partial image data A13 to the first monitoring server unit 2.

[0033] The CPU unit 122 repeats the detection process over the entire image data area, and when the image data detection process is completed, it performs image encoding together with the image ID added within the frame (step S12), and records the image data in the image storage unit 13 via the external IO unit 124 (step S13).

[0034] Furthermore, when the first monitoring server unit 2 requests image data together with an image ID, the CPU unit 122 analyzes the image ID and extracts a frame number from the image ID (step S14). The CPU unit 122 reads out stored image data (image stream) including the image data of the frame number from the image storage unit 13 (step S15). The CPU unit 122 outputs the image data (image stream) to the transmission / reception A unit 14 (step S16). The transmission / reception A unit 14 transmits the image data to the first monitoring server unit 2.

[0035] These operations make it possible to maintain image quality that allows image matching while reducing the size of data sent and received between the first monitoring information terminal unit 1 and the first monitoring server unit 2. Furthermore, after image matching, a monitor on the first monitoring server unit 2 side can monitor the entire image of the matching result.

[0036] Next, the object detection operation of the image processing A unit 12 shown in Fig. 1 will be described in detail with reference to Fig. 16. For example, when the surveillance target is a person, if the surveillance target is a wanted criminal, it is desirable to perform face matching with a wanted photograph. Therefore, it is desirable that the size of the face image to be detected is large enough to be able to match it with a wanted photograph.

[0037] 16(1), for example, when the distance W1 between the eyes of a person's face is greater than a predetermined number of pixels TH1 and less than TH2, the image processing A unit 12 cuts out an image data area that is larger than the contours of the face, because in this case, the size of the face image is likely to be large enough to allow face matching.

[0038] On the other hand, when the distance W2 between the eyes of a person's face is smaller than the predetermined number of pixels TH1, as shown in (2) of Fig. 16, the image processing A unit 12 cuts out an image data area larger than the outline of the entire body, since the size of the face image is likely to be insufficient for face matching, so that image matching can be performed using the image of the entire subject.

[0039] However, in cases where the face size is within the threshold but there is a possibility that the facial features of the person may not be fully captured, as in (1) of Fig. 16, the image processing A unit 12 may crop the image to a size larger than the outline of the entire body, as in (2). In such cases, the person may be wearing glasses or a mask.

[0040] As another example, let us consider the case where the target object is an automobile, as shown in (3) of Figure 16. Assuming that the monitored object is a wanted vehicle, it is important to detect the license plate area and determine whether the license plate can be read. Therefore, if the width W3 of the detected license plate is greater than a predetermined number of pixels TH1 and less than TH2, the image processing A unit 12 cuts out the license plate area as an image data area. This is because there is a high possibility that the license plate can be read.

[0041] In contrast, if the width W4 of the license plate is smaller than the predetermined number of pixels TH1, as in (4) of Figure 16, the image processing A unit 12 cuts out an image data area larger than the outline of the entire vehicle and sends it to the monitoring server.

[0042] By cutting out the image in this way, it is possible to prevent unnecessary image areas from being sent to the first monitoring server unit 2, thereby reducing the communication data size.

[0043] According to this embodiment, it is possible to maintain image quality sufficient for image matching while reducing the size of data transmitted and received between the first monitoring information terminal unit 1 and the first monitoring server unit 2. Furthermore, after image matching, a monitor on the first monitoring server unit 2 side can monitor the entire image of the matching result. Therefore, the image processing system can provide appropriate business support.

[0044] Although the above description describes a monitoring task as a task, the task is not limited to monitoring. For example, this system can also be used for customer service, maintenance, and inspection. Therefore, in other tasks, the monitoring information terminal unit and monitoring server unit may simply be referred to as a terminal and a server, respectively. The terminal is held by a monitor or customer service staff member. Here, "held" includes being worn integrally with clothing such as a hat or clothing (wearable, etc.) or being held by the hand or other device. The held terminal may be what is known as a scouter. A scouter is a wearable computer that combines a glasses-type head-mounted display that displays translucent images in part or all of the field of view with an eye-tracking camera. A scouter is formed, for example, by a small computer that outputs video and communicates with other devices. When connected to dedicated camera-equipped eyeglass frames or audio devices such as a microphone and earphones, a scouter can support not only monitoring tasks but also on-site tasks such as maintenance, inspection, and assembly. These points will not be repeated in the following embodiments, but they apply equally unless otherwise noted.

[0045] <Second embodiment> 5 is a diagram showing an example of the overall configuration of an image processing system according to the second embodiment of the present invention. The image processing system includes a second monitoring information terminal unit 3, and a first monitoring server unit 2 or a second monitoring server unit 4.

[0046] The second monitoring information terminal unit 3 and the first monitoring server unit 2 or the second monitoring server unit 4 are connected via wired or wireless communication C1. Hereinafter, a case where the second monitoring information terminal unit 3 and the second monitoring server unit 4 are connected via communication C1 will be described in detail. Explanations of parts that are the same as those in the first embodiment will be simplified as appropriate. This embodiment differs from the first embodiment in that an image display unit 15 is included on the monitoring information terminal unit 3 side.

[0047] The second monitoring information terminal unit 3 includes a camera unit 11, an image processing unit A 12, an image storage unit 13, a transmission / reception unit 14, and an image display unit 15.

[0048] Image data A11 captured by the camera unit 11 is input to the image processing A unit 12. As in the first embodiment, the image processing A unit 12 cuts out an object detected in the image data A11 based on preset detection parameters. As in the first embodiment, the image processing A unit 12 outputs an image ID such as a frame number input from the camera unit 11 and the cut-out object image data A13 (partial image data A13) to the transmission / reception A unit 14.

[0049] The image processing A unit 12 records the image data A11 and the image ID in the image storage unit 13, as in the first embodiment.

[0050] The transmission / reception A unit 14 combines the partial image data A13 and the image ID output from the image processing A unit 12 and transmits them to the second monitoring server unit 4, as in the first embodiment.

[0051] The second monitoring server unit 4 includes a transmission / reception B unit 21, an image processing B unit 22, and a database unit .

[0052] As in the first embodiment, the partial image data A13 and the image ID are input to the image processing B unit 22. The image processing B unit 22 performs a comparison between the partial image data A13 and image data registered in the database unit 23.

[0053] As in the first embodiment, when a partial image A13 is matched with an image in the database unit 23, the image processing B unit 22 extracts the image ID related to the matched image and transmits the image ID to the second monitoring information terminal unit 3 via the transmission / reception B unit 21.

[0054] The image processing A unit 12 of the second monitoring information terminal unit 3 refers to the image storage unit 13, and displays image data A14 obtained by superimposing information related to the object image matching result on image data related to the image ID acquired from the second monitoring information terminal unit 3 on the image display unit 15. Specifically, for example, the image processing A unit 12 extracts the frame number (FrameNum), coordinate position information (ObjectCoord), and image data area (ObjectXsize, ObjectYsize) based on the image ID (step S21 in FIG. 6). Next, the image processing A unit 12 refers to the image storage unit 13 and reads out the image stream of the extracted frame number (step S22 in FIG. 6). Next, the image processing A unit 12 decodes the target frame of the read image stream, and superimposes and displays information related to the object image matching result on the matched image area based on the coordinate position information (step S23 in FIG. 6). An example of the superimposed display is the same as that in the first embodiment.

[0055] According to this embodiment, it is possible to reduce the size of data transmitted and received via communication C1 between the second monitoring information terminal unit 3 and the second monitoring server unit 4, while ensuring sufficient image quality for image matching. Furthermore, according to this embodiment, when image matching is performed by the second monitoring server unit 4, the monitor can check the image of the matching result on the monitoring information terminal unit 3, so that the monitor can carefully monitor the object that has been matched. Note that when the second monitoring information terminal unit 3 is connected to the first monitoring server unit 2, the monitor monitoring on the server side can also perform similar monitoring. In this way, the image processing system can provide appropriate business support.

[0056] <Third embodiment> 7 is a diagram showing an example of the configuration of an image processing system according to the third embodiment of the present invention. The image processing system includes a third monitoring information terminal unit 5, and a first monitoring server unit 2 or a second monitoring server unit 4.

[0057] The third monitoring information terminal unit 5 and the first monitoring server unit 2 or the second monitoring server unit 4 are connected via wired or wireless communication C1. The system connected to the first monitoring server unit 2 will be described in detail below. Explanations of parts that are similar to those in the above-mentioned embodiment will be simplified as appropriate. The monitoring information terminal unit 5 of this embodiment differs from the above-mentioned embodiment in that it includes an input unit 16.

[0058] The third monitoring information terminal unit 5 includes a camera unit 11, an image processing A unit 12, an image storage unit 13, a transmitting / receiving unit 14, an image display unit 15, and an input unit 16.

[0059] As in the above-described embodiment, image data A11 captured by the camera unit 11 is input to the image processing unit A 12. The image processing unit A 12 extracts an object image detected from the image data A11 based on preset detection parameters. The transmission / reception unit A 14 transmits the image ID and the extracted object image data A13 to the first surveillance server unit 2. The image processing unit A 12 then records the image data A11 together with the image ID in the image storage unit 13. The image processing unit A 12 also superimposes the detected object on the camera input image and displays it on the image display unit 15. In this case, for example, a frame is superimposed on the detected face area on the image display unit 15, as shown in FIG. 8. Furthermore, as shown in FIG. 8, an ID identifying the person may be superimposed and displayed near the frame of the face area.

[0060] The input unit 16 is an information input means provided as, for example, a touch sensor on the display screen, a cross key, or a button for directly inputting an ID.

[0061] The input unit 16 is used as follows. For example, assume that the object is a person. For example, when a person behaving suspiciously is captured in an image, a monitor holding the third monitoring information terminal unit 5 specifies information indicating the object area, such as the person's ID, using the input unit 16. The input method is not particularly limited. For example, as shown in FIG. 8, a frame indicating the ID may be superimposed on the face area, and the person's ID may be selected and input by selecting the frame.

[0062] When an ID is input, the third monitoring information terminal unit 5 transmits the ID to the first monitoring server unit 2 so that the ID can be distinguished from other IDs. The first monitoring server unit 2 compares, prior to other processing, whether or not the facial image of the person identified by this ID matches a facial image registered in the database unit 23. If the facial image is not registered, the person may be additionally registered in the database unit 23 as a person requiring attention.

[0063] The operation of this embodiment will be described with reference to Figures 2, 3 and 9. The configuration of the image processing A unit 12 is as shown in Figure 2 as described above. The description up to step S10 is the same as in Figure 3, so will be omitted.

[0064] Next, the CPU unit 122 superimposes the detected object on the camera input image and displays it on the image display unit 15 (step S31). If an object of interest is present in the video, the operator of the third monitoring information terminal unit 5 inputs or selects the object's ID via the input unit 16 (YES in step S32). This causes the CPU unit 122 to add a target object flag to the ID and calculate an image ID (step S33). The flow then proceeds to step S11 in FIG. 3.

[0065] The first monitoring server unit 2 takes priority over other processes in verifying whether or not the image of the object identified by the image ID is an image registered in the database unit 23. If the image of the object is not registered, the image may be additionally registered in the database unit 23 as a suspicious object.

[0066] According to this embodiment, the monitoring information terminal unit 3 can select the target to be monitored, thereby giving priority to obtaining the matching result. When the third monitoring information terminal unit 5 is connected to the first monitoring server unit 2, the monitor monitoring on the server side can also monitor. In this way, the image processing system can appropriately support business operations.

[0067] <Fourth embodiment> 10 is a diagram showing an example of the configuration of an image processing system according to the fourth embodiment of the present invention. The image processing system includes a fourth monitoring information terminal unit 7, and a first monitoring server unit 2 or a second monitoring server unit 4.

[0068] The fourth monitoring information terminal unit 7 and the first monitoring server unit 2 or the second monitoring server unit 4 are connected via wired or wireless communication C1. The system connected to the second monitoring server unit 4 will be described in detail below. Explanations of parts that are the same as those in the above-mentioned embodiment will be omitted as appropriate. The monitoring information terminal unit 7 of this embodiment differs from the above-mentioned embodiment in that it includes an image processing C unit 17.

[0069] The fourth monitoring information terminal unit 7 includes a camera unit 11, an image processing unit A 12, an image storage unit 13, a transmission / reception unit A 14, an image display unit 15, and an image processing unit C 17. The functions and configurations other than the image processing unit C 17 are as described above, and therefore will not be described here.

[0070] When an object for which surveillance is to be strengthened within the surveillance area is identified in advance, the second surveillance server unit 4 transmits image data or image features of the object to the fourth surveillance information terminal unit 7. An object for which surveillance is to be strengthened may be, for example, a wanted criminal or an object that could be a murder weapon, but in cases other than surveillance work, it may also be a valued customer. Such an object will be simply referred to as a target object below. Such target objects are designated in advance by a surveillance person or the like and stored in the database unit 23.

[0071] Image data or image features of the target object are input to the fourth monitoring information terminal unit 7 from the second monitoring server unit 4, and the features etc. are stored (or temporarily stored) in the image processing C unit 17.

[0072] Image processing C unit 17 performs image matching using the object image region data detected by image processing A unit 12 and the stored image data or image feature amounts. If the image of the target object is matched as a result of image matching, image display unit 15 displays the image of the target object or information that distinguishes the image from other objects.

[0073] The configuration of the image processing C unit 17 may be the same as that of the image processing A unit shown in Fig. 2. Therefore, if the performance of the CPU unit 122 in Fig. 2 is sufficient, the image processing A unit 12 and the image processing C unit 17 may perform calculations in the same CPU unit.

[0074] This allows a monitor or the like to monitor for objects requiring attention, etc. In this way, the image processing system can provide appropriate support for work.

[0075] <Fifth embodiment> 11 is a diagram showing an example of the configuration of an image processing system according to the fifth embodiment of the present invention. The image processing system includes a fifth monitoring information terminal unit 8, and a first monitoring server unit 2 or a second monitoring server unit 4.

[0076] The fifth monitoring information terminal unit 8 and the first monitoring server unit 2 or the second monitoring server unit 4 are connected via wired or wireless communication C1. The system connected to the second monitoring server unit 4 will be described in detail below. Explanations of parts that are the same as those in the above-mentioned embodiment will be omitted as appropriate. The monitoring information terminal unit 8 of this embodiment differs from the above-mentioned embodiment in that it includes both an input unit 16 and an image processing C unit 17.

[0077] The fifth monitoring information terminal unit 8 includes a camera unit 11, an image processing A unit 12, an image storage unit 13, a transmission / reception unit 14, an image display unit 15, an input unit 16, and an image processing C unit 17. Descriptions of functions and configurations other than those of the input unit 16 and the image processing C unit 17 will be omitted.

[0078] The input unit 16 is an input means such as a touch sensor, a cross key, or a button that allows direct input of an ID, as described above. When a person behaving suspiciously is captured on video, a monitor holding the fifth monitoring information terminal unit 8 inputs the person's ID via the input unit 16. In this case, the fifth monitoring information terminal unit 8 transmits the ID to the second monitoring server unit 4 so that the ID can be distinguished from other IDs. The second monitoring server unit 4 compares, with priority over other processes, whether the facial image of the person identified by the real ID is a facial image registered in the database unit 23. If the facial image is not registered, the facial image may be additionally registered in the database unit 23 as a suspicious person.

[0079] When the target object is known in advance, the second monitoring server unit 4 transmits its image data or image feature amounts to the fifth monitoring information terminal unit 8. As a result, the image data or image feature amounts of the target object are input from the second monitoring server unit 4 to the fifth monitoring information terminal unit 8, and the feature amounts are stored (or temporarily stored) in the image processing C unit 17.

[0080] Image processing C unit 17 performs image matching using the object image region data detected by image processing A unit 12 and the stored image data or image feature amounts. As a result of image matching, if the image of the target object is matched, the image of the target object or information that distinguishes the image from other objects is displayed on image display unit 15.

[0081] In this way, by providing both the input unit 16 and the image processing C unit 17, it is possible to specify an object of interest on both the terminal side and the server side. This allows the monitor to monitor objects requiring attention more carefully. In this way, the image processing system can provide appropriate support for the work.

[0082] Sixth Embodiment Fig. 12 is a diagram showing an example of the configuration of an image processing system in the sixth embodiment of the present invention. The image processing system includes a plurality of second monitoring information terminal units 3 and 3', and a first monitoring server unit 2 or a second monitoring server unit 4. In Fig. 12 and the following description, two second monitoring information terminal units 3 and 3' are shown, but the number of second monitoring information terminal units may be three or more.

[0083] 12, the second monitoring information terminal units 3 and 3' and the first monitoring server unit 2 (or the second monitoring server unit 4) are connected via a wired or wireless communication network 9 (hereinafter also referred to as the network 9). Since the configuration and operation of the second monitoring information terminal units 3 and 3' have been explained in the second embodiment, only the different parts of the operation will be explained in detail.

[0084] Partial image data A13 of an object detected by the second monitoring information terminal unit 3 is input to the first monitoring server unit 2 via the network 9. In the first monitoring server unit 2, the image processing B unit 22 performs image matching between the image data or image feature amounts in the database unit 23 and the partial image data A13. When the partial image data A13 is matched with image data registered in the database unit 23, the first monitoring server unit 2 transmits the matched image data to the second monitoring information terminal unit 3' as matched image data.

[0085] The second monitoring information terminal unit 3' displays the image data transmitted via communication C1 on the image display unit 15. In this way, the image data detected by another monitoring information terminal is shared.

[0086] According to this embodiment, image data registered in the database unit 23 can be displayed to the monitor who can view the image display unit 15 of the second monitoring information terminal unit 3'. This allows other monitors to share information when they discover a suspicious object or person. In this way, the image processing system can provide appropriate support for operations.

[0087] Seventh Embodiment Fig. 13 is a diagram showing an example of the configuration of an image processing system in the seventh embodiment of the present invention. The image processing system includes a plurality of third monitoring information terminal units 5 and 5' and a first monitoring server unit 2 or a second monitoring server unit 4. In Fig. 13 and the following description, two third monitoring information terminal units 5 and 5' are shown, but the number of third monitoring information terminal units may be three or more.

[0088] As shown in Fig. 13, the third monitoring information terminal units 5 and 5' and the first monitoring server unit 2 (or the second monitoring server unit 4) are connected via a wired or wireless communication network 9. The configuration and operation of the third monitoring information terminal units 5 and 5' have been explained in the third embodiment, so only the different operations will be explained in detail. Also, explanations of the parts that perform the same operations as in the sixth embodiment will be omitted.

[0089] As described above, for example, a monitor holding the third monitoring information terminal unit 5 inputs the ID of an object of interest in the image data resulting from object detection, using the input unit 16. The ID is input to the first monitoring server unit 2 via the network 9 together with the partial image data A13. In the first monitoring server unit 2, the image processing B unit 22 performs image matching between the image data or image feature amounts in the database unit 23 and the partial image data A13.

[0090] When the partial image data A13 is compared with image data registered in the database unit 23, the first monitoring server unit 2 transmits the image data to the third monitoring information terminal unit 5' as comparison image data via communication C1.

[0091] The third monitoring information terminal unit 5' displays the received collation image data on the image display unit 15. In this way, the image data detected by the other monitoring information terminal is shared.

[0092] According to this embodiment, image data registered in the database unit 23 can be displayed to the monitor who can view the image display unit 15 of the third monitoring information terminal unit 5'. This allows other monitors to share information when they discover a suspicious object or person. In this way, the image processing system can provide appropriate support for operations.

[0093] Eighth Embodiment Fig. 14 is a diagram showing an example of the configuration of an image processing system in the eighth embodiment of the present invention. The image processing system includes a plurality of fourth monitoring information terminal units 7 and 7' and a first monitoring server unit 2 or a second monitoring server unit 4. In Fig. 14 and the following description, two fourth monitoring information terminal units 7 and 7' are shown, but the number of fourth monitoring information terminal units may be three or more.

[0094] As shown in Fig. 14, the fourth monitoring information terminal units 7 and 7' and the first monitoring server unit 2 (or the second monitoring server unit 4) are connected via a wired or wireless communication network 9. The configuration and operation of the fourth monitoring information terminal units 7 and 7' have been explained in the fourth embodiment, so only the different operations will be explained in detail. Also, explanations of the parts that perform the same operations as in the other embodiments will be omitted.

[0095] Image data or image features of a target object are input to the fourth monitoring information terminal unit 7 from the first monitoring server unit 2, and the features are stored in the image processing C unit 17. The image processing C unit 17 performs image matching using the object image area data detected by the image processing A unit 12 and the stored image data or image features. Similar processing is performed in the fourth monitoring information terminal unit 7'.

[0096] Partial image data A13 of the object detected by the fourth monitoring information terminal unit 7 or 7' is transmitted to the first monitoring server unit 2 via the network 9. The first monitoring server unit 2 transmits the image data to other terminals, namely, the fourth monitoring information terminal units 7' and 7. The fourth monitoring information terminal unit 7' displays the image data S3 on the image display unit 15. This allows the image data detected by another monitoring information terminal to be shared.

[0097] According to this embodiment, images of the monitored object can be shared. This allows other monitors to share information when they discover a suspicious object or person. In this way, the image processing system can provide appropriate support for operations.

[0098] <Ninth embodiment> Fig. 15 is a diagram showing an example of the configuration of an image processing system according to the ninth embodiment of the present invention. The image processing system includes a plurality of fifth monitoring information terminal units 8 and 8', and a first monitoring server unit 2 or a second monitoring server unit 4. Although Fig. 15 and the following description show two fifth monitoring information terminal units 8 and 8', the number of fifth monitoring information terminal units may be three or more.

[0099] The fifth monitoring information terminal units 8 and 8' are connected to the first monitoring server unit 2 or the second monitoring server unit 4 via a wired or wireless communication network 9. The configuration and operation of the fifth monitoring information terminal units 8 and 8' have been explained in the fifth embodiment, so only the different parts of the operation will be explained in detail. Also, explanations of the parts explained in the above embodiment will be omitted.

[0100] A monitor holding the fifth monitoring information terminal unit 8 inputs the ID of an object that the monitor wishes to distinguish from other objects via the input unit 16. The fifth monitoring information terminal unit 8 transmits the ID to the first monitoring server unit 2. The first monitoring server unit 2 compares, prior to other processing, whether or not the image of the object identified by this ID is image data registered in the database unit 23.

[0101] If the image of the object is not image data registered in the database unit 23, the image data is transmitted as collation image data to the fifth monitoring information terminal unit 8' via communication C1. The fifth monitoring information terminal unit 8' displays the image data S3 on the image display unit 15.

[0102] Furthermore, when the first monitoring server unit 2 knows in advance the object to be detected, it transmits the image data or image feature quantities thereof to the fifth monitoring information terminal units 8 and 8'. As a result, the image data or image feature quantities of the object to be detected are input from the first monitoring server unit 2 to the fifth monitoring information terminal units 8 and 8', and the feature quantities are stored in the image processing C unit 17.

[0103] The image processing C unit 17 compares the image data transmitted by communication C1 with the image data or image feature amount of the target object, and displays the comparison image on the image display unit 15 if the comparison is successful.

[0104] According to this embodiment, images of the monitored object can be shared. This allows other monitors to share information when they discover a suspicious object or person. In this way, the image processing system can provide appropriate support for operations.

[0105] <Tenth embodiment> Next, a tenth embodiment of the present invention will be described. Fig. 17 shows an example of the configuration of an image processing system according to this embodiment. The image processing system includes a terminal 10 having an image storage unit 101, a transmission unit 102, and an output unit 103, and a server 20 having an image matching unit 201 and a transmission unit 202.

[0106] The image storage unit 101 stores an image and an ID (i.e., identification information) of the image or a partial image of the image in association with each other. The image may be an image acquired from an imaging device such as a camera. The terminal 10 may assign a unique ID to each acquired image (or each partial image) and record the ID in the image storage unit 101, or may acquire an image to which an ID has been assigned in advance and record the image in the image storage unit 101. A partial image is a partial image cut out from an image. The partial image includes, for example, an area in which an object is captured (i.e., an object area). As described in the first embodiment, the terminal 10 may be equipped with an image processing unit with an object detection function. Note that an ID may be assigned to each image based on the frame number of the image itself. However, since multiple objects may be included on the screen, an ID may be assigned to each partial image based on object position information (i.e., coordinate information) or object size, etc. The transmission unit 102 transmits the ID and the partial image to the server 20.

[0107] The output unit 103 outputs additional information based on the ID received from the server 20. The output includes image display output to a display unit, output to an external device, etc. The additional information is information related to the matching result in the server 20. For example, the additional information is information that distinguishes an image (or a partial image) associated with the ID received from the server 20 from other images (or other partial images). For example, when the object is a face image of a person, the additional information is a frame superimposed on the detected face area as shown in FIG. 8. Furthermore, as shown in FIG. 8, an ID that identifies the person may be superimposed near the frame of the face area. In this case, the ID itself is the additional information. Furthermore, the additional information may be a partial image itself in which the face area is captured.

[0108] The image matching unit 201 matches a partial image received from the terminal 10 with a candidate image. The candidate images are stored in a database (not shown) provided inside or outside the server 20. The transmission unit 202 transmits an ID associated with the matched image to the terminal 10.

[0109] The operation of the image processing system of this embodiment will be described with reference to FIG. 18. As described above, the transmission unit 102 of the terminal 10 transmits an ID and a partial image to the server 20 (step S101). The image matching unit 201 of the server 20 matches the partial image received from the terminal 10 with a candidate image (step S102). If a match is found (YES in step S102), the image matching unit 201 transmits an ID associated with the matched image to the terminal 10 (step S103). The output unit 103 of the terminal 10 outputs additional information based on the ID received from the server 20 (step S104). Since the terminal 10 stores the entire image, it can also grasp the relevance between the matching result of the partial image and the entire image including the partial image. Therefore, for example, the output unit 103 may superimpose the partial image (e.g., a face image) and the entire image (e.g., an image of the entire person or a background image) on the display unit, as shown in FIG. 8.

[0110] According to this embodiment, the terminal only needs to transmit a portion of the image to the server, thereby reducing the communication load. Furthermore, there is no need to provide an image matching unit in the terminal itself; the terminal owner can check the results of the image matching performed by the server. Therefore, the image processing system according to this embodiment can appropriately support operations such as surveillance and customer service.

[0111] <Eleventh embodiment> Next, an eleventh embodiment of the present invention will be described. Fig. 19 shows an example of the configuration of an image processing system of this embodiment. The image processing system includes a terminal 10 having an image storage unit 101 and a transmission unit 104, and a server 20 having an image matching unit 201 and a transmission unit 202. The image storage unit 101, the image matching unit 201, and the transmission unit 202 are the same as those in the tenth embodiment, so their description will be omitted. A detailed description of the operation will be omitted as it overlaps with the tenth embodiment, but step S105 shown in Fig. 18 is different from the tenth embodiment.

[0112] In the tenth embodiment, the processing result of the image matching executed in the server 20 is presented to the terminal 10. In contrast, when a partial image is transmitted to the server 20 and image matching is performed, an observer or the like on the server 20 side may want to grasp not only the partial image but also the entire image including the partial image. Therefore, the transmitting unit 104 of this embodiment is similar to the transmitting unit 102 in that it transmits the partial image to the server 20, but then further transmits the entire image including the partial image identified by the ID received from the server 20 to the server 20 (step S105 in FIG. 20 ).

[0113] As a result, when the server 20 checks the partial image against the candidate image, the server 20 can issue a request to the terminal 10 to send the entire image including the partial image.

[0114] <Twelfth embodiment> Next, a twelfth embodiment of the present invention will be described. An image processing device 100 according to this embodiment includes an output unit 1001 (see FIG. 21).

[0115] An output unit 1001 outputs an image of an object region in an image captured by an imaging unit (not shown) if the value indicating the size of the object region is greater than a threshold value, and outputs an image of a predetermined region including the object region if the value is not greater than a threshold value. The output includes image display output to a display unit, output to an external device, etc.

[0116] Specifically, the image processing device 100 operates, for example, as follows. First, the image processing device 100 includes an imaging unit such as a camera (not shown), and the user of the image processing device 100 captures an image of the surroundings using the imaging unit. Furthermore, the image processing device 100 includes an object detection unit (not shown), which detects an object area from the image captured by the imaging unit. An object may be a person, a car, a product, a part of any of these, a printed portion thereon, or a sticker attached thereto. Here, it is assumed that the object is a person's face.

[0117] It is desirable that the size of the face image detected by the object detection unit is large enough to be able to be compared with a wanted photo, etc. Therefore, for example, as shown in (1) in Fig. 16, when the distance W1 between the eyes of a person's face, which is a value indicating the size of the object area, is larger than the threshold number of pixels TH1, the object detection unit cuts out the face image.

[0118] On the other hand, if the distance W2 between the eyes of a person's face is smaller than the number of pixels TH1, as shown in (2) of Figure 16, the object detection unit cuts out an image data area of ​​the size of the outline of the entire body of the person, which is a predetermined area including the face image.

[0119] Note that, in cases where the face size is within the threshold but there is a possibility that the facial features of the person cannot be sufficiently acquired, as in (1) shown in Fig. 16, the object detection unit may cut out an image data area that is larger than the outline of the entire body, as in (2) shown in Fig. 16. In such cases, the person may be wearing glasses or a mask.

[0120] As another example, a case where the object is an automobile license plate, as shown in (3) in FIG. 16, will be described. In this case, if the width W3 of the detected license plate is greater than the predetermined number of pixels TH1, the object detection unit cuts out the area of ​​the license plate as an image data area. On the other hand, if the width W4 of the license plate is smaller than the predetermined number of pixels TH1, as shown in (4) in FIG. 16, the object detection unit cuts out an image data area of ​​the outline of the entire car or a larger size. The output unit 1001 outputs the image cut out in this manner.

[0121] As another example, a case where the object is a product logo, as shown in Figure 22, will be described. Note that a logo is not limited to a trademark or trade mark, but also includes symbols, letters, figures, etc. that can distinguish the product from others. In this case, if the width D2 of the detected logo is greater than a predetermined number of pixels, the object detection unit cuts out the logo area as an image data area. On the other hand, if the width D2 of the logo is smaller than the predetermined number of pixels, as shown in Figure 22, the object detection unit cuts out an image data area that is the outline of the entire product or a larger size. The output unit 1001 outputs the image cut out in this manner.

[0122] According to this embodiment, image clipping can be used to avoid outputting unnecessary image areas, thereby enabling efficient image processing and providing appropriate business support.

[0123] The present invention is not limited to the above-described embodiment, and can also be described as follows, but is not limited thereto. (Appendix 1) an image storage means for storing an image and identification information of the image or a partial image of the image; a transmitting means for transmitting the identification information and the partial image to a server; a terminal including an output means for outputting additional information based on the identification information received from the server; an image matching means for matching the partial image received from the terminal with stored candidate images; a server including a transmitting means for transmitting the identification information corresponding to the matched image to the terminal; An image processing system comprising: (Appendix 2) The output means is an image display means for displaying an image, and displays information about a matching result as the additional information superimposed on the image. 2. The image processing system of claim 1. (Appendix 3) an image storage means for storing an image and identification information of the image or a partial image of the image; a terminal including a transmitting means for transmitting identification information of the image and a partial image of the image to a server, and transmitting the image identified by the identification information received from the server to the server; an image matching means for matching the partial image received from the terminal with stored candidate images; a server including a transmitting means for transmitting the identification information corresponding to the matched image to the terminal; An image processing system comprising: (Appendix 4) the partial image includes an object detected in the image; The identification information is position information of the object or time information when the image was acquired. 4. An image processing system according to any one of claims 1 to 3. (Appendix 5) The terminal an input means for specifying the detected object region; If a partial image including the object region designated by the input means is not matched with the candidate image, the partial image is stored in a database. 5. The image processing system of claim 4. (Appendix 6) the transmitting means of the server transmits an image designated from the candidate images to the terminal; The terminal includes an image processing unit that, when receiving the specified image, compares the image with the partial image. 6. An image processing system according to any one of Supplementary Notes 4 and 5. (Appendix 7) There are a plurality of the terminals, and when the partial image transmitted from at least one of the terminals to the server is verified by the image verification means, the server transmits the identification information corresponding to the verified image to a terminal other than the terminal. 7. An image processing system according to any one of claims 1 to 6. (Appendix 8) and an output means for outputting an image of the object region when a value indicating the size of the object region in the image captured by the imaging means is greater than a threshold value, and an image of a predetermined region including the object region when the value is not greater than a threshold value. Image processing device. (Appendix 9) The object region is a face region of a person, and the predetermined region is an image including the entire person. 9. The image processing device according to claim 8. (Appendix 10) The object region is a license plate of a car, and the predetermined region is an image including the entire car. 9. The image processing device according to claim 8. (Appendix 11) a terminal stores an image and identification information of the image or a partial image of the image, transmits the identification information and the partial image to a server, and outputs additional information based on the identification information received from the server; The server compares the partial image received from the terminal with stored candidate images, and transmits the identification information corresponding to the compared image to the terminal. Image processing methods. (Appendix 12) The terminal outputs the additional information to an image display means that displays an image, and displays information about the matching result as the additional information superimposed on the image. 12. The image processing method according to claim 11. (Appendix 13) a terminal stores an image and identification information of the image or a partial image of the image, transmits the identification information of the image and the partial image to a server, and transmits the image identified by the identification information received from the server to the server; The server compares the partial image received from the terminal with stored candidate images, and transmits the identification information corresponding to the compared image to the terminal. Image processing methods. (Appendix 14) the partial image includes an object detected in the image; The identification information is position information of the object or time information when the image was acquired. 14. An image processing method according to any one of appendices 11 to 13. (Appendix 15) The terminal Accepting designation of the detected object region via an input means for designating the object region, and if a partial image including the designated object region does not match with the candidate image, storing the partial image in a database. 15. The image processing method according to claim 14. (Appendix 16) the server transmits an image designated from the candidate images to the terminal; When the terminal receives the specified image, it compares the image with the partial image. 16. An image processing method according to any one of appendices 14 to 15. (Appendix 17) There are a plurality of the terminals, and when the partial image transmitted from at least one of the terminals to the server is verified, the server transmits the identification information corresponding to the verified image to a terminal other than the terminal. 17. An image processing method according to any one of appendices 11 to 16. (Appendix 18) If a value indicating the size of the object area of ​​the image captured by the imaging means is greater than a threshold, the terminal outputs an image of the object area, and if not, outputs an image of a predetermined area including the object area. Image processing methods. (Appendix 19) The object region is a face region of a person, and the predetermined region is an image including the entire person. 19. The image processing method of claim 18. (Appendix 20) The object region is a license plate of a car, and the predetermined region is an image including the entire car. 19. The image processing method of claim 18. (Appendix 21) The terminal includes an input means for specifying the detected object region, and a partial image including the object region specified by the input means is compared with the candidate image in priority over other partial images. 5. The image processing system of claim 4. (Appendix 22) The terminal receives a designation of the detected object area via an input means for designating the object area, and a partial image including the designated object area is compared with the candidate image with priority over other partial images. 15. The image processing method according to claim 14. (Appendix 23) A computer is caused to execute the image processing method according to any one of Supplementary Notes 18 to 20. Image processing program. Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. This application claims priority based on Japanese Patent Application No. 2014-070719, filed March 31, 2014, the disclosure of which is incorporated herein by reference in its entirety. [Explanation of symbols]

[0124] 1. First monitoring information terminal unit 2. First monitoring server 3 Second monitoring information terminal unit 4 Second monitoring server 5. Third monitoring information terminal unit 7. Fourth monitoring information terminal 8 Fifth Surveillance Information Terminal Unit 9. Communication Networks 11 Camera Section 12 Image Processing Section A 13 Image storage unit 14 Transmitting and receiving section A 15 Image display section 16 Input section 17 Image Processing C Section 21 Transmitting and Receiving Section B 22 Image Processing Section B 23 Database Department 24 Image display section 121 Image IO section 122 CPU section 123 Memory section 124 External IO section 10 devices 20 servers 101 Image storage unit 102 Transmitter 103 Output section 104 Transmitter 201 Image matching unit 202 Transmission Unit 1001 Output section

Claims

1. A video monitoring method using a camera terminal and a server, The camera terminal includes: determining that a surveillance image captured by the camera terminal includes a face, at least a portion of which meets a first size; generating a partial image by cutting out an area including the face from the surveillance image; transmitting the partial image to the server; The server receiving the partial images from at least one of the camera terminals; Matching the partial image with registered images stored in a database; Video surveillance methods.

2. extracting an area including a face, at least a part of which satisfies the first size, from the surveillance image, and generating the extracted area as the partial image; The video monitoring method according to claim 1 .

3. The video monitoring method according to claim 1 or 2, wherein the camera terminal transmits the partial image including the face, at least a part of which meets the first size, to the server.

4. The video monitoring method of claim 3, wherein when it is determined that the monitoring image includes a face, at least a portion of which meets the first size, the partial image including the face and having a predetermined second size is generated.

5. the first size is a size necessary for matching with data registered in the database, 5. The video monitoring method according to claim 4, wherein the required size is determined by the distance between the eyes of the face.

6. the first size has an upper limit and a lower limit; 5. The video monitoring method according to claim 4, further comprising determining whether the size of at least a part of a face is within a range indicated by said upper limit value and said lower limit value.

7. 5. The video monitoring method according to claim 4, wherein the predetermined second size is selected from two patterns.

8. an acquisition means for acquiring a monitoring image; a determining means for determining whether the surveillance image includes a face, at least a portion of which meets a first size; a generating means for generating a partial image by cutting out an area including the face from the surveillance image; a transmitting means for transmitting the partial image to a server; a camera terminal comprising: a receiving means for receiving the partial image from at least one of the camera terminals; a matching means for matching the partial image with a registered image stored in a database; The server comprising: Video surveillance system including.

9. the generating means extracts an area including a face, at least a part of which satisfies the first size, from the surveillance image, and generates the extracted area as the partial image; The video surveillance system according to claim 8.

10. A camera terminal capable of communicating with a server, an imaging means for capturing a monitoring image; a determining means for determining whether the surveillance image includes a face, at least a portion of which meets a first size; a generating means for generating a partial image by cutting out an area including the face from the surveillance image; a transmitting means for transmitting the partial image to a server; A video surveillance terminal comprising:

Images