Disaster Prevention System
The disaster prevention system reduces processing load and improves fire detection accuracy by performing image processing only on abnormal areas and confirming fire with both smoke and flame detection.
Patent Information
- Application Number
- JP2020207566
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2020-12-15
- Publication Date
- 2024-12-04
- Estimated Expiration
- 2040-12-15
AI Technical Summary
Existing fire detection methods using surveillance camera images face high processing loads and inaccuracies due to false alarms from smoke or flame detection alone.
A disaster prevention system that performs image processing only on images where abnormalities are detected, combining smoke detection by a second image processing device with flame detection by a fire detector to confirm fire occurrence.
Accurately detects fires with reduced processing load and increased accuracy by limiting image processing to abnormal areas and requiring both smoke and flame detection.
Smart Images

Figure 0007594425000001 
Figure 0007594425000002 
Figure 0007594425000003
Abstract
Description
[Technical field]
[0001] The present invention relates to a disaster prevention system. [Background technology]
[0002] There is technology for detecting fires using images captured by surveillance cameras (eg, Patent Documents 1 to 3). [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Patent No. 5697587 [Patent Document 2] Japanese Patent Application Publication No. 6-290389 [Patent Document 3] JP 2020-126439 A Summary of the Invention [Problem to be solved by the invention]
[0004] One method for detecting fires is to apply image processing to images captured by surveillance cameras to detect smoke. However, constantly applying image processing to images captured by surveillance cameras to detect smoke places a heavy processing load. Also, when detecting fires using flame detection methods or smoke detection methods alone, there is a possibility that a fire will be falsely detected even when no fire has occurred.
[0005] An object of the present invention is to detect fires with high accuracy and with a small processing load. [Means for solving the problem]
[0006] One aspect of the present invention provides a disaster prevention system that includes an image processing device that detects smoke by applying image processing to images taken by a surveillance camera installed at a fire prevention object when an abnormality is detected at the fire prevention object, a fire detector that detects flames, and a disaster prevention control panel that determines that a fire has occurred when both the flame and the smoke are detected.
[0007] The image processing device may apply the image processing only to images taken of the location where the abnormality was detected, out of multiple images taken by multiple surveillance cameras installed at the fire prevention object.
[0008] The disaster prevention control panel may provide a different notification to the monitoring device depending on whether it is determined that a fire has occurred or whether the smoke is detected but the flames are not detected. Effect of the Invention
[0009] According to the present invention, fires can be detected with high accuracy and with a small processing load. [Brief description of the drawings]
[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of an overview of a disaster prevention system. [Diagram 2] FIG. 2 illustrates an example of a configuration of a second image processing device. [Diagram 3] FIG. 2 is a diagram illustrating an example of a configuration of a disaster prevention receiving panel. [Figure 4] 1 is a sequence chart showing an example of an operation of the disaster prevention system. [Diagram 5] FIG. 13 illustrates an example of an abnormality. [Figure 6] FIG. 13 is a diagram showing an example of a correspondence table according to a modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0011] FIG. 1 is a diagram showing an example of an outline of a disaster prevention system 10 according to an embodiment. The disaster prevention system 10 is a system for quickly discovering a disaster and minimizing damage caused by the disaster. The disaster prevention system 10 includes a CCTV (Closed-Circuit Television) facility 100, an emergency facility 200, and a remote monitoring device 300. The CCTV facility 100 and the emergency facility 200 are installed in, for example, a tunnel. The tunnel is an example of a fire prevention object according to the present invention. The remote monitoring device 300 is installed in, for example, a monitoring center. The CCTV facility 100 and the remote monitoring device 300 are connected via a signal line 51. The CCTV facility 100 and the emergency facility 200 are connected via a signal line 52. The emergency facility 200 and the remote monitoring device 300 are connected via a signal line 53.
[0012] The CCTV equipment 100 is equipment for monitoring road conditions. The CCTV equipment 100 includes multiple surveillance cameras 110 and a first image processing device 120. The first image processing device 120 and the multiple surveillance cameras 110 are connected via a signal line 54.
[0013] The surveillance cameras 110 are placed, for example, at a predetermined interval above a tunnel, and capture images of the road to monitor the road conditions inside the tunnel. The images referred to here are images in digital format, that is, image data. These images are, for example, moving images captured at a predetermined frame rate. However, these images are not necessarily limited to moving images, and may be still images captured repeatedly at a predetermined time interval.
[0014] The first image processing device 120 detects traffic abnormalities by applying image processing to the images captured by the surveillance camera 110. The abnormalities include stopped vehicles. The abnormalities may include events such as low speed, traffic jams, wrong-way driving, and avoidance. Low speed refers to a vehicle traveling at or below a predetermined speed. Avoidance refers to a vehicle traveling outside its original lane to avoid an obstacle. As an image processing method for detecting abnormalities, for example, a method is available in which a known image processing technique is used to detect a moving object such as a vehicle from an image, track the same moving object between image frames, and determine whether the behavior of each moving object is abnormal.
[0015] The CCTV equipment 100 distributes images captured by the monitoring camera 110 to the remote monitoring device 300 and the emergency equipment 200. This distribution may be, for example, real-time streaming distribution. Furthermore, when an abnormality is detected by the first image processing device 120, the CCTV equipment 100 transmits an abnormality signal to the remote monitoring device 300 and the emergency equipment 200.
[0016] The emergency equipment 200 is equipment used when an emergency such as a fire occurs. The emergency equipment 200 includes a plurality of fire detectors 210, a second image processing device 220, and a disaster prevention receiving panel 230. The disaster prevention receiving panel 230 and the plurality of fire detectors 210 are connected via a signal line 55. The disaster prevention receiving panel 230 and the second image processing device 220 are connected via a signal line 56. Note that FIG. 1 mainly shows a configuration related to determining a fire by detecting flames and smoke, and other configurations are omitted.
[0017] The fire detector 210 detects a flame and transmits a fire signal to the disaster prevention receiving panel 230. The fire detector 210 detects a flame by using, for example, a detection principle called a two-wavelength flickering method. However, the method by which the fire detector 210 detects a flame is not limited to the two-wavelength flickering method, and other methods may be used.
[0018] 2 is a diagram showing an example of the configuration of the second image processing device 220. The second image processing device 220 detects smoke by applying image processing to the image captured by the surveillance camera 110, and transmits a smoke detection signal to the disaster prevention receiving panel 230. The second image processing device 220 is an example of an image processing device according to the present invention.
[0019] The second image processing device 220 includes a control unit 221, a storage unit 222, and a communication unit 223. The control unit 221 is also called a processor, and controls each unit of the second image processing device 220 and performs various processes. The control unit 221 includes, for example, a CPU (Central Processing Unit). The storage unit 222 is also called a memory, and stores various data and programs. The storage unit 222 includes, for example, at least one of a ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Erasable Programmable ROM), and a RAM (Random Access Memory). The storage unit 222 stores a program for realizing the functions of the second image processing device 220. The communication unit 223 is a communication interface for connecting the second image processing device 220 to a signal line 56. The communication unit 223 is used to communicate with other devices connected via the signal line 56.
[0020] The control unit 221 functions as an image processing means 225, a determination means 226, and a transmission means 227. These functions are realized by the control unit 221 executing a program stored in the storage unit 222, and the control unit 221 performing calculations or controlling each unit of the second image processing device 220. When the first image processing device 120 detects an abnormality from an image taken by the surveillance camera 110, the image processing means 225 performs image processing for detecting smoke on the image. That is, the image processing means 225 does not perform image processing for detecting smoke during a period in which the first image processing device 120 does not detect an abnormality from an image taken by the surveillance camera 110. The reason why image processing for detecting smoke is performed when an abnormality is detected is because there is a possibility that a fire may break out when an abnormality such as a vehicle stop occurs. For example, the technology described in JP 2010-97412 A is used for detecting smoke from an image. For example, the image processing means 225 detects smoke by comparing a reference image under normal circumstances when no abnormality is detected with an image in which an abnormality is detected. The determination means 226 determines whether or not smoke has been detected by the image processing performed by the image processing means 225. The transmission means 227 transmits a smoke detection signal to the disaster prevention receiving panel 230 when the determination means 226 determines that smoke has been detected.
[0021] Fig. 3 is a diagram showing an example of the configuration of the disaster prevention receiving panel 230. The disaster prevention receiving panel 230 determines whether or not a fire has occurred based on the detection results of the first image processing device 120, the fire detector 210, and the second image processing device 220, and notifies the result. The disaster prevention receiving panel 230 is an example of a disaster prevention control panel according to the present invention. Note that Fig. 3 mainly shows the configuration related to fire determination and notification, and other configurations are omitted.
[0022] The disaster prevention receiving panel 230 includes a control unit 231, a storage unit 232, a communication unit 233, and a display unit 234. The control unit 231, the storage unit 232, and the communication unit 233 are the same as the control unit 221, the storage unit 222, and the communication unit 223 described above. However, the storage unit 232 stores a program for realizing the functions of the disaster prevention receiving panel 230. The communication unit 233 is a communication interface for connecting the disaster prevention receiving panel 230 to the signal lines 52, 53, 55, and 56. The communication unit 233 is used to communicate with other devices connected via the signal lines 52, 53, 55, or 56. The display unit 234 displays various information. The display unit 234 includes, for example, a liquid crystal display.
[0023] The control unit 231 functions as a transfer means 235, a decision means 236, and a notification means 237. These functions are realized by the control unit 231 executing a program stored in the storage unit 232, and the control unit 231 performing calculations or controlling each unit of the disaster prevention receiving panel 230. The transfer means 235 transfers the image received from the CCTV equipment 100 to the second image processing device 220. The decision means 236 decides whether or not a fire has occurred according to the detection results of the first image processing device 120, the fire detector 210, and the second image processing device 220. For example, when a flame is detected by the fire detector 210 and smoke is detected by the second image processing device 220 from an image in which an abnormality is detected by the first image processing device 120, the decision means 236 decides that a fire has occurred. When the decision means 236 decides that a fire has occurred, the notification means 237 notifies the notification destination including the remote monitoring device 300 that the occurrence of a fire has been confirmed. Furthermore, even if the determination means 236 does not determine that a fire has occurred, when smoke is detected by the second image processing device 220, the notification means 237 may notify the notification destinations including the remote monitoring device 300 that smoke has been detected. When it is not determined that a fire has occurred, a notification different from that when it is determined that a fire has occurred is performed.
[0024] Returning to Fig. 1, the remote monitoring device 300 is used by a monitor at a monitoring center to remotely monitor the location where the CCTV equipment 100 and the emergency equipment 200 are installed. The remote monitoring device 300 displays, for example, images captured by the monitoring camera 110 and information notified from the disaster prevention receiving panel 230. The monitor quickly finds and deals with abnormalities such as fires by checking the images captured by the monitoring camera 110 and information notified from the disaster prevention receiving panel 230. The remote monitoring device 300 is an example of a monitoring device according to the present invention.
[0025] FIG. 4 is a sequence chart showing an example of the operation of the disaster prevention system 10. Here, the surveillance camera 110 always photographs the road, and the first image processing device 120 sequentially performs image processing for detecting abnormalities on the images photographed by the surveillance camera 110. In addition, the images photographed by the surveillance camera 110 are distributed in real time from the CCTV facility 100 to the disaster prevention receiving panel 230, and the disaster prevention receiving panel 230 sequentially transfers the images received from the CCTV facility 100 to the second image processing device 220. The second image processing device 220 stores images in normal times distributed from the CCTV facility 100 as reference images every few days in the storage unit 222 during a period when no abnormality is detected by the first image processing device 120. Note that images not used as reference images among the images distributed from the CCTV facility 100 may be deleted.
[0026] In step S11, the first image processing device 120 of the CCTV equipment 100 detects an abnormality by performing image processing on the image captured by the surveillance camera 110. Fig. 5 is a diagram showing an example of an abnormality. For example, as shown in Fig. 5, when a stopped vehicle exists on a road included in the capture range of the surveillance camera 110A, the stopped vehicle is detected from the image captured by the surveillance camera 110A.
[0027] In step S12, the CCTV equipment 100 transmits an abnormality signal indicating that an abnormality has been detected and an image in which the abnormality has been detected to the remote monitoring device 300. In step S13, the CCTV equipment 100 transmits an abnormality signal indicating that an abnormality has been detected and an image in which the abnormality has been detected to the disaster prevention receiving panel 230. The image in which the abnormality has been detected is an image in which the location in which the abnormality has been detected is captured. The image in which the abnormality has been detected also includes an identifier of the monitoring camera 110 that captured the image. For example, as shown in FIG. 5, when a stopped vehicle is detected from an image captured by the monitoring camera 110A, an image obtained by extracting a portion of the image captured by the monitoring camera 110A within a range of a predetermined time before and after the time when the abnormality was detected is used as the image in which the abnormality has been detected. This image includes "CM-A", which is the identifier of the monitoring camera 110A. In step S14, the transfer means 235 of the disaster prevention receiving panel 230 transfers the abnormality signal received from the CCTV equipment 100 and the image in which the abnormality is detected to the second image processing device 220.
[0028] Also, when a flame occurs near the location where the abnormality has occurred, in step S15, the fire detector 210, which includes this location in its detection range, detects the flame. For example, as shown in FIG. 5, when a stopped vehicle is included in the detection range of the fire detector 210A, if a flame occurs near the stopped vehicle, the fire detector 210A detects the flame. In step S16, the fire detector 210 transmits a fire signal indicating that a flame has been detected to the disaster prevention receiving panel 230. In step S17, when the fire signal is received from the fire detector 210, the notification means 237 of the disaster prevention receiving panel 230 notifies the surroundings of the disaster prevention receiving panel 230 and the remote monitoring device 300 that a fire has been detected. For example, the notification means 237 displays information indicating that a fire has been detected on the display unit 234, and transmits a fire detection signal indicating that a fire has been detected to the remote monitoring device 300. Note that the processes of steps S15 to S17 are not necessarily performed after the process of step S11. For example, if a flame is detected before an abnormality is detected, the processes of steps S15 to S17 are performed before the process of step S11.
[0029] In step S18, when the image processing means 225 of the second image processing device 220 receives an abnormality signal and an image in which an abnormality is detected from the disaster prevention receiving panel 230, the image processing means 225 performs image processing for detecting smoke on the image. For example, as shown in FIG. 5, when a stopped vehicle is detected from an image taken by the monitoring camera 110A and this image is received from the disaster prevention receiving panel 230, the image processing means 225 performs image processing for detecting smoke on the image. Note that image processing for detecting smoke is not performed on images taken by the monitoring cameras 110 other than the monitoring camera 110A. In step S19, the determination means 226 of the second image processing device 220 determines whether or not smoke is detected by image processing. For example, as shown in FIG. 5, when smoke is coming out of a stopped vehicle, smoke is detected by image processing. When smoke is detected by image processing in this way (determination of step S19 is YES), the second image processing device 220 proceeds to step S20. On the other hand, if smoke is not detected by image processing (determination in step S19 is NO), the subsequent processes are not performed. In step S20, the transmission means 227 of the second image processing device 220 transmits a smoke detection signal indicating that smoke has been detected to the disaster prevention receiving panel 230. In step S21, upon receiving the smoke detection signal from the second image processing device 220, the notification means 237 of the disaster prevention receiving panel 230 notifies the surroundings of the disaster prevention receiving panel 230 and the remote monitoring device 300 that smoke has been detected. For example, the notification means 237 displays information indicating that smoke has been detected on the display unit 234, and transmits a smoke detection signal indicating that smoke has been detected to the remote monitoring device 300.
[0030] In step S22, the determination means 236 of the disaster prevention receiving panel 230 determines whether or not a fire has occurred depending on whether or not a fire signal and a smoke detection signal have been received. For example, when a smoke detection signal is received from the second image processing device 220 and a fire signal is received from the fire detector 210, it is determined that a fire has occurred, since this indicates that a fire and smoke are occurring from the location where an abnormality has occurred. On the other hand, when a smoke detection signal is received from the second image processing device 220 but no fire signal is received from any of the fire detectors 210 within a predetermined time, it is not determined that a fire has occurred, since this indicates that smoke is occurring from the location where an abnormality has occurred but no fire is occurring.
[0031] In step S23, when it is determined in step S22 that a fire has occurred, the notification means 237 of the disaster prevention receiving panel 230 notifies the surroundings of the disaster prevention receiving panel 230 and the remote monitoring device 300 that a fire has occurred. For example, the notification means 237 displays information indicating that a fire has occurred on the display unit 234, and transmits a fire confirmation signal indicating that a fire has occurred to the remote monitoring device 300. Note that, when it is not determined in step S22 that a fire has occurred, the notification in step S23 is not performed. That is, when it is determined that a fire has occurred, three notifications are performed: a notification in step S17 indicating that a fire has been detected, a notification in step S21 indicating that smoke has been detected, and a notification in step S23 indicating that a fire has been confirmed. However, when it is not determined that a fire has occurred, only the notification in step S17 indicating that a fire has been detected and the notification in step S21 indicating that smoke has been detected are performed, and the notification in step S23 indicating that a fire has been confirmed is not performed. In this way, different notifications are performed when a fire has occurred and when it has not occurred.
[0032] According to the embodiment described above, only when an abnormality is detected from an image captured by the surveillance camera 110, image processing for detecting smoke is performed on this image, so the load of image processing is smaller than when this image processing is always performed on images captured by the surveillance camera 110. Also, since image processing for detecting smoke is performed only on images in which an abnormality is detected among a plurality of images captured by a plurality of surveillance cameras 110, the load of image processing is smaller than when this image processing is performed on all images captured by the plurality of surveillance cameras 110. Furthermore, since the occurrence of a fire is confirmed only when both smoke and flame are detected, the accuracy of determining the occurrence of a fire is higher than when it is determined that a fire has occurred when either smoke or flame is detected. Furthermore, in some fires, only smoke occurs first from the location where an abnormality has occurred, and flame occurs later. Even in such a case, since the detection of smoke is notified at the time of smoke occurrence, such fires can also be detected early. Furthermore, since smoke is detected using the surveillance camera 110 included in the existing CCTV equipment 100, the cost required for building the system can be reduced compared to when a new camera dedicated to smoke detection is provided.
[0033] Variations The present invention is not limited to the above-described embodiment. The above-described embodiment may be modified as in the following modified examples. The embodiment and the modified examples may be used in combination, or may be switched depending on the implementation. Similarly, the following modified examples may be used in combination, or may be switched depending on the implementation.
[0034] In the above-described embodiment, the determination means 236 of the disaster prevention receiving panel 230 may determine that a fire has occurred only when a flame is detected by the fire detector 210, smoke is detected by the second image processing device 220 from the image in which an abnormality is detected by the first image processing device 120, and the shooting range of the monitoring camera 110 that captured the image in which the abnormality was detected overlaps with the detection range of the fire detector 210 that detected the fire. That is, even if a flame is detected by the fire detector 210 and smoke is detected by the second image processing device 220 from the image in which an abnormality is detected by the first image processing device 120, the determination means 236 does not determine that a fire has occurred if the shooting range of the monitoring camera 110 that captured the image in which the abnormality was detected does not overlap with the detection range of the fire detector 210 that detected the fire. This is because, if the shooting range of the surveillance camera 110 that captured the image in which the abnormality was detected does not overlap with the detection range of the fire detector 210 that detected the fire, the abnormality detected in the image captured by the surveillance camera 110 is considered to be a different event from the fire detected by the fire detector 210, and therefore, even if these events occur at the same time, it cannot necessarily be said that a fire has definitely occurred.
[0035] In this modification, for example, a correspondence table 240 is stored in the storage unit 232 of the disaster prevention receiving panel 230. The correspondence table 240 shows the correspondence between each monitoring camera 110 and a fire detector 210 having a detection range that overlaps with the shooting range of the monitoring camera 110. FIG. 6 is a diagram showing an example of the correspondence table 240 according to this modification. The correspondence table 240 includes an identifier that uniquely identifies the monitoring camera 110 and an identifier that uniquely identifies the fire detector 210. The identifier of each monitoring camera 110 is previously associated with the identifier of the fire detector 210 having a detection range that overlaps with the shooting range of the monitoring camera 110. In the example shown in FIG. 6, the identifier "CM-A" of the monitoring camera 110A is associated with the identifier "FD-A" of the fire detector 210A. 6, the identifier of one fire detector 210 is associated with the identifier of one surveillance camera 110, but the identifiers of multiple fire detectors 210 may be associated with the identifier of one surveillance camera 110, or the identifier of one fire detector 210 may be associated with the identifiers of multiple surveillance cameras 110. In this modification, the fire signal includes the identifier of the fire detector 210 that detected the flame. For example, as shown in FIG. 5, when a flame occurs within the detection range of the fire detector 210A and the flame is detected by the fire detector 210A, the fire signal includes "FD-A", which is the identifier of the fire detector 210A.
[0036] Here, it is assumed that a flame is detected by the fire detector 210 and smoke is detected by the second image processing device 220 from an image in which an abnormality is detected by the first image processing device 120. For example, when the image received from the CCTV equipment 100 includes "CM-A" which is the identifier of the monitoring camera 110A, the determination means 236 judges whether or not the identifier of the fire detector 210 included in the fire signal received from the fire detector 210 is "FD-A" which is associated with the identifier of the monitoring camera 110A "CM-A" in the correspondence table 240. When the identifier of the fire detector 210 included in the fire signal is "FD-A", the determination means 236 determines that a fire has occurred. On the other hand, when the identifier of the fire detector 210 included in the fire signal is not "FD-A", the determination means 236 does not determine that a fire has occurred. According to this modified example, the accuracy of determining the occurrence of a fire is further improved.
[0037] In the above-described embodiment, the trigger for the second image processing device 220 to perform image processing for detecting smoke is not limited to the detection of an abnormality by the first image processing device 120. For example, the second image processing device 220 may perform image processing for detecting smoke when the fire detector 210 detects a fire. This fire detection is also included in the detection of an abnormality according to the present invention. In this modified example, when the transfer means 235 of the disaster prevention receiving panel 230 receives a fire signal from the fire detector 210, it transfers the fire signal to the second image processing device 220. The fire signal includes the identifier of the fire detector 210 that detected the fire and the time when the fire was detected. For example, as shown in FIG. 5, when a fire occurs in the detection range of the fire detector 210A and the fire is detected by the fire detector 210A, the fire signal includes "FD-A", which is the identifier of the fire detector 210A. In addition, the disaster prevention receiving panel 230 identifies the surveillance camera 110 that captures the location where the fire was detected, and notifies the second image processing device 220. For example, the memory unit 232 of the disaster prevention receiving panel 230 stores the correspondence table 240 shown in Fig. 6. The disaster prevention receiving panel 230 identifies the identifier of the monitoring camera 110 associated with the identifier of the fire detector 210 included in the fire signal, and transmits the identified identifier of the monitoring camera 110 to the second image processing device 220. For example, as shown in Fig. 5, when the detection range of the fire detector 210A and the imaging range of the monitoring camera 110A overlap, the identifier "FD-A" of the fire detector 210A and the identifier "CM-A" of the monitoring camera 110A are associated with each other as shown in Fig. 6, so that the identifier "CM-A" of the monitoring camera 110A is identified and transmitted to the second image processing device 220.
[0038] The second image processing device 220 stores a plurality of images taken and distributed by a plurality of monitoring cameras 110 in the storage unit 222 for a predetermined period of time. The second image processing device 220 selects an image taken by a monitoring camera 110 identified by an identifier received from the disaster prevention receiving panel 230 from among the images stored in the storage unit 222, and further extracts a portion of the selected image within a predetermined time range before and after the time when the flame was detected. The image processing means 225 of the second image processing device 220 performs image processing for detecting smoke on the extracted image. At this time, the image processing means 225 does not perform image processing on images taken by monitoring cameras 110 other than the monitoring camera 110 identified by the identifier received from the disaster prevention receiving panel 230. The determination means 236 of the disaster prevention receiving panel 230 determines that a fire has occurred when the second image processing device 220 detects smoke from an image taken of a place where a flame was detected by the fire detector 210. Alternatively, the determination means 236 may determine that a fire has occurred when smoke is detected by the second image processing device 220 from an image taken of the location where a flame was detected by the fire detector 210, and an abnormality is detected by the first image processing device 120.
[0039] According to this modification, image processing for detecting smoke is applied to the image captured by the surveillance camera 110 only when a flame is detected by the fire detector 210, so the load of image processing is lighter than when this image processing is always applied to the images captured by the surveillance camera 110. Also, image processing for detecting smoke is applied only to the image captured at the location where a flame was detected among the multiple images captured by the multiple surveillance cameras 110, so the load of image processing is lighter than when this image processing is applied to all the images captured by the multiple surveillance cameras 110. Furthermore, since it is determined that a fire has occurred only when both smoke and flame are detected, the accuracy of determining that a fire has occurred is higher than when it is determined that a fire has occurred when either smoke or flame is detected.
[0040] In the above-described embodiment, various signals, notifications, etc. transmitted from the CCTV equipment 100 and the disaster prevention receiving panel 230 to the remote monitoring device 300 may include identifiers of the surveillance camera 110 and the fire detector 210. Similarly, the display of various information on the display unit 234 performed by the notification means 237 of the disaster prevention receiving panel 230 may include identifiers of the surveillance camera 110 and the fire detector 210. By using the identifiers, it is possible to quickly confirm what kind of event has occurred in what shooting range or detection range.
[0041] In the above-described embodiment, when smoke is detected but flame is not detected and the occurrence of a fire is not confirmed, a notification may not be sent to the remote monitoring device 300. For example, when the occurrence of a fire is not confirmed, the notification means 237 of the disaster prevention receiving panel 230 may display information indicating that smoke has been detected on the display unit 234, but may not transmit a smoke detection signal indicating that smoke has been detected to the remote monitoring device 300.
[0042] In the above-described embodiment, the disaster prevention control panel is not limited to the disaster prevention receiving panel 230 installed in the tunnel. The disaster prevention control panel may be any device that can receive a fire signal from the fire detector 210 and a smoke detection signal from the second image processing device 220. For example, a fire receiver may be adopted as the disaster prevention control panel instead of the disaster prevention receiving panel 230. In addition, when a fire receiver is adopted, a flame detector or a flame detector may be adopted instead of the fire detector 210. In this modification, the abnormality detected by the first image processing device 120 from the image captured by the surveillance camera 110 includes an abnormality such as an intruder, a suspicious person, or a suspicious object instead of an abnormality related to traffic.
[0043] In the above-mentioned embodiment, the configuration of the disaster prevention system 10 is not limited to the above-mentioned example. The disaster prevention system 10 may be configured to include one or more of the above-mentioned devices, or may be configured without including some of the devices. In addition, the entity having the functions of the disaster prevention system 10 is not limited to the above-mentioned example. For example, the function of the disaster prevention receiving panel 230 may be realized by cooperation of multiple devices. The disaster prevention receiving panel 230 may not include the display unit 234, and a device other than the disaster prevention receiving panel 230 may include the display unit 234.
[0044] In the above-described embodiment, the operation of the disaster prevention system 10 is not limited to the above-described example. The order of the processing procedures of the disaster prevention system 10 may be changed as long as there is no contradiction. In addition, some of the processing procedures of the disaster prevention system 10 may be omitted.
[0045] Another embodiment of the present invention may provide a method having steps of processing performed in the disaster prevention system 10, the disaster prevention receiving panel 230, or the second image processing device 220. Furthermore, yet another embodiment of the present invention may provide a program executed in the disaster prevention receiving panel 230 or the second image processing device 220. This program may be provided by being stored in a computer-readable recording medium, or may be provided by downloading via the Internet or the like. [Explanation of symbols]
[0046] 10: Disaster prevention system, 100: CCTV equipment, 110: Surveillance camera, 120: First image processing device, 200: Emergency equipment, 210: Fire detector, 220: Second image processing device, 230: Disaster prevention receiving panel, 300: Remote monitoring device
Claims
[Claim 1] A fire detector that detects flames by a means other than image processing; an image processing device that detects smoke by applying the image processing to an image captured by a surveillance camera installed in the fire prevention object when the flame is detected by the fire detector in the fire prevention object; a disaster prevention control panel that determines that a fire has occurred when the flame and the smoke are detected; a storage unit that stores correspondence information indicating a correspondence relationship between the fire detector and a monitoring camera having a shooting range that overlaps with a detection range of the fire detector, The disaster prevention control panel identifies the monitoring camera having the shooting range that overlaps with the detection range of the fire detector that detected the flame based on the correspondence information stored in the memory unit, the disaster prevention control panel transmits to the image processing device a time when the flame is detected by the fire detector; The image processing device extracts a portion of a predetermined time range based on the time when the flame was detected by the fire detector from the image captured by the specified surveillance camera, and detects the smoke by applying the image processing to the extracted portion. Disaster prevention system.
Citation Information
Patent Citations
Disposal of sewage and its apparatus
JP1981097587A
Complex fire sensor
JP1993120580A
Abnormal state detector for running road
JP1994290389A
Fire detector
JP1998269471A
Fire detecting device
JP2000137877A
