JP7327792B2 - Image composition system and image composition method - Google Patents

Description

The present disclosure relates to image compositing systems and image compositing methods.

Patent Document 1 describes a plurality of surveillance cameras, a video conversion/combination unit that combines a plurality of videos captured by a plurality of surveillance cameras into one combined video, an encoder that encodes the combined video, and transmission from the encoder. A video monitoring system is disclosed that includes a decoder that decodes a combined video transmitted via a channel, and a display device that displays video of the decoded combined video captured by a plurality of monitoring cameras on a display screen. .

WO2016/174946

However, in the configuration of Patent Document 1, when displaying images captured by a plurality of surveillance cameras on a display screen of a display device, one of the plurality of images used to generate a combined image is selected. displayed above. For this reason, Patent Document 1 technically discloses that a plurality of images are combined to generate a combined image in order to efficiently transmit a large number of images at once when transmitting to a display device. It was not possible to combine multiple images to display a wide-ranging image of the location where the images were taken. For this reason, when a point of interest such as the site of an incident or accident is photographed by a plurality of cameras, it is not possible to combine the plurality of photographed images to obtain an image of the scene in a wide range.

The present disclosure has been devised in view of the above-described conventional situation, an image synthesizing system and an image synthesizing system that obtains a wide range of images of a point of interest and effectively supports observation and understanding of the surrounding situation of the point. The purpose is to provide a method.

The present disclosure is an image synthesizing system including a plurality of cameras and a server communicably connected to each of the plurality of cameras, wherein each of the plurality of cameras captures a specific object . The individual captured images sent from each of the plurality of cameras are sent to the server, and the server extracts meta information having characteristic elements of the specific object appearing in the individual captured images sent from each of the plurality of cameras, and extracts the meta information. and corresponding captured images are recorded in association with each other, and based on the meta information corresponding to the individual captured images, a composite image is generated by synthesizing a plurality of captured images in which the characteristic elements of the specific object match. To provide an image compositing system that sends an image to a viewer device.

Further, the present disclosure provides an image composition method executed by an image composition system including a plurality of cameras and a server communicably connected between each of the plurality of cameras, the image composition method comprising : The individual captured images are sent to the server, meta information having characteristic elements of the specific object appearing in the individual captured images sent from each of the plurality of cameras is extracted, and the meta information is associated with the meta information. and a viewer device for generating a synthesized image obtained by synthesizing a plurality of captured images matching the characteristic elements of the specific object based on the meta information corresponding to the individual captured images. To provide an image compositing method.

Further, the present disclosure is an image synthesizing system including a camera and a server communicably connected to the camera, wherein the camera captures a specific object , and multiple to the server, and the server extracts meta information having characteristic elements of the specific object appearing in each of the plurality of captured images sent from the camera, and extracts the image corresponding to the meta information and a spatial image obtained by synthesizing a plurality of captured images matching the characteristic elements of the specific object based on the meta information corresponding to each of the plurality of captured images. Provide an image compositing system to send to the device.

Further, the present disclosure provides an image composition method executed by an image composition system including a camera and a server communicably connected to the camera, wherein a specific object is imaged, temporally A plurality of successive captured images are sent to the server, meta information having characteristic elements of the specific object appearing in each of the plurality of captured images sent from the camera is extracted, and a captured image corresponding to the meta information is extracted. and are recorded in association with each other, and based on the meta information corresponding to each of the plurality of captured images, a spatial image is generated by synthesizing a plurality of captured images matching the characteristic elements of the specific object, and a viewer device To provide an image compositing method.

Advantageous Effects of Invention According to the present disclosure, it is possible to obtain a wide-range image of a point of interest and effectively support observation and understanding of the situation around the point.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a schematic explanatory diagram showing a system configuration example of a wearable camera system according to Embodiment 1; Block diagram showing an example hardware configuration of a wearable camera Block diagram showing a hardware configuration example of an in-vehicle PC FIG. 4 is a sequence diagram showing an example of an operation procedure of the wearable camera system according to Embodiment 1 in chronological order; A diagram showing an example of a spatial image and an imaging area including captured images to which the same case number is assigned A diagram for explaining an operation example of generating a spatial image using a plurality of captured images to which the same case number is assigned. FIG. 11 is a sequence diagram showing an example of an operation procedure of the wearable camera system according to Embodiment 2 in chronological order; FIG. 4 is a diagram for explaining an operation example of generating a spatial image using a plurality of images captured by one wearable camera;

Hereinafter, embodiments specifically disclosing an image synthesizing system and an image synthesizing method according to the present disclosure will be described in detail with reference to the drawings as appropriate. However, more detailed description than necessary may be omitted. For example, detailed descriptions of well-known matters and redundant descriptions of substantially the same configurations may be omitted. This is to avoid unnecessary verbosity in the following description and to facilitate understanding by those skilled in the art. It should be noted that the accompanying drawings and the following description are provided for a thorough understanding of the present disclosure by those skilled in the art and are not intended to limit the claimed subject matter.

(Embodiment 1)
FIG. 1 is a schematic explanatory diagram showing a system configuration example of a wearable camera system 1 according to Embodiment 1. As shown in FIG. A wearable camera system 1 as an example of an image synthesizing system includes, for example, a wearable camera 10 worn by a police officer as an example of a user arriving at a field, and various types of cameras placed in a police station. It is composed of equipment and various equipment mounted in a police vehicle VC1 (Police Vehicle) such as a patrol car that has arrived at the scene. The wearable camera 10 may be used inside the police station or outside the police station (for example, inside the police vehicle VC1 or at the scene). The wearable camera 10 is sometimes called a BWC (Body Worn Camera). A site as an example of a point of interest regarding an incident or the like is, for example, a point where an incident occurred, or a point where a criminal exists or is barricaded.

Various devices arranged in the police station include, for example, a back end streaming server 60 (BSS: Back End Streaming Server), a back end server 70 (BES: Back End Server), a back end client 80 (BEC: Back End Client). ), one or more wireless LAN (Local Area Network) access points, and a gang charger 90 as an example of a charging device capable of collectively charging a plurality of wearable cameras 10, but are not limited to these. Note that the wireless LAN access point mediates communication between the in-vehicle camera system 50 and a server in the police station (for example, the backend server 70).

Various devices mounted in the police vehicle VC1 include, for example, an in-vehicle camera system 50 (ICV: In-Car Video system), a common trigger box 54 (CTB: Common Trigger Box) as an example of a trigger device, a charging device ( PD (pairing dock) as an example includes at least a charging base 55 and a rotating warning light PL1, but is not limited to these. For example, a smart phone carried by a police officer to communicate with the police station may also be included. Note that the common trigger box 54 may be included in the vehicle-mounted camera system 50 .

The wearable camera 10, which is an example of a camera, is attached to the uniform of a policeman, captures the situation in front of the policeman as a subject, records (that is, records) the captured video for a certain period of time, and transmits the captured video via a cable (for example, a USB cable). ) or wirelessly (eg, the common trigger box 54) to the onboard camera system 50. When the wearable camera 10 detects that it has been connected to a wireless LAN access point in the police station for wireless communication, the wearable camera 10 may send the captured video to the backend server 70 connected via the wireless LAN access point. good. The wearable camera 10 may be charged when it is manually placed on the charging surface of the gang charger 90 by a police officer.

The wearable camera 10 and the in-vehicle camera 51, which will be described later, do not only capture people, but also scene scenes of incidents, crowds (so-called onlookers) gathered near the scene, and people around the imaging position. May include atmosphere.

The in-vehicle camera system 50 has one or more in-vehicle cameras 51, an in-vehicle PC 52, and an in-vehicle recorder 53. The on-vehicle camera 51 captures the situation of the scene where the police vehicle VC1 has arrived, and the image obtained by imaging (hereinafter referred to as " captured image”) is recorded (that is, video-recorded) in the vehicle-mounted recorder 53 . The in-vehicle camera 51, the in-vehicle PC 52, and the in-vehicle recorder 53 are connected by wire so that they can transmit and receive data or information, but they may be connected wirelessly. The in-vehicle camera system 50 (for example, the in-vehicle PC 52) and the wearable camera 10 may be connected by wire (for example, a USB cable compatible with USB (Universal Serial Bus)) so that data or information can be transmitted and received.

The in-vehicle camera 51 as an example of a camera includes, for example, a front camera attached so as to be able to image the front of the police vehicle VC1, a side camera attached so as to be able to image the side direction of the police vehicle VC1, and an image behind the police vehicle VC1. a possibly mounted rear facing camera. The vehicle-mounted camera 51 sends the imaged image to the vehicle-mounted recorder 53 , and the imaged image is recorded in the vehicle-mounted recorder 53 .

In-vehicle PC52 controls each operation of in-vehicle camera 51 and in-vehicle recorder 53 according to a policeman's operation. In addition, although the details will be described later, the in-vehicle PC 52 as an example of the viewer device is operated by a police officer riding in the police vehicle VC1, and images are captured by the one or more wearable cameras 10 and the in-vehicle camera 51 during the same time period. The picked-up video may be read out from the vehicle-mounted recorder 53 and displayed and played back. As a result, the police officer using the in-vehicle PC 52 can easily view the images of the scene captured by the wearable camera 10 and the in-vehicle camera 51 at the same time, and can confirm the situation of the scene in a wide area. You can improve your own work efficiency, such as remembering the situation clearly. Note that the in-vehicle PC 52 may charge the wearable camera 10 by supplying power to the wearable camera 10 when detecting that it is connected to the wearable camera 10 via the USB cable.

In-vehicle recorder 53 records images captured by wearable camera 10 and in-vehicle camera 51 respectively. The in-vehicle PC 52 reads and acquires the captured image captured by the wearable camera 10 from the in-vehicle recorder 53 by the policeman's operation, or reads the image captured by the wearable camera 10 independently in a predetermined application installed in the in-vehicle PC 52. The captured image may be reproduced, or the attribute information of the captured image may be added in the application. Similarly, the in-vehicle PC 52 reads and acquires the captured video imaged by the in-vehicle camera 51 from the in-vehicle recorder 53 by the operation of the police officer, or obtains the captured video of the in-vehicle camera 51 in the default application installed in the in-vehicle PC 52 may be reproduced independently, or the attribute information of the captured image may be added in the application.

The in-vehicle camera system 50 is connected to a common trigger box 54 by a wire (for example, a LAN cable) and operates according to commands from the common trigger box 54 . The operation according to the command from the common trigger box 54 includes, for example, starting or stopping recording (that is, recording) of images captured by the vehicle-mounted camera 51 and starting or stopping recording (that is, recording) of images captured by the wearable camera 10. included. The in-vehicle camera system 50 may be connected to the wearable camera 10 via the common trigger box 54 so as to enable wireless communication of data or information.

The in-vehicle camera system 50 streams images captured by the wearable camera 10 and the in-vehicle camera 51 (for example, real-time live images being captured) to the backend streaming server 60 via the common trigger box 54 and the network NW1. you can Network NW1 is, for example, a mobile communication network or the Internet. When the in-vehicle camera system 50 (for example, the in-vehicle PC 52) detects that it is connected to the wireless LAN access point in the police station for wireless communication (for example, the police vehicle VC1 parks in the parking lot in the police station (time), images captured by the wearable camera 10 and the vehicle-mounted camera 51 (for example, recorded images captured in the past) may be sent to the backend server 70 via the wireless LAN access point.

The common trigger box 54 is connected to the rotation warning light PL1, acceleration sensor (not shown), siren (not shown), on-vehicle camera system 50, and charging stand 55 by wire (for example, GPIO (physical cable) or LAN cable), Alternatively, each device is wirelessly connected in response to IoT (Internet Of Things). The common trigger box 54 can also be connected to the wearable camera 10 via the charging base 55 when the wearable camera 10 is placed on the charging base 55 .

For example, when the common trigger box 54 is connected to the in-vehicle camera system 50 with a wire (eg, a LAN cable), the in-vehicle camera system 50 receives an alarm notification (eg, recording start or recording stop) when a predetermined event is detected. control signal). As a result, the in-vehicle camera system 50 operates according to the control signal from the common trigger box 54, for example, starts recording (recording) the captured image captured by the in-vehicle camera 51 in the in-vehicle recorder 53, or starts the recording. (Recording) can be stopped. When the common trigger box 54 acquires an operation start signal from a device mounted on a police vehicle such as a revolving warning light PL1 or a siren, the wearable camera connected to the common trigger box 54 detects the start of use of the device mounted on the police vehicle. A control signal for starting or stopping recording may be sent to at least one of 10 and in-vehicle camera system 50 . As a result, at least one of the wearable camera 10 and the in-vehicle camera system 50 operates in accordance with the control signal from the common trigger box 54, for example, when the rotary warning light PL1 starts rotating or when the siren sounds. You can start and stop recording.

The charging base 55 is arranged, for example, at a predetermined position (for example, near the center console) of the police vehicle VC1, and is connected to the common trigger box 54 by wire (for example, PoE (Power over Ethernet (registered trademark)) using a LAN cable). connected by The charging stand 55 has a housing portion (not shown) in which the wearable camera 10 is placed. The charging stand 55 can charge the battery of the wearable camera 10 based on the current supplied from the common trigger box 54 when it detects that the wearable camera 10 is placed in the housing (not shown).

A smart phone (see above) possessed by a police officer has a telephone function and a wireless communication function (for example, communication with the in-vehicle camera system 50), and is used, for example, for emergency contact from or to the police station. . According to the operation of the policeman, the smartphone displays and reproduces the image captured by the wearable camera 10 or the in-vehicle camera 51, and edits such as adding attribute information (also referred to as meta information) to the captured image. or The attribute information may be, for example, an incident type that directly or indirectly suggests the content of the captured video.

The smartphone has a tethering function, and using this tethering function, images captured by the wearable camera 10 and the vehicle-mounted camera 51 from the vehicle-mounted camera system 50 are transmitted to the back-end streaming server 60 in the police station via the network NW1. may be relayed to Here, a wireless LAN such as BLE (Bluetooth (registered trademark) Low Energy) or Wifi (registered trademark), for example, is used between the vehicle-mounted camera system 50 and the smartphone.

The back-end streaming server 60, which is an example of a server, is configured with a high-performance server computer and storage, and captures video (e.g., live video) streamed from the in-vehicle camera system 50 via the common trigger box 54 and network NW1. ) is received and transferred to the backend server 70 .

A back-end server 70, which is an example of a server, is configured with a high-performance server computer and storage, and manages evidence videos of incidents. The back-end server 70 composes the images captured by the wearable camera 10 and the vehicle-mounted camera 51, for example, according to a request according to the operation of a user (for example, an analysis specialist in a police station) who uses the back-end client 80. It has a video analysis function that includes various image processing such as face detection, recognition, and matching.

A back-end client 80 as an example of a viewer device is configured by a computer such as a PC (Personal Computer), and accesses a suspicious person database (not shown) by operation of a user (for example, an analysis specialist in a police station). It has a browser or a dedicated application that can search for information related to criminal cases and display the search results on a display device. The display device is configured by, for example, an LCD (Liquid Crystal Display) or an organic EL (Electroluminescence) provided in the backend client 80 . In the suspicious person database, for example, persons on the wanted list or past criminals are registered in advance in association with information identifying cases (for example, case numbers). A back-end client 80, which is an example of a viewer device, backs up captured images captured by the wearable camera 10 and the vehicle-mounted camera 51 in the same time zone by the operation of a user (for example, an analysis specialist in a police station). It reads out from the end server 70 and displays and reproduces it. As a result, the user of the back-end client 80 can easily view the images of the site captured by the wearable camera 10 and the vehicle-mounted camera 51 during the same time period, so that the situation of the site can be confirmed in a wide area. You can improve your work efficiency, such as clearly identifying the situation.

The wireless LAN access point is wirelessly connected to the in-vehicle camera system 50 via a wireless LAN, and relays, for example, captured video sent from the in-vehicle camera system 50 to the backend server 70 .

The gang charger 90 can place the wearable cameras 10 worn by each of a plurality of police officers on a predetermined charging surface, and charges the batteries incorporated in the individual wearable cameras 10 placed.

FIG. 2 is a block diagram showing a hardware configuration example of the wearable camera 10. As shown in FIG. Wearable camera 10 includes imaging unit 11 , GPIO 12 (General Purpose Input/Output), RAM 13 (Random Access Memory), ROM 14 (Read Only Memory), and storage unit 15 . The wearable camera 10 includes an EEPROM 16 (Electrically Erasable Programmable ROM), an RTC 17 (Real Time Clock), and a GNSS (Global Navigation Satellite System) receiver 18 . The wearable camera 10 includes an MCU 19 (Micro Controller Unit), a BLE communication unit 21A, a WLAN communication unit 21B, a USB interface 22, a contact terminal 23, a power supply unit 24, and a battery 25. Note that the interface is abbreviated as "I/F" in the accompanying drawings.

The wearable camera 10 includes a recording switch SW1, a snapshot switch SW2, a communication mode switch SW3, an attribute information addition switch SW4, and a wireless registration switch SW5.

Wearable camera 10 includes three LEDs 26a, 26b, 26c (Light Emission Diodes), vibrator 27, audio output unit 28, microphone 29A, speaker 29B, and earphone terminal 29C.

The imaging unit 11 has an imaging lens 115 and a solid-state imaging device based on a CCD (Charge Coupled Device) type image sensor or a CMOS (Complementary Metal Oxide Semiconductor) type image sensor. The imaging unit 11 outputs the data of the captured image of the subject obtained by imaging to the MCU 19 .

Detection terminal 23T of contact terminal 23 is a terminal that causes a voltage change when wearable camera 10 is placed on charging stand 55 or gang charger 90 or removed from charging stand 55 or gang charger 90 . A detection terminal 23T of the contact terminal 23 is connected to an AD converter CV. A signal indicating a voltage change of the detection terminal 23T is converted into a digital signal by the AD converter CV, and the digital signal is input to the MCU 19 via the I2C20.

GPIO 12 is a parallel interface. The GPIO 12 includes a recording switch SW1, a snapshot switch SW2, a communication mode switch SW3, an attribute information addition switch SW4, a wireless registration switch SW5, LEDs 26a, 26b, 26c, a vibrator 27, an audio output section 28, a microphone 29A, a speaker 29B and earphones. Each of terminals 29C is connected. The GPIO 12 inputs and outputs signals between these various electronic components and the MCU 19 .

The microphone 29A picks up sounds around the wearable camera 10 and outputs audio data of the picked-up sounds to the MCU 19 via the GPIO 12 . Note that the microphone 29A may be a built-in microphone housed in the housing of the wearable camera 10 or a wireless microphone wirelessly connected to the wearable camera 10 . In the case of wireless microphones, police officers can attach them to any location to improve sound pickup.

The audio output unit 28 outputs audio signals regarding the operation of the wearable camera 10 under the instruction of the MCU 19 . The audio output unit 28 reads out audio data having a predetermined message audio stored in advance in the ROM 14 or the like, and outputs an audio signal based on this audio data from the speaker 29B. The earphone terminal 29C outputs the audio signal output from the audio output section 28 to the earphone connected to the earphone terminal 29C. The speaker 29B receives the audio signal output from the audio output unit 28 and outputs audio.

Also, the AD converter CV is connected to the MCU 19 via a communication interface such as I2C20 (Inter-Integrated Circuit). A similar effect can be obtained by connecting the detection terminal 23T of the contact terminal 23 to the GPIO 12 without the AD converter CV.

The RAM 13 is a work memory used in the operation of the MCU 19, for example. The ROM 14 pre-stores, for example, programs and data for controlling execution of operations (processes) of the MCU 19 .

The storage unit 15 is configured by a storage medium such as a memory card, for example, and stores images captured by the imaging unit 11 based on, for example, an instruction to start recording based on an operation by a police officer or an instruction to start recording from the in-vehicle camera system 50. data recording (i.e. recording). The storage unit 15 always pre-buffers and holds data of an image captured by the imaging unit 11 for a predetermined time (for example, 30 seconds), and stores image data for a predetermined time (for example, 30 seconds) before the current time. Continually accumulate data. When receiving an instruction to start recording, the storage unit 15 starts recording the data of the captured image, and continues recording the data of the captured image until receiving an instruction to stop recording. In addition, when the storage unit 15 is composed of a memory card, it is attached to the housing of the wearable camera 10 so as to be freely inserted and removed.

The EEPROM 16 stores, for example, identification information for identifying the wearable camera 10 (for example, a serial number as a camera ID) and various setting information. The RTC 17 counts the current time information and outputs it to the MCU 19 .

The GNSS receiving unit 18 receives satellite signals including respective signal transmission times and position coordinates transmitted from a plurality of (for example, four) navigation satellites and outputs them to the MCU 19 . The MCU 19 uses a plurality of satellite signals to calculate the current position coordinates of the wearable camera 10 and the reception time of the satellite signals. Note that this calculation may be performed by the GNSS receiver 18 instead of the MCU 19 . This reception time information may also be used to correct the system time of wearable camera 10 (that is, the output of RTC 17). The system time is used, for example, to record the imaging time of a captured image (including still images and moving images).

The MCU 19 has a function as a control unit of the wearable camera 10, for example, control processing for overall control of the operation of each unit of the wearable camera 10, data input/output processing with each unit of the wearable camera 10, Performs data arithmetic (calculation) processing and data storage processing. MCU 19 operates according to various programs and data stored in ROM 14 . During operation, the MCU 19 uses the RAM 13 to obtain current time information from the RTC 17, and obtains current position information from the GNSS receiver 18 or calculates current position information using output from the GNSS receiver 18. do.

The BLE communication unit 21A performs wireless communication with a smartphone, a common trigger box 54, or the like using BLE (Bluetooth (registered trademark) Low Energy) communication, which is a communication standard for short-range wireless communication. BLE is the designation for version 4.0 of Bluetooth®. BLE enables communication with low power consumption, but its communication speed is as low as about 100 kbps.

The WLAN communication unit 21B is connected to a smartphone as a wireless LAN access point using a tethering function, a wireless LAN access point provided in a police station, or the like via a wireless LAN (that is, WLAN), and performs wireless communication with the connection destination. . Compared to BLE, a wireless LAN is capable of high-speed communication with a communication speed of several tens to several hundred Mbps, but consumes more power because it is always connected to a wireless LAN access point. In addition, the WLAN communication unit 21B communicates with a common trigger box 54 mounted in the police vehicle VC1 by wireless LAN communication, and transmits image data obtained by the imaging unit 11 to the common trigger box 54. send. The captured image data is sent to the back-end streaming server 60 in the police station via the common trigger box 54 and the network NW1. Further, when the police vehicle VC1 is located within the communication range of the wireless LAN access point in the police station, the captured image data is sent to the back-end server 70 in the police station via the common trigger box 54 and the wireless LAN access point. may be sent to

In addition to BLE communication or WLAN communication, the wearable camera 10 performs communication for performing short-range wireless communication such as NFC (Near Field Communication) or wireless communication using a mobile network (for example, LTE: Long Term Evolution). You may each have the structure (illustration omitted) of a part.

The USB interface 22 is a serial bus and enables connection with, for example, an in-vehicle PC 52 or a backend client 80 in a police station.

The contact terminal 23 is a terminal for electrically connecting to the charging base 55 , and is connected to the MCU 19 via the USB interface 22 as well as to the power supply section 24 . The power supply unit 24 charges the battery 25 in response to detection of connection between the contact terminal 23 and the charging base 55 . The contact terminal 23 can communicate video data read from the storage unit 15 by the MCU 19 to an external device (for example, the common trigger box 54 ) connected via the charging stand 55 according to the connection with the charging stand 55 . be.

The contact terminal 23 is provided with, for example, a “charging terminal V+” (not shown), a “detection terminal 23T”, “data terminals D− and D+” (not shown), and a “ground terminal” (not shown). The detection terminal 23T is a terminal for detecting voltage and voltage change. The data terminals D− and D+ are terminals for transferring image data captured by the wearable camera 10 to the in-vehicle PC 52 via, for example, a USB connector terminal. A detection terminal 23T of the contact terminal 23 is connected to a communication interface such as I2C 20 via an AD converter CV, and the detected voltage value of the contact terminal 23 is input to the MCU19.

By connecting the contact terminal 23 and the connector of the charging stand 55, data communication is possible between the wearable camera 10 and an external device (for example, the common trigger box 54).

The power supply unit 24 is supplied from an external power supply (for example, a common trigger box 54, a cigar charger (not shown) in the police vehicle VC1, accessories in the police vehicle VC1) connected to the charging stand 55 via the contact terminal 23, for example. The battery 25 is charged by supplying the charging current to the battery 25 .

The battery 25 is composed of, for example, a rechargeable secondary battery, and supplies power to each part of the wearable camera 10 .

The recording switch SW1 is a push button switch for inputting an operation instruction for starting/stopping recording (imaging of a moving image) by, for example, a policeman's pressing operation. Also, the MCU 19 may start recording (capturing a moving image) when the recording switch SW1 is pressed for a short time, and end recording when the recording switch SW1 is pressed for a long time. Also, the MCU 19 may start recording (capturing a moving image) when the recording switch SW1 is pressed an odd number of times, and end recording when the recording switch SW1 is pressed an even number of times.

The snapshot switch SW2 is a push-button switch for inputting an operation instruction for capturing a still image, for example, by a policeman's pressing operation. For example, every time the snapshot switch SW2 is pressed, the MCU 19 captures a still image at the time of pressing.

The communication mode switch SW3 is a slide switch for inputting an operation instruction for setting a communication mode between the wearable camera 10 and an external device, for example. Communication modes include, for example, access point mode, station mode, and OFF mode.

The access point mode is a mode in which the wearable camera 10 operates as a wireless LAN access point, wirelessly connects to, for example, a smartphone owned by a police officer, and performs communication between the wearable camera 10 and the smartphone. In the access point mode, by connecting to the wearable camera 10, the smartphone can display current live images, play back recorded images, and display still images captured by the wearable camera 10.

The station mode is a mode in which communication is performed using the external device as an access point when connecting to the external device using a wireless LAN. For example, a smartphone may be set as an external device by using the tethering function of the smartphone. In the station mode, the wearable camera 10 can perform various settings, transfer (upload) of recorded images held by the wearable camera 10 , and the like to the in-vehicle camera system 50 .

The OFF mode is a mode in which the communication operation of the wireless LAN is turned off and the wireless LAN is not used.

The attribute information adding switch SW4 is a push button switch operated to add attribute information to the video data. The attribute information indicates the content of the image captured by the wearable camera 10 (for example, type of incident, murder, robbery, disaster, etc.).

The wireless registration switch SW5 registers and sets an external device (e.g., smartphone, common trigger box 54) with which the wearable camera 10 performs wireless communication (e.g., wireless communication using BLE or wireless LAN) as a communication partner (hereinafter referred to as " This is a push button switch that is operated during communication setting processing. Hereinafter, for example, in wireless communication using BLE, the process of registering and setting a communication partner device may be referred to as “pairing”.

The LED 26 a is a display unit that indicates, for example, the power-on state (on/off state) of the wearable camera 10 and the state of the battery 25 .

The LED 26b is a display unit that indicates, for example, the imaging operation state (recording state) of the wearable camera 10 .

The LED 26c is, for example, a display unit that indicates the state of the communication mode of the wearable camera 10. FIG. Also, the three LEDs 26a to 26c blink according to instructions from the MCU 19 when the wearable camera 10 receives notification data from the vehicle-mounted camera system 50 (for example, the vehicle-mounted PC 52). At this time, the MCU 19 varies the blinking patterns of the LEDs 26a to 26c according to the information about the sound source contained in the notification data.

The MCU 19 detects the inputs of the recording switch SW1, the snapshot switch SW2, the communication mode switch SW3, the attribute information addition switch SW4, and the wireless registration switch SW5, and processes the switch inputs that have been operated.

When the MCU 19 detects an operation input of the recording switch SW1, the MCU 19 controls the start or stop of the image pickup operation in the image pickup section 11, and saves the image obtained from the image pickup section 11 in the storage section 15 as a moving image.

When the MCU 19 detects the operation input of the snapshot switch SW2, the MCU 19 saves the image captured by the imaging unit 11 when the snapshot switch SW2 was operated in the storage unit 15 as a still image.

The MCU 19 detects the state of the communication mode switch SW3, and operates the communication section 21 in the communication mode according to the setting of the communication mode switch SW3.

When the attribute information adding switch SW4 is pressed, the MCU 19 adds the attribute information corresponding to the data of the image captured by the imaging unit 11 to the image in association with the image.

When the wireless registration switch SW5 is pressed, the MCU 19 performs predetermined processing to be performed in the communication setting processing (for example, pairing) with the peripheral external device (for example, the common trigger box 54) that can be the communication partner of the wearable camera 10. to run. Here, exemplifying pairing, the predetermined processing includes generation of registration request information as a communication partner of wireless communication, output to the BLE communication unit 21A, and generation of connection information for specifying the communication partner that is the connection destination. and output to the BLE communication unit 21A, and storage in the storage unit 15 of the connection information transmitted from the communication partner. However, it goes without saying that the default processing related to wireless LAN communication settings is the same as the default processing when pairing is exemplified above.

FIG. 3 is a block diagram showing a hardware configuration example of the in-vehicle PC 52. As shown in FIG. The in-vehicle PC 52 includes a CPU 201, an I/O (Input/Output) control unit 202, a communication unit 203, a memory 204, an input unit 205, a display unit 206, a speaker 207, and an HDD 208. . The in-vehicle PC 52 can communicate with each of the wearable camera 10 and the in-vehicle recorder 53, and also communicate with various servers in the police station (for example, the backend streaming server 60 and the backend server 70) via the common trigger box 54. It is possible.

The CPU 201 performs, for example, control processing for overall control of the operation of each unit of the in-vehicle PC 52, input/output processing of data to/from other units via the I/O control unit 202, and calculation of data. Processing and data storage.

The CPU 201 authenticates whether or not the policeman can log in to the vehicle-mounted camera system 50 by the policeman's input operation on the login screen to the vehicle-mounted camera system 50 displayed on the display unit 206, for example. The police officer's input operation is, for example, an operation of inputting an officer ID and a password. Various types of information about police officers to whom login is permitted are pre-stored, for example, in the memory 204. 50 is determined. This login may be a login to the in-vehicle camera system 50 via the in-vehicle PC 52 or a login to a default application installed in the in-vehicle PC 52 .

The I/O control unit 202 controls input/output of data between the CPU 201 and each unit of the in-vehicle PC 52 (for example, the communication unit 203, the input unit 205, the display unit 206, and the speaker 207). Relay data to Note that the I/O control unit 202 may be configured integrally with the CPU 201 .

The communication unit 203 performs wired or wireless communication with, for example, the vehicle-mounted camera 51 or the vehicle-mounted recorder 53 or the wearable camera 10 that can be worn by a police officer.

The memory 204 is configured using, for example, RAM, ROM, nonvolatile or volatile semiconductor memory, functions as a work memory during operation of the CPU 201, and stores predetermined programs and data for operating the CPU 201. . Memory 204 stores, for example, login information relating to police officers who are permitted to login to onboard camera system 50 .

The input unit 205 is a UI (User Interface) for receiving an input operation by the policeman and notifying the CPU 201 via the I/O control unit 202, and is a pointing device such as a mouse and a keyboard. The input unit 205 may be arranged corresponding to the screen of the display unit 206, for example, and may be configured using a touch panel or a touch pad that can be operated by a policeman's finger or a stylus pen. The input unit 205 inputs login information for logging in to the in-vehicle camera system 50, for example.

The display unit 206 is configured using, for example, an LCD or an organic EL, and displays various information. In addition, the display unit 206 displays the data of the image portion included in the images captured by the wearable camera 10 and the vehicle-mounted camera 51 on the same screen under the instruction of the CPU 201, for example, according to the input operation of the police officer. indicate.

The speaker 207 outputs, under the instruction of the CPU 201, the data of the audio part included in the images captured by the wearable camera 10 and the vehicle-mounted camera 51, for example, according to the policeman's input operation. Note that the display unit 206 and the speaker 207 may be configured separately from the in-vehicle PC 52 .

The HDD 208 stores, for example, various data and software (software programs). Specifically, the HDD 208 stores, for example, software for controlling and setting the vehicle-mounted camera 51 and the vehicle-mounted recorder 53 and software for controlling and setting the wearable camera 10 . Further, the HDD 208 may store, for example, imaged video data captured by the wearable camera 10 and imaged video data captured by the in-vehicle camera 51 .

Next, an operation procedure of the wearable camera system 1 according to Embodiment 1 will be described.

Here, an example will be described in which the images captured by the wearable cameras 10 worn by two police officers OA and OB (see FIG. 4) are combined by the backend server 70 and displayed on the backend client 80 as a spatial image. . In order to distinguish between the wearable cameras 10 worn by the two police officers OA and OB, the wearable camera 10 worn by the police officer OA will be referred to as "BWC1" here for convenience, and the wearable camera 10 worn by the police officer OB will be referred to as "BWC1" for convenience. commonly referred to as "BWC2". BWC1 and BWC2 are both wearable cameras 10 having the same hardware configuration (see FIG. 2).

FIG. 4 is a sequence diagram showing an example of an operation procedure of the wearable camera system 1 according to Embodiment 1 in chronological order. Assume a situation where police officers OA and OB are present at the scene of an incident or accident (hereinafter also simply referred to as "incident scene").

In FIG. 4, when the incident scene is imaged by the BWC 1 worn by the police officer OA, the BWC 1 periodically uploads recorded evidence images to the backend server 70 (T1). For example, assume a scene in which a criminal is locked up at home. When the police officer OA patrols this house, recorded evidence video by BWC 1 is sent to the backend server 70 every 30 seconds, 1 minute, 5 minutes, for example. Needless to say, the timing (period) at which the recorded evidence video is transmitted is not limited to 30 seconds, 1 minute, or 5 minutes. At this time, the BWC 1 transmits the recorded evidence video including the time information and the current position information as meta information of the recorded evidence video.

Recorded evidence video obtained by BWC 1 is transmitted to back-end streaming server 60 via common trigger box 54 and network NW1 connected to BWC 1 via wireless LAN, or back-end streaming server 60 further via back-end streaming server 60, for example. It is sent to the server 70 . After the video evidence recorded by the BWC 1 is accumulated in the vehicle-mounted recorder 53, the common trigger box 54 is connected to the wireless LAN access point in the police station so as to be communicable, and then sent to the back end via the common trigger box 54. It may be sent directly to the server 70 .

Similarly, when the scene of the incident is imaged by the police officer OB, the BWC 2 periodically uploads recorded evidence images to the backend server 70 (T2). At this time, the BWC 2 transmits the recorded evidence video including the time information and the current position information as meta information of the recorded evidence video. The transmission route of the recorded evidence video from the BWC 2 to the backend server 70 may be the same as or different from the transmission route of the recorded evidence video from the BWC 2 to the backend server 70 described above.

Similarly, the vehicle-mounted camera 51 images the incident scene where the police vehicle VC1 has arrived. The in-vehicle camera system 50 (ICV) periodically transmits the recorded evidence video obtained by the in-vehicle camera 51 to the backend server 70 (T3). At this time, the in-vehicle PC 52 transmits the time information and the current position information together with the recorded evidence video as meta information of the recorded evidence video.

Recorded evidence video obtained by the vehicle-mounted camera 51 is transmitted from the vehicle-mounted PC 52 connected to the vehicle-mounted camera 51, for example, via the common trigger box and the network NW1, to the back-end streaming server 60, or further via the back-end streaming server 60. It is sent to the backend server 70 . After the video evidence recorded by the in-vehicle camera 51 is stored in the in-vehicle recorder 53, the common trigger box 54 is communicatively connected to the wireless LAN access point in the police station, and then transmitted through the common trigger box 54. It may be sent directly to the backend server 70 .

The backend server 70 receives and records (accumulates) recorded evidence video including meta information from each of the BWC1, BWC2 and the vehicle-mounted camera 51 . Based on the meta information corresponding to the accumulated documentary evidence video, the backend server 70, for the documentary evidence video in the same time period and in the same area (location), the case number ( case number) is given (T4). The same time zone is a time during which images are judged to represent the same incident, accident, etc., and is arbitrarily set. For example, when a policeman questions a suspicious person, the same time period is set to 10 minutes. The same area is a predetermined range based on current position information obtained by the GNSS receiver 18 mounted on the wearable camera 10 . Here, the case of using GPS (Global Positioning System), which is one of GNSS, is used as the current position information. Note that the current position information is not limited to the position information obtained by the GNSS receiver, and may be substituted by the position information of a wireless base station that transmits and receives wireless signals to and from the wearable camera.

If there is at least one documented evidence video with the same incident number, the backend server 70 extracts the feature element of the specific object recorded in the evidence documented video as meta information, time) and GPS position information (T5). Here, the specific object is an object that serves as a landmark (base point) at the site of an incident, accident, etc. (in other words, a point of interest regarding the incident, etc.), for example, an inanimate object such as a house or tree that does not move easily. . In the case of using recorded evidence images obtained by the BWC1, BWC2 and the vehicle-mounted camera 51 in a short period of time, a movable vehicle may be employed as the specific object.

The back-end server 70 searches for objects with matching feature elements from a plurality of recorded evidence videos to which the same case number is assigned (T6). In this object search, it is possible to search for objects with matching feature elements in the documented evidence video captured by the same camera (for example, a wearable camera worn by the same police officer), or to search for objects with different feature elements (wearable by different police officers, respectively). Objects with matching characteristic elements may be searched for in documentary evidence images captured by a wearable camera. Note that the different camera may be a combination of a wearable camera worn by a police officer and an in-vehicle camera of a police vehicle. Also, the number of cameras is not limited to two, and may be three or more.

As a result of the search, when an object with matching feature elements is found, the backend server 70 uses the object with the matching feature elements as a base point (reference point), and selects each object from two or more different evidence recording videos. The images containing the object are extracted, and the two or more extracted images are combined so as to maintain the same appearance shape of the entire object or a common part thereof to generate a composite image (T7). For example, the two or more extracted images are images captured at the same timing by the two wearable cameras 10 (BWC1, BWC2). Note that the two or more extracted images may be images captured at different timings.

The composite image is simply the addition of two or more extracted images to the extent that, even if combined, the same overall or common portion of the common object in each documentary evidence image retains the same appearance shape. It is a still image generated by, for example, an area where two or more images overlap. In addition, in the composite image, a portion that does not appear in any image where two or more images are close to each other is not subjected to interpolation processing by image processing etc. (in other words, imaging blank area) without creating an image that is not. As a result, the synthesized image is a genuine image (in other words, an image whose evidentiary reliability is guaranteed).

The back-end server 70 adds (splices) images of a plurality of frames that precede and follow each other in the time direction with respect to two or more images used to generate a composite image to generate a larger spatial image. (T8). This spatial image consists of a composite image containing two or more images whose base point is an object with matching feature elements, and a static image obtained by combining one or more preceding and succeeding frame images of the two or more images included in this composite image. It is an image. Therefore, the spatial image is composed of two or more images whose base points are objects with matching feature elements, from the previous frame (the image before a predetermined number of frames) of the composite image to the image after the composite image (the image after the predetermined number of frames). images) are obtained in a superimposed state. It should be noted that the preceding and following frames may be only the frames after the image serving as the base point, or may be only the frames before. Also, the number of frames before and after each image serving as a base point may be different for each case number, for example.

In the case of displaying a spatial image, the spatial image may be continuously displayed frame by frame like a slide show from the front frame to the rear frame image of the composite image. That is, the spatial image may be displayed as a moving image so as to continuously reproduce still images.

The backend server 70 performs streaming distribution of the spatial image data combined with one video to the backend client 80 (T9). Here, streaming distribution is performed to the backend client 80 connected to the backend server 70 via a wired LAN or the like. Note that streaming distribution may be performed to the in-vehicle PC 52 or another viewer device (smartphone, tablet terminal) or the like via the wireless LAN, network NW1 and common trigger box 54 .

On the other hand, the backend client 80 receives the spatial image data transmitted from the backend server 70 (T10). Based on the received spatial image data, the backend client 80 displays the spatial image SG (see FIG. 6) so that the analysis specialist of the police station can view it (T11).

In the present embodiment, the backend server 70 performs the process of extracting the characteristic elements of the object as meta information. may be done. For example, the in-vehicle PC 52 may extract meta information based on the recorded evidence video recorded in the in-vehicle recorder 53 .

FIG. 5 is a diagram showing an example of a spatial image and an imaging area including captured images assigned the same case number. In the figure, the five shot images G11, G12, G13, G14, and G15 indicated by the dotted frame are the same incident shot continuously by the police officer OA at times t1, t2, t3, t4, and t5, respectively. It is a numbered image. Similarly, the four captured images G22, G23, G23, and G24 indicated by the dotted frame are continuously captured by the police officer OB at times t2, t3, t4, and t5, respectively, and given the same case number. It is an image. Of these captured images, for example, between the captured image G12 captured by the police officer OA and the captured image G22 captured by the police officer OB, the characteristic elements (windshield, left and right side mirrors, etc.) of the object (for example, the same vehicle) match. Here, the captured image G12 and the captured image G22 are images captured at the same time t2, but may be images captured at different times. This is the same for the captured image G13 and the captured image G23, and the captured image G14 and the captured image G24. However, it is desirable that the five captured images G11, G12, G13, G14, G15 and the four captured images G22, G23, G23, G24 are images of frames continuously captured in time series. .

FIG. 6 is a diagram for explaining an operation example of generating a spatial image using a plurality of captured images to which the same case number is assigned. The back-end server 70 combines the captured image G12 and the captured image G22 that match the feature elements of the objects included in the meta information as a combined reference image, and generates a combined image MG. Furthermore, the back-end server 70 assigns the same incident number as the captured images G12 and G22, and each image of a plurality of frames preceding or succeeding in the time direction with respect to the above-described combined reference image (for example, images captured one frame later). The image G13 and the captured image G23) are combined to generate a combined image MG1 after one frame. Similarly, the back-end server 70 combines the captured image G14 and the captured image G24 two frames later in the time direction with respect to the combined reference image described above to generate a combined image MG2 after two frames. Similarly, the back-end server 70 combines the captured image G15 and the captured image G25 three frames later in the time direction with respect to the combined reference image described above, and generates a combined image MG3 after three frames.

Note that if there exists a captured image G21 that is one frame earlier than the captured image G22 that is the combined reference image captured by the BWC 2 (in FIG. 6, the captured image G21 does not exist), the backend server 70 , the captured image G11 and the captured image G21 may be combined to generate a synthesized image one frame before. In the example of FIG. 6, only the captured image G11 of the previous frame is used because the synthesized image of the previous frame is not generated. The backend server 70 connects the composite image MG, one or more preceding and subsequent composite images (for example, one frame later composite image MG1, two frame later composite image MG2, and three frame later composite image MG3) and the captured image G11 one frame before. A spatial image SG is generated.

In this way, the spatial image SG is an image obtained by combining one or more preceding and subsequent composite images (for example, one frame later composite image MG1, two frame later composite image MG2, and three frame later composite image MG3) into the composite image MG. This image has a wider imaging area than the image MG and the images of one or more preceding and following frames. Therefore, an analysis specialist at a police station can confirm the situation at the scene of an incident, accident, or the like with a wide range of images. In addition, the spatial image SG does not include an image in a range exceeding the composite image MG and one or more previous and subsequent frame images. That is, the spatial image SG is a true image without falsity (eg, not including an image generated by image interpolation) obtained based on the composite image MG and one or more previous and subsequent frame images. Therefore, the spatial image can secure its value as evidence recording video.

The images used for generating the composite image may be a plurality of (two or more) images captured at arbitrary timing among the plurality of captured images assigned the same case number. In other words, the base points of objects with matching characteristic elements are not limited to the same timing, but may be included in frame images at different timings in a time zone treated as the same case number. Alternatively, the spatial image may be generated by simply combining the images of each frame into the composite image without generating and connecting one or more preceding and succeeding composite images for the composite image.

As described above, in the wearable camera system 1 according to Embodiment 1, the wearable camera system 1 includes the plurality of wearable cameras 10 and the back-end server 70 connected to each of the plurality of wearable cameras 10 so as to be able to communicate with each other. and including. Each of the multiple wearable cameras 10 sends individual captured images of the incident scene to the backend server 70 . The back-end server 70 extracts meta information having characteristic elements of specific objects appearing in individual captured images sent from each of the plurality of wearable cameras 10, and records the meta information in association with the corresponding captured images. do. The backend server 70 generates a composite image by synthesizing a plurality of captured images matching the characteristic elements of a specific object based on the meta information corresponding to each captured image, and sends the composite image to the backend client 80 .

As a result, the analysis specialist at the police station can view a wide range of images of incidents, accidents, etc. (points of interest) captured using multiple wearable cameras 10 and displayed on the backend client 80. can. Therefore, the wearable camera system 1 can obtain a wide-range image of a point of interest such as an incident or accident, and can effectively assist the police in observing and grasping the circumstances surrounding the scene of the incident or accident.

In addition, the back-end server 70 uses images of one or more frames before and after the imaging time of each of the multiple captured images used to generate the composite image (previous and subsequent captured images) to generate a specific image. Generating one or more front and rear synthesized images (for example, one frame post synthesized image MG1, two frame post synthesized image MG2, and three frame post synthesized image MG3) obtained by synthesizing a plurality of before and after captured images in which feature elements of an object match, and generating a synthesized image. A spatial image is generated by connecting the MG and one or more preceding and following synthesized images, and is sent to the backend client 80. - 特許庁As a result, the wearable camera system 1 can display temporally continuous images of the site of an incident, accident, etc., and can more effectively support observation and understanding of the circumstances surrounding the site of the incident, accident, etc.

Also, each of the plurality (for example, two) wearable cameras 10 can acquire position information by the GNSS receiver 18 . Each wearable camera 10 associates the location information of the site of an incident, accident, etc. and the imaging time with the captured image and sends the captured image to the backend server 70 . The back-end server 70 assigns the same case number to each captured image when the position information and imaging time corresponding to each captured image sent from each of the two wearable cameras 10 are the same. Record. As a result, the backend server 70 can retrieve only the captured images related to the same incident, accident, etc., and display them on the backend client 80 . Therefore, an analysis specialist at a police station can quickly view captured images related to incidents and accidents.

In addition, the backend server 70 extracts meta information having characteristic elements of a specific object using individual captured images to which the same case number is assigned. As a result, the backend server 70 can use the meta information to associate individual captured images to which the same case number is assigned. For example, the back-end server 70 can combine two captured images with matching object feature elements to generate a composite image.

In addition, two wearable cameras 10 worn by each of a plurality of (for example, two) police officers OA and OB are used as the plurality of cameras. Thereby, the backend server 70 can obtain images of a wide range of sites captured by the two wearable cameras 10 .

Also, as the plurality of cameras, the wearable camera 10 worn by each of one or more police officers and the vehicle-mounted camera 51 provided in the police vehicle VC1 in which the police officer rides are used. As a result, the backend server 70 can obtain images of a wide range of sites captured by one or more wearable cameras 10 and vehicle-mounted cameras 51 .

Further, the spatial image SG combines the synthesized image MG and one or more preceding and subsequent synthesized images (for example, one frame later synthesized image MG1, two frame later synthesized image MG2, and three frame later synthesized image MG3) to form the synthesized image MG and one or more This is an image captured by two BWC1 and BWC2, which has a wider imaging area than each of the front and rear synthesized images. As a result, the spatial image SG becomes an image with a wider imaging area than the composite image MG and the images of one or more preceding and following frames. Therefore, an analysis specialist at a police station can confirm the situation at the scene of an incident, accident, or the like with a wide range of images. Also, the spatial image SG is a true image without falsity (not including an image generated by image interpolation, for example) obtained based on the synthesized image MG and one or more previous and subsequent frame images. Therefore, the spatial image can secure its value as evidence recording video.

Note that here, the backend server generates a spatial image by combining a plurality of captured images to which the same incident number is assigned. Alternatively, images captured by wearable cameras worn by different police officers may be combined to generate a spatial image based on the identification number of the police officer who went to the same incident scene.

(Embodiment 2)
In Embodiment 1, images captured by wearable cameras worn by a plurality of (two or more) police officers are combined to form a composite image, and the composite image is combined with one or more previous and subsequent frame images to form a spatial image. is generated. In the second embodiment, an example will be described in which images of one or more frames before and after captured by one wearable camera worn by one policeman are combined to generate a spatial image. An in-vehicle camera mounted on a police vehicle may be used instead of one wearable camera.

Also, the wearable camera system of the second embodiment has substantially the same configuration as that of the first embodiment. The same reference numerals are used for the same components as in the first embodiment, and the description thereof is omitted.

FIG. 7 is a sequence diagram showing an example of the operation procedure of the wearable camera system 1 according to Embodiment 2 in chronological order. Here, one wearable camera 10 is a BWC2 worn by one police officer OB, but may be a BWC1 worn by a policeman OA.

In FIG. 7, when the scene of an incident, accident, etc. is imaged by the police officer OB, the BWC 2 periodically uploads recorded evidence images to the backend server 70 (T31). At this time, the BWC 2 transmits the recorded evidence video including the time information and the current position information as meta information of the recorded evidence video. Instead of the BWC 2, the vehicle-mounted camera 51 takes an image of the situation at the scene where the police vehicle VC1 has arrived, and likewise, the recorded evidence video including meta information such as time information and current position information is periodically sent to the back-end server 70. may be sent to

If at least one recorded evidence video exists, the backend server 70 extracts the characteristic elements of the object recorded in each evidence recorded video as meta information and accumulates them together with the recording time and GPS position information (T32).

The back-end server 70 searches for an object whose feature element matches with respect to a plurality of recorded evidence videos (T33). In this object search, objects with matching characteristic elements are searched for in documentary evidence images captured by the same camera (for example, a wearable camera worn by the same policeman).

If an object with matching feature elements is found as a result of the search, the backend server 70 sets the object with the matching feature elements as a base point (reference point) (T34). The back-end server 70 adds (splices) one or more images of preceding and following frames to one image including the base point to generate a large spatial image SG2 (see FIG. 8) (T35). This spatial image SG2 is a still image obtained by combining one or more previous and subsequent frame images with respect to an image whose base point is an object whose feature elements match. It should be noted that the preceding and following frames may be only the frames after the image serving as the base point, or may be only the frames before. Also, the number of frames before and after each image serving as a base point may differ depending on GPS position information, recording time, and the like.

The backend server 70 performs streaming distribution of the spatial image data combined with one video to the backend client 80 (T36).

On the other hand, the backend client 80 receives the spatial image data transmitted from the backend server 70 (T37). Based on the received spatial image data, the backend client 80 displays the spatial image SG2 so that the analysis specialist of the police station can view it (T38).

FIG. 8 is a diagram illustrating an operation example of generating a spatial image using a plurality of images captured by one wearable camera. In the drawing, four captured images G22, G23, G24, and G25 indicated by dotted-line frames are images captured continuously at times t2, t3, t4, and t5 by the police officer OB, respectively. For example, between the captured image G22 and the captured image G23, the characteristic elements (headlights, side mirrors, etc.) of the object (same vehicle) match.

The back-end server 70 uses the captured image G22 as an original image, combines the images of the frames before and after the captured image G22 (captured images G23, G24, and G25) with the captured image G22 to generate the spatial image SG2. Here, the case where the backend server 70 combines the captured images G23, G24, and G25 of the later frames with the captured image G22, which is the original image, is shown, but the images of the previous frames may be combined. Therefore, the spatial image SG2 is an image obtained by combining the captured image G22 with one or more images of the preceding and succeeding frames, and has a wider imaging area than the captured image G22 and the one or more images of the preceding and succeeding frames. In addition, the spatial image SG2 is a genuine image that does not contain an image in a range exceeding the captured image G22 and the captured images G23, G24, and G25 of one or more preceding and succeeding frames (for example, does not include an image generated by image interpolation). is an image. Therefore, the spatial image can secure its value as evidence recording video.

When displaying a spatial image, the spatial image may be displayed continuously like a slide show from the previous frame to the subsequent frame of the original image. In this case, the spatial image is displayed as a moving image that reproduces still images continuously.

As described above, in the wearable camera system according to Embodiment 2, the wearable camera system includes one wearable camera 10, the backend server 70 connected to each of the plurality of wearable cameras 10 so as to be able to communicate with each other, including. The wearable camera 10 sends to the back-end server 70 a plurality of temporally-sequenced framed images of the scene of the incident. The back-end server 70 extracts meta-information having characteristic elements of specific objects appearing in each of the plurality of frames, and records the meta-information and the corresponding captured image in association with each other. The backend server 70 generates a composite image by synthesizing a plurality of captured images in which the characteristic elements of a specific object match, based on the meta information corresponding to each of the multiple frames of captured images, and sends the composite image to the backend client 80 . .

As a result, the analysis specialist at the police station can view a wide range of scene images of incidents, accidents, and the like, which are displayed on the backend client 80 and captured using a single wearable camera 10 . Therefore, the wearable camera system 1 can effectively support the observation and understanding of the circumstances around the site of an incident, accident, etc., by an analysis specialist at a police station.

Various embodiments have been described above with reference to the drawings, but it goes without saying that the present disclosure is not limited to such examples. It is obvious that a person skilled in the art can conceive of various modifications, modifications, substitutions, additions, deletions, and equivalents within the scope of the claims. Naturally, it is understood that it belongs to the technical scope of the present disclosure. In addition, the constituent elements of the various embodiments described above may be combined arbitrarily without departing from the spirit of the invention.

INDUSTRIAL APPLICABILITY The present disclosure is useful as an image synthesizing system and image synthesizing method that obtains a wide-range image of a spot of interest and effectively assists observation and understanding of the surrounding conditions of that spot.

1 wearable camera system 10 wearable camera 50 in-vehicle camera system 51 in-vehicle camera 52 in-vehicle PC
53 In-vehicle recorder 54 Common trigger box 60 Backend streaming server 70 Backend server 80 Backend client NW1 Network

Claims (10)

An image synthesizing system including a plurality of cameras and a server communicably connected to each of the plurality of cameras,
each of the plurality of cameras,
Sending individual captured images obtained by capturing a specific object to the server,
The server is
extracting meta information having characteristic elements of the specific object appearing in the individual captured images sent from each of the plurality of cameras, and recording the meta information in association with the corresponding captured image;
Based on the meta information corresponding to the individual captured images, a composite image is generated by synthesizing a plurality of captured images matching the characteristic elements of the specific object, and the combined image is sent to a viewer device.
Image synthesis system. The server is
Synthesizing a plurality of before-and-after captured images in which characteristic elements of the specific object match, using the before-and-after captured images temporally before and after the capturing time of each of the plurality of captured images used to generate the composite image. generating one or more before and after combined images, generating a spatial image connecting the combined image and the one or more before and after combined images, and sending the spatial image to the viewer device;
The image synthesizing system according to claim 1. each of the plurality of cameras,
Position information can be acquired, and the position information and the imaging time of the specific object are associated with the captured image and sent to the server;
The server is
when the position information and the imaging time corresponding to the individual captured images sent from each of the plurality of cameras are the same, assigning the same incident management number to the individual captured images and recording them;
The image synthesizing system according to claim 1. The server is
extracting the meta information having characteristic elements of the specific object using the individual captured images assigned the same incident management number;
4. The image synthesizing system according to claim 3. The plurality of cameras are
A wearable camera worn by each of a plurality of police officers,
The image synthesizing system according to any one of claims 1 to 4. The plurality of cameras are
A wearable camera worn by each of one or more police officers, and an in-vehicle camera provided in a police vehicle in which the police officer rides,
The image synthesizing system according to any one of claims 1 to 4. The spatial image is
The composite image and one or more of the preceding and succeeding composite images are combined, and an image captured by the camera is constituted by an imaging area wider than an imaging area shown in each of the composite image and one or more of the preceding and succeeding composite images. ,
3. The image synthesizing system according to claim 2. An image synthesizing method executed by an image synthesizing system including a plurality of cameras and a server communicably connected to each of the plurality of cameras,
Sending individual captured images obtained by capturing a specific object to the server,
extracting meta information having characteristic elements of the specific object appearing in the individual captured images sent from each of the plurality of cameras, and recording the meta information in association with the corresponding captured image;
Based on the meta information corresponding to the individual captured images, a composite image is generated by synthesizing a plurality of captured images matching the characteristic elements of the specific object, and the combined image is sent to a viewer device.
Image composition method. An image synthesizing system including a camera and a server communicably connected to the camera,
The camera is
Sending to the server a plurality of captured images of a specific object captured in chronological order,
The server is
extracting meta information having characteristic elements of the specific object appearing in each of the plurality of captured images sent from the camera, and recording the meta information in association with the corresponding captured image;
Based on the meta information corresponding to each of the plurality of captured images, a spatial image is generated by synthesizing a plurality of captured images in which characteristic elements of the specific object match, and is sent to a viewer device.
Image synthesis system. An image synthesizing method executed by an image synthesizing system including a camera and a server communicably connected to the camera,
Sending to the server a plurality of captured images of a specific object captured in chronological order,
extracting meta information having characteristic elements of the specific object appearing in each of the plurality of captured images sent from the camera, and recording the meta information in association with the corresponding captured image;
Based on the meta information corresponding to each of the plurality of captured images, a spatial image is generated by synthesizing a plurality of captured images in which characteristic elements of the specific object match, and is sent to a viewer device.
Image composition method.

Images