Monitoring system, image-processing apparatus, management apparatus, event detecting method, and program

Abstract

A monitoring system includes a plurality of image-capturing apparatuses each including an event detector that executes on a corresponding captured image at least one of a plurality of processing algorithms for detection of a monitor event, and a transmission controller that outputs to a network only a processing result of the executed processing algorithm when a monitor event is not detected and that outputs to the network at least the captured image when a monitor event is detected; and a management apparatus managing the plurality of image-capturing apparatuses via the network and including an event determination unit that determines occurrence of a monitor event in accordance with the received processing result and a record controller that records the received captured image.

Claims

1. A camera system comprising: (1) an image-capturing apparatus including an event detector configured to process first event detection on a corresponding captured image for a first event and to detect a feature in the first event, a first receiver configured to receive a request for sending an image, and a transmitter configured to output to a network a processing result of the first event detection including position information that indicates position of an area corresponding to the feature detected in the first event and to output an image in response to the request for an image; and (2) a management apparatus including a second receiver configured to receive the processing result of the first event detection including the position information, from the image-capturing apparatus via the network, wherein the received processing result of the first event detection is not an image, an event determination unit configured to determine occurrence of a second event by processing the received processing result of the first event detection, and a request sending unit configured to send the request for sending an image corresponding to the second event when the second event occurs, to receive the captured image.

2. The camera system according to claim 1, further comprising: a non-transitory storage medium recording the captured image received via the network.

3. The camera system according to claim 1, further comprising: a display device displaying the captured image received via the network.

4. The camera system according to claim 1, wherein the position information is related to a detected moving object.

5. The camera system according to claim 1, wherein the processing result of the first event detection at the event detector includes information indicating existence of a non-moving object.

6. The camera system according to claim 5, wherein the event determination unit is further configured to determine a moving object in a set area that has not moved for a predetermined period of time.

7. A management apparatus comprising: a receiver configured to receive a processing result of a first event detection from an image-capturing apparatus via a network, the processing result including position information that indicates position of an area corresponding to a feature detected in the first event detection, wherein the received processing result of the first event detection is not an image, an event determination unit configured to determine occurrence of a second event by processing the received processing result of the first event detection, and a request sending unit configured to send a request for sending an image corresponding to the second event when the second event occurs, to receive a captured image.

8. The management apparatus according to claim 7, wherein the position information is related to a detected moving object.

9. The management apparatus according to claim 7, wherein the processing result of the first event detection at an event detector includes information indicating existence of a non-moving object.

10. The management apparatus according to claim 7, wherein the event determination unit is further configured to determine a moving object in a set area that has not moved for a predetermined period of time.

11. A method for detecting an occurrence of an event by a management apparatus comprising the steps of: receiving a processing result of a first event detection from an image-capturing apparatus via a network, the processing result including position information that indicates position of an area corresponding to a feature detected in the first event detection, wherein the received processing result of the first event detection is not an image; determining occurrence of a second event by processing the received processing result of the first event detection; and sending a request for sending an image corresponding to the second event when the second event occurs, to receive a captured image.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

(1) FIG. 1 shows an example of a known configuration of a security system;

(2) FIG. 2 shows an example of functional allocation for an image-capturing apparatus and a management apparatus according to a known technology;

(3) FIG. 3 shows an example of use of network bandwidth according to the known technology;

(4) FIG. 4 shows an example in which an apparatus manages image-capturing cameras according to the known technology;

(5) FIG. 5 shows an example of a system according to the known technology in which many image-capturing cameras are managed;

(6) FIG. 6 shows the relationship between the number of image-capturing cameras and the necessary number of management apparatuses when a system is configured using known apparatuses;

(7) FIG. 7 shows a security system according to an embodiment of the present invention;

(8) FIGS. 8A to 8E show an example of processing steps when intrusion of a moving body is detected;

(9) FIG. 9 shows an example of functional allocation for an image-capturing apparatus and a management apparatus according to the embodiment;

(10) FIG. 10 shows an example of use of network bandwidth according to the embodiment;

(11) FIG. 11 shows an example of the system according to the embodiment when many image-capturing cameras are managed;

(12) FIG. 12 shows the relationship between the number of image-capturing cameras and the necessary number of management apparatuses when the system is configured using the apparatuses according to the embodiment;

(13) FIG. 13 shows an example of a security system according to another embodiment of the present invention;

(14) FIG. 14 shows an example of a security system according to another embodiment of the present invention;

(15) FIG. 15 shows an example of processing steps when intrusion or installation of a non-moving body is detected;

(16) FIGS. 16A to 16E show processing results when a moving body makes intrusion; and

(17) FIGS. 17A to 17E show processing results when a non-moving body makes intrusion.

DESCRIPTION OF THE PREFERRED EMBODIMENTS

(18) Embodiments of the present invention will be described.

(19) Well-known technologies in the technical field of the present invention are applied to portions not illustrated or described in this specification.

(20) The embodiments given below are merely examples, and the present invention is not limited to the embodiments.

First Embodiment

(21) FIG. 7 shows an example of the configuration of a monitoring system when applied to a security system. In FIG. 7, parts corresponding to parts in FIG. 1 are referred to with the same reference numerals.

(22) The security system includes an image-capturing camera 111 and a management apparatus 131 that manages the image-capturing camera 111. A display device 5 is externally connected to the management apparatus 131.

(23) The image-capturing camera 111 includes an image-capturing element 11, a camera signal processor 13, a CPU 15, an image compressor 17, a network processor 19, and an event detector 113.

(24) The image-capturing element 11 includes a solid-state image-capturing element, such as a charge-coupled device (CCD) sensor or a complementary metal-oxide semiconductor (CMOS) sensor. The camera signal processor 13 is a processing device that performs signal amplification processing, analog/digital conversion processing, exposure control processing, and other processing necessary for converting a captured image into a video signal.

(25) The CPU 15 is a control device that controls processing operations of the entire image-capturing camera 111. For example, the CPU 15 includes a microprocessor. The CPU 15 also functions as a transmission controller that selects data to be output to a network.

(26) The image compressor 17 is a processing device that compresses and encodes a captured image to be output to the network.

(27) The network processor 19 is a communication device that performs data transmission and reception via the network.

(28) The event detector 113 is a processing device that performs image processing on image data captured by the image-capturing element 11 and that detects occurrence of a monitor event. A process for detecting a monitor event is achieved by performing a plurality of processing steps in accordance with a detection purpose and a processing detail.

(29) FIGS. 8A to 8E show an example of processing steps when a monitor event indicates intrusion of a moving body into a set area. In this case, the detection process includes motion detection processing (FIG. 8B), region integration processing (FIG. 8C), labeling processing (FIG. 8D), and region determination processing (FIG. 8E).

(30) In the motion detection processing, motion vectors in a captured image (FIG. 8A) are detected.

(31) In the region integration processing, regions including detected motion vectors are integrated together for each moving body. In this processing, a size S and coordinates (x,y) of each integrated region are acquired.

(32) In the labeling processing, a label is provided to each integrated region.

(33) In the region determination processing, it is determined where on the screen each region provided with a label is located.

(34) By performing the above-described processing, intrusion or non-intrusion of a moving body and the position into which the moving body intrudes can be acquired.

(35) In this embodiment, when intrusion of a moving body is detected, the CPU 15, which serves as the transmission controller, gives an instruction to output to the network a captured image and a processing result acquired by the moving body detection process. In contrast, when intrusion of a moving body is not detected, the CPU 15, which serves as the transmission controller, gives an instruction to output to the network only a processing result acquired by the moving body detection process. That is, the CPU 15 transmits a captured image only in a case where a captured image to be recorded is generated. In other cases, the CPU 15 transmits only the current detection result.

(36) In contrast, the management apparatus 131 includes a network processor 31, a CPU 33, a display controller 35, an image decompressor 37, a disk controller 41, a hard disk device 43, and an event determination unit 133.

(37) The network processor 31 is a communication device that performs data transmission and reception via the network.

(38) The CPU 33 is a control device that controls processing operations of the entire management apparatus 131. For example, the CPU 33 includes a microprocessor. The CPU 33 also functions as a record controller that gives an instruction to record to the hard disk device 43 a captured image received via the network.

(39) The display controller 35 is a data processor that outputs to the display device 5 security conditions and a captured image received from the containing image-capturing camera 111.

(40) The image decompressor 37 is a decoder that releases compression and encoding processing on a captured image in order to recover the original image.

(41) The disk controller 41 is a controller that controls the hard disk device 43 to record and play back data including a captured image.

(42) The event determination unit 133 is a processing device that determines whether or not a monitor event received via the network occurs. The event determination unit 133 performs the processing on a processing result acquired by the moving body detection process. Thus, even if the management apparatus 131 manages many image-capturing cameras 111, the event determination unit 133 handles only a small processing load. In this embodiment, the event determination unit 133 sends out an alert when a moving body makes intrusion.

(43) FIG. 9 shows an example of function allocation of processing algorithms for moving body detection. Referring to FIG. 9, the image-capturing camera 111 performs processing from image capture to transfer of a motion detection result (processing result) to a network. The management apparatus 131 performs a series of processes from determination of the received processing result to alert execution.

(44) Thus, since the image-capturing camera 111 performs the motion detection processing, this security system is capable of minimizing the occupied bandwidth during a normal period.

(45) Parts (a) and (b) of FIG. 10 show examples of use of network bandwidth. Part (a) of FIG. 10 shows an example of use of bandwidth during a period (normal period) in which intrusion of a moving body is not detected. Part (b) of FIG. 10 shows an example of use of bandwidth during a period (alert period) after intrusion of a moving body is detected.

(46) As shown in parts (a) and (b) of FIG. 10, in the security system shown in FIG. 7, during a period in which intrusion of a moving body is not detected, the occupied bandwidth can be reduced to about several kbps even if the management apparatus 131 manages four image-capturing cameras 111. In addition, in any cases other than a case where all the four image-capturing cameras 111 detect intrusion of moving bodies, the occupied bandwidth of the network can be reduced compared with a case where an existing security system is used.

(47) Moreover, since the processing load of the management apparatus 131 can be dramatically reduced, the single management apparatus 131 is capable of managing many image-capturing cameras 111. Thus, an increase or decrease in the number of image-capturing cameras can be easily achieved. Therefore, a system can be flexibly changed even after system operation.

(48) FIG. 12 shows the relationship between the number of image-capturing cameras 111 and the necessary number of management apparatuses 131. As shown in FIG. 12, an increase in the number of the management apparatuses 131 can be suppressed with respect to an increase in the number of the image-capturing cameras 111.

Other Embodiments

(49) In the first embodiment, a case where the image-capturing camera 111 includes the event detector 113 is described. That is, a configuration of a product in which the event detector 113 is mounted or installed in the image-capturing camera 111 is described.

(50) However, the configuration of an apparatus on an image capture side is not limited to this. For example, the event detector 113 may be installed in an image-processing apparatus that is independent of an image-capturing apparatus. In this case, the image-processing apparatus is provided with a function of communicating with the network.

(51) FIG. 13 shows another example of the configuration of the monitoring system. In FIG. 13, parts corresponding to parts in FIG. 7 are referred to with the same reference numerals.

(52) The monitoring system shown in FIG. 13 includes an image-capturing camera 141, an image-processing apparatus 151, and a management apparatus 131. Since each device within the apparatuses is similar to that in the first embodiment, the description of the device will be omitted. In this system configuration, since a captured image (image data) is distributed on the network only when a moving body is detected, advantages similar to those in the first embodiment can be achieved.

(53) Although the configuration of an image-capturing camera is described in the foregoing embodiments, the monitoring system can be established using an image-processing apparatus 161 of any type having a function other than the image-capturing function.

(54) For example, the monitoring system can be established using a portable information terminal, such as a cellular phone or a mobile information terminal, or a robot, such as a humanoid robot or animal robot.

(55) FIG. 14 shows an example of the configuration of a monitoring system of this type. In FIG. 14, parts corresponding to parts in FIG. 7 are referred to with the same reference numerals.

(56) In the monitoring system shown in FIG. 14, the image-processing apparatus 161 including the image-capturing element 11 performs a process for detecting a monitor event, and transmits a processing result to the management apparatus 131 via the network. In this case, advantages similar to those in the foregoing embodiments can be achieved.

(57) Although a case where intrusion of a moving body is detected as a monitor event is described in the foregoing embodiments, the monitor event does not necessarily indicate intrusion of a moving body.

(58) For example, the present invention can also be applied to a case where intrusion or installation of a non-moving body into a set area is detected as a monitor event.

(59) FIG. 15 shows an example of a process performed by the event detector 113 for detecting a non-moving body. In this case, the event detector 113 performs processing for detecting motion (step S1), processing for performing region integration (step S2), processing for determining a static region (step S3), processing for performing labeling (step S4), and processing for determining a region (step S5).

(60) The processing steps other than the processing step of determining a static region can be realized by processing steps similar to those for the moving body detection process. In the processing for determining a static region, it is determined whether or not a region that is identified as a moving body at a point in time is kept stationary at a position for a predetermined period of time. Labeling is performed only on a region whose static state is confirmed, and detection is not performed on a region whose static state is not confirmed.

(61) FIGS. 16A to 16E show processing results corresponding to screens on which captured images of a vehicle traversing the screen are displayed. The vehicle is detected as a moving body at a point in time when the vehicle intrudes into an image capture range, and the vehicle traverses the screen. Thus, the vehicle is not detected as a non-moving body.

(62) FIGS. 17A to 17E show processing results corresponding to screens on which captured images of a vehicle stopping or parking in the screen are displayed.

(63) At a point in time when the vehicle intrudes into an image capture range, the vehicle is detected as a moving body. Then, after the vehicle stops moving and stands still at a place in the screen, the vehicle is detected as a non-moving body.

(64) The processing results shown in FIGS. 17A to 17E indicate the sizes S, coordinates (x,y), and times t of integrated regions.

(65) A case where the event detector 113 performs the entire detection process is described in the foregoing embodiments. That is, a case where, in a moving body detection process, all the motion detection processing (FIG. 8B), the region integration processing (FIG. 8C), the labeling processing (FIG. 8D), and the region determination processing (FIG. 8E) are executed in the event detector 113 is described in the foregoing embodiments.

(66) However, a procedure in which the event detector 113 performs only some of processing functions of the processing algorithms and in which the management apparatus 131 (the event determination unit 133) performs the other processing functions can be adopted. For example, the event detector 113 may perform processes until the region integration processing and may transmit the processing results to the management apparatus 131 via the network, and the management apparatus 131 may perform the labeling processing and the region determination processing. In this case, the occupied bandwidth can be significantly reduced compared with a case where a captured image is distributed on the network.

(67) In addition, since a large load is not necessary for the labeling processing and the region determination processing, many image-capturing cameras can be managed by a management apparatus without any trouble.

(68) In this case, a procedure in which the management apparatus instructs the image-capturing apparatus to transmit a captured image in accordance with detection of a monitor event can be adopted.

(69) The event detector 113 may autonomously determine transmission of a captured image within a range determined from a result of processing performed by the event detector 113.

(70) Descriptions are mostly focused on a security system in the foregoing embodiments.

(71) However, the present invention can also be applied to an industrial camera system, a video convention system, a remote camera system (for talks, lectures, and other educational subjects, chamber photography, and event photography), and other monitoring systems as long as the system is used for recording a captured image and for sending out an alert only when a particular monitor event is detected.

(72) Although a case where a process for detecting a monitor event is realized in terms of hardware is described in the foregoing embodiments, such a process can be realized as software processing. In this case, a program may be distributed via a network or distributed by being stored on a storage medium. The storage medium used for distribution may be a magnetic storage medium, an optical storage medium, a semiconductor storage medium, or the like.

(73) Various modifications can be made to the present invention without departing from the scope of the present invention. In addition, various modifications and applications can be created or combined in accordance with the descriptions in this specification.

(74) It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and alterations may occur depending on design requirements and other factors insofar as they are within the scope of the appended claims or the equivalents thereof.