WO2013173994A1 - Embedded system board, method, front device, backend server and system for video surveillance - Google Patents

Embedded system board, method, front device, backend server and system for video surveillance Download PDF

Info

Publication number
WO2013173994A1
WO2013173994A1 PCT/CN2012/075970 CN2012075970W WO2013173994A1 WO 2013173994 A1 WO2013173994 A1 WO 2013173994A1 CN 2012075970 W CN2012075970 W CN 2012075970W WO 2013173994 A1 WO2013173994 A1 WO 2013173994A1
Authority
WO
WIPO (PCT)
Prior art keywords
target data
backend server
notice
transmission
front device
Prior art date
Application number
PCT/CN2012/075970
Other languages
French (fr)
Inventor
Elsa WONG
Original Assignee
Nec Hong Kong Limited
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nec Hong Kong Limited filed Critical Nec Hong Kong Limited
Priority to PCT/CN2012/075970 priority Critical patent/WO2013173994A1/en
Publication of WO2013173994A1 publication Critical patent/WO2013173994A1/en

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H04N7/188—Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position

Definitions

  • the present invention relates to the technical field of video surveillance, in particular, to an embedded system board, a method, a front device, a backend server and a system for video surveillance.
  • Public safety involves the prevention of and protection from events that could endanger the safety of the general public from significant danger, injury, harm or damage, such as crimes or man-made disasters. Public safety is the most concern for all the people living in the society.
  • CN201010296729.X discloses a face recognition method and system.
  • a front- side terminal collects face video and transmits it to a backend server through the 3G network.
  • the backend server receives the face video and recognizes faces with the face video.
  • CN201110104053.4 discloses a traffic image capturing method through the network.
  • a camera captures the data frame with car image by analyzing the video of traffic flow, then the camera encodes the data frame and transmits the encoded data frame to a storage center for storage.
  • An object of the present invention is to provide an embedded system board, a method, a front device, a backend server and a system for video surveillance.
  • the technical solution is as follows:
  • a method for video surveillance comprising:
  • identifying target data from the video stream and transmitting the target data to the backend server for surveillance analysis comprises:
  • the above method further comprises:
  • controlling the target data transmission to the backend server according to the notice comprises:
  • the above method further comprises: sending status information of transmission to the backend server after the step of controlling the target data transmission to the backend server according to the notice.
  • the above method further comprises:
  • the step wherein transmitting the target data to the backend server for surveillance analysis comprises:
  • the target images comprise at least one kind of the images which include face images, human images, crowd images and object images.
  • a method for video surveillance comprising:
  • the above method further comprises:
  • the step wherein judging whether overload is incurred according to the received target data comprises:
  • the step wherein sending a notice for transmission control to at least one front device comprises:
  • the above method further comprises:
  • the above method further comprises:
  • a front device for video surveillance wherein said front device comprises:
  • a capture module for capturing video stream
  • a transmission module for transmitting the target data to the backend server for surveillance analysis.
  • the processing module is used for identifying the target images from the video stream and the transmission module is used for transmitting the video frames including the target images to the backend server for surveillance analysis, or
  • the processing module is used for identifying the target images from the video stream, cropping the target images from the corresponding video frames, and the transmission module is used for transmitting the cropped target images to the backend server for surveillance analysis.
  • the transmission module further comprises: a receipt unit for receiving a notice for transmission control from the backend server; and
  • control unit for controlling the target data transmission to the backend server according to the notice.
  • control unit is used for stopping the target data transmission at a designated period or until receiving the notice for continuing transmission from the backend server according to the notice;
  • control unit is used for transmitting the target data by reducing the quantity of the target data according to the notice.
  • the transmission module is further used for sending status information of transmission to the backend server after controlling the target data transmission to the backend server according to the notice.
  • the transmission module is further used for transmitting the video stream to the backend server.
  • the transmission module is used for transmitting the target data to the backend server for surveillance analysis via wired network or wireless network.
  • the target images comprise at least one kind of the images which include face images, human images, crowd images and object images.
  • a backend server for video surveillance comprises: a receipt module for receiving target data from at least one front device which captures video stream and identifies target data from the video stream; and
  • an analysis module for performing surveillance analysis on the target data.
  • the backend server further comprises:
  • a judging module for judging whether overload is incurred according to the received target data
  • control module for sending a notice for transmission control to at least one front device if the judging module judges overload is incurred according to the received target data.
  • the judging module is used for judging whether the quantity of the target data reaches a threshold; and if so, overload is incurred.
  • the control module comprises:
  • a first control unit for choosing at least one front device randomly and sending a notice for transmission control to each of the chosen front device
  • a second control unit for choosing at least one front device of which the quantity of transmitted target data reaches a threshold, and sending a notice for transmission control to each of the chosen front device;
  • a third control unit for choosing at least one group of front devices of which the quantity of transmitted target data reaches a threshold, and sending a notice for transmission control to at least one front device in each of the chosen group.
  • the receipt module is further used for receiving status information of transmission from the front device which has received the notice for transmission control, after the control module sends a notice for transmission control to at least one front device.
  • the backend server further comprises:
  • an notice module for prompting notice if the result of analysis on the target data shows predetermined situation.
  • a system for video surveillance wherein comprises the above front device and the above backend server.
  • An embedded system board for video surveillance wherein said embedded system board comprises:
  • a transmission module for transmitting the target data to the backend server for surveillance analysis.
  • the processing module is used for identifying the target images from the video stream and the transmission module is used for transmitting the video frames including the target images to the backend server for surveillance analysis, or
  • the processing module is used for identifying the target images from the video stream, cropping the target images from the corresponding video frames, and the transmission module is used for transmitting the cropped target images to the backend server for surveillance analysis.
  • the transmission module further comprises:
  • control unit for controlling the target data transmission to the backend server according to the notice.
  • the control unit is used for stopping the target data transmission at a designated period or until receiving the notice for continuing transmission from the backend server according to the notice; or
  • control unit is used for transmitting the target data by reducing the quantity of the target data according to the notice.
  • the transmission module is further used for sending status information of transmission to the backend server after controlling the target data transmission to the backend server according to the notice.
  • the transmission module is further used for transmitting the video stream to the backend server.
  • the transmission module is used for transmitting the target data to the backend server for surveillance analysis via wired network or wireless network.
  • the target images comprise at least one kind of the images which include face images, human images, crowd images and object images.
  • the processing module is embedded, wherein, the processing module is dedicated to specific tasks.
  • the technical solution provided by the present invention realizes the transmission of the target data for video surveillance from the front device to the backend server, so that the backend server can perform surveillance analysis on the target data. Moreover, the above technical solution is low cost and the investment is one-off, and it is also easy and convenient to install and maintain.
  • the front device can transmit the target images or transmit the data frames having the target images to the backend server.
  • the front device can reduce the load of the backend server by transmitting the target images to the backend server.
  • the backend server When the backend server is overload, the backend server sends a notice for transmission control to at least one front device, so that the front device can control the target data transmission to reduce the load of the backend server, which greatly reduces the time for the backend server to perform the surveillance analysis and effectively improves the efficiency.
  • the surveillance analysis on the target data includes face recognition, human behavior tracking, human detection, crowd detection and object detection etc. It provides more intelligence information for the supervisor to investigate. According to the invention, the backend server notices the supervisor immediately for any unusual or suspect events, which is helpful to safeguard the public security.
  • the front device By using a capture module and a processing module, the front device not only can capture video stream, but also can perform process function such as identifying target data from the video stream. By transmitting the target data to the backend server, the target data can be analyzed for public safety.
  • the front device can be installed in all necessary buildings, and the supervisor can know the surveillance information from the backend server, therefore it can realize a large-scale search and save a lot of manpower and time in monitoring and identifying the suspect cases.
  • the public can have a safe environment without employing more guards but just by installing a video surveillance system.
  • the above technical solution can be used in lots of surveillance fields which include police, banking, immigration, properties management, retail store, etc.
  • Figure 1 is a schematic view of the system for video surveillance in an embodiment
  • Figure 2 is a schematic view wherein the two channels used by the front device for transmission in another embodiment
  • Figure 3 is a schematic view showing a configuration of a front device in one embodiment
  • Figure 4 is a schematic view showing a configuration of a front device in another embodiment
  • FIG. 5 is a flowchart of the method for video surveillance in another embodiment
  • Figure 6 is a flowchart of the method for video surveillance in another embodiment
  • Figure 7 is a schematic view wherein the two channels used by the front device for transmission in another embodiment
  • Figure 8 is a schematic view of the front device for video surveillance in another embodiment
  • Figure 9 is a schematic view of the backend server for video surveillance in another embodiment
  • Figure 10 is a schematic view of an embedded system board for video surveillance in another embodiment.
  • a video surveillance system comprises at least one front device 11, and a backend server 12.
  • the front device 11 can be a camera or any device that can capture video input. It also embeds with a microprocessor, a microcontroller or a digital signal processor(DSP) that provides image data processing function.
  • the camera can be a high density 3G camera. It is designed for capturing the video stream with high resolution and able to perform different functions such as capturing video stream, detecting target and cropping target image.
  • the front device 11 and the backend server 12 can be connected via wired network such as a Wide Area Network(WAN), or wireless network such as 3G network.
  • the video surveillance system can also comprise external storages; the front device 11 provides a connection for user to connect the front device to an external storage device for long term data storage.
  • the front device captures the video streaming and the video streaming will be processed by two channels as shown in Figure 2: One Channel will encode the video streaming with H.264 and transmitted the encoded video streaming via mobile or fixed network. Another channel will identify the target data such as the face image from the video streaming file and crop each face image identified. The cropped face images will then be encrypted and transmitted to the backend server for further processing via mobile or fixed network.
  • a front device comprises lens, a CCD and a mainboard, the front device is not integrated with an existing CCTV camera.
  • a front device comprises a camera and a mainboard, the front device is integrated with an existing CCTV camera.
  • the surveillance system performs the follow method: step 201: at least one front device captures video stream, identifies target data from the video stream, and transmits the target data to the backend server for surveillance analysis.
  • the front device can process data for video surveillance.
  • the target data can be analyzed for public safety.
  • At least one front device captures video stream and identifies the target data from the video stream.
  • the front device can be installed in any necessary places such as rail station, airport, subway, or buildings.
  • the front device captures video stream in real time.
  • the captured video stream can be stored in either the front device or the external storages as video stream file.
  • the microprocessor embedded inside the front device can identify target data from the video stream file.
  • the target data can be video frames which include at least one target image.
  • the target data can be one video frame shows a face image of a suspect of terrorist.
  • the front device can also crop the target images from the corresponding video frames.
  • the microprocessor embedded inside the front device can process cropping to get the face image from the video frame that shows a face image of a suspect of terrorist.
  • the target data can also be target image itself.
  • the target images comprise at least one kind of the images which include face images, human images, crowd images and object images etc.
  • the target data can be stored in the front device and then transmitted to the backend server when necessary.
  • the target data is transmitted to the backend server.
  • the target data can be encrypted before transmitting in order to guarantee data safety.
  • the backend server can store all the target data from more than one front device in one backend server for later analysis. This enables overall monitoring from one control center.
  • the target data will be sent to the backend server only if the target presents at the front device. For example, by transmitting the video frames including target images to the backend server, the server will not have to identify the target images from the video stream, and therefore the transmission of the video stream is not necessary. Thus the workload of the server and the data transfer between the front device and the backend server could be reduced. Furthermore, by transmitting only the cropped target images to the backend server, the backend server will not have to locate target images in the corresponding video frames, so that the workload of the server and the data transfer between the front device and the backend server could be reduced even more. The advantage of less data transfer is especially useful when in the mobile network environment.
  • the video stream captured by the front device can be also transmitted to the backend server and displayed in a monitoring center.
  • the video stream captured by the front device will be processed by two channels. One channel is used to transmit the target data, another channel is used to transmit the video stream. Either the video stream captured or the target data identified by the front device can be transmitted via wired network or wireless network with advanced encoding and data compression technology.
  • the backend server receives target data from at least one front device, and performs surveillance analysis on the target data.
  • the backend server can perform surveillance analysis on the target data by using various engines/algorithms; the engines/algorithms are not limited in this invention.
  • the surveillance analysis includes but is not limited to face matching, human behavior tracking, object detection, human detection and crowd detection. Once the surveillance analysis shows suspect case, for example, the face image of one suspect of terrorist is matched, an notice will be prompt for the supervisor to take appropriate action. Since the notice will be prompt automatically after the surveillance analysis, the supervisor does not need to keep monitoring the screen manually. This saves a lot of manpower and enhances the public security.
  • the video stream will be also received if it is transmitted and will be store and displayed in the monitoring center.
  • step 304 the backend server judges whether overload is incurred according to the received target data, and if so, enter the next step 305; otherwise, return step 303, the backend server can keep receiving the target data as usual.
  • the backend server judges whether the quantity of the target data reaches a preset threshold within a predetermined time, and if so, the overload is incurred.
  • the quantity of the target data can be the numbers of the target images or the total size of the target images, or the numbers of the video frames or the total size of the video frames.
  • step 305 When overload is incurred in the backend server, step 305 will be performed.
  • the backend server sends a notice for transmission control to at least one front device.
  • the backend server chooses a front device to which the notice is sent.
  • the backend server chooses at least one front device randomly and sends a notice for transmission control to each of the chosen front device; or in another embodiment, the backend server chooses at least one front device of which the quantity of transmitted target data within a predetermined time reaches the preset threshold, and sends a notice for transmission control to each of the chosen front device.
  • the backend server can rank the quantity of transmitted target data from high to low for each front device, and choose the front devices with high rank.
  • the backend server when the backend server receives 10 cropped face images as image data from front device A, 20 from device B, 30 from device C, the backend server can choose top 2 front devices B and C as the target for sending notice for transmission control. With the increased number of front devices, the front devices can be grouped according to their attributes. Then the front devices may be managed by group. Yet in another embodiment, the backend server chooses at least one group of front devices of which the quantity of transmitted target data within a predetermined time reaches the preset threshold, and sends a notice for transmission control to each or at least one front device in each of the chosen group.
  • the quantity of the target data can be the numbers of the target images or the total size of the target images, or the numbers of the video frames or the total size of the video frames.
  • the quantity of the target data can be calculated either by the front devices and sent to the server, or by the backend server after receiving target data from the front devices.
  • the front device receives the notice for transmission control from the backend server, and controls the target data transmission to the backend server according to the notice.
  • the target data transmission to the backend server can be controlled in various ways. For example, in one embodiment, the front device stops the target data transmission at a designated period or until receiving the notice for continuing transmission from the backend server according to the notice; or in another embodiment, the front device transmits the target data by reducing the quantity of the target data according to the notice. There are various ways of reducing quantity of the target data.
  • the front device can reduce the frequency of sending the target data; or the front device can reduce the size of the target data by compressing target data; or the front device can extract the features of the target data and transmits the features to the backend server instead of transmitting the target data.
  • the various ways of target data transmission control can be stated in the notice sent from the backend server, or triggered by the front device itself.
  • target data flow from front devices is controlled by the backend server, and the workload and processing time of the backend server is reduced. Efficiency is effectively improved.
  • the front device sends its status information of transmission to the backend server after controlling the target data transmission to the backend server according to the notice. It is to be noted, to save signaling overhead, the front device may don't have to transmit its status information of transmission to the backend server. And the front device can decide by itself whether or when to transmit its status information of transmission to the backend server. Furthermore, the status information can also be displayed on the display unit.
  • the display unit can be a standalone unit or a unit in the front device or in the backend server.
  • the status information of transmission refers to the information which includes but is not limited to: whether the front device is transmitting the target data, the quantity of the target data, what kind of strategy the front device is using to control the target data transmission etc.
  • the quantity of the target data includes but is not limited to: the numbers of the target images, or the total size of the target images, or the frequency of the target images transmission, or the numbers of the video frames, or the total size of the video frames, or the frequency of the video frames.
  • the backend server can understand the transmission status of the front devices, so that the backend server can control the transmission of the front device precisely.
  • the front device can be installed in all necessary buildings, and the supervisor can know the surveillance information from the backend server, therefore it can realize a large-scale search and save a lot of manpower and time in monitoring and identifying the suspect cases.
  • the public can have a safe environment without employing more guards but just by installing a video surveillance system.
  • the above technical solution can be used in lots of surveillance fields which include police, banking, immigration, properties management, retail store, etc.
  • the above method realizes the transmission of the target data about video surveillance from the front device to the backend server, so that the backend server can perform surveillance analysis on the target data. Moreover, the above technical solution is low cost and the investment is one-off, and it is also easy and convenient to install and maintain.
  • a front device for video surveillance comprises:
  • an embedded processing module 502 dedicated to specific tasks, used for identifying target data from the video stream;
  • a transmission module 503 for transmitting the target data to the backend server for surveillance analysis.
  • the front device can be a camera. It is built on an embedded system board.
  • An embedded system is a computer system designed for specific control functions within a larger system, often with real-time computing constraints. It is embedded as part of a complete device often including hardware and mechanical parts.
  • Embedded systems contain processing cores that are typically microprocessors, microcontrollers or digital signal processors (DSP). So the processing module 502 may be a module including a microprocessor, microcontroller or digital signal processor (DSP).
  • the processing module 502 is used for identifying the target images from the video stream and the transmission module is used for transmitting the video frames including the target images to the backend server for surveillance analysis, or
  • the processing module is used for identifying the target images from the video stream, cropping the target images from the corresponding video frames
  • the transmission module is used for transmitting the cropped target images to the backend server for surveillance analysis.
  • the transmission module further comprises:
  • control unit for controlling the target data transmission to the backend server according to the notice.
  • control unit is used for stopping the target data transmission at a designated period or until receiving the notice for continuing transmission from the backend server according to the notice;
  • control unit is used for transmitting the target data by reducing the quantity of the target data according to the notice.
  • the transmission module is further used for sending status information of transmission to the backend server after controlling the target data transmission to the backend server according to the notice.
  • the transmission module is further used for transmitting the video stream to the backend server.
  • the transmission module is used for transmitting the target data to the backend server for surveillance analysis via wired network or wireless network.
  • the processing module is a microprocessor, microcontroller or digital signal processor.
  • the front device can be installed in any necessary places such as rail station, airport, subway, or buildings.
  • the front device captures video stream in real time.
  • the target images comprise at least one kind of the images which include face images, human images, crowd images and object images.
  • the front device can not only capture video stream, but also perform process function such as identifying target data from the video stream.
  • a backend server for video surveillance comprises:
  • the backend server further comprises:
  • a judging module for judging whether overload is incurred according to the received target data
  • control module for sending a notice for transmission control to at least one front device if the judging module judges overload is incurred according to the received target data.
  • target data flow from front devices is controlled by the backend server, and the workload and processing time of the backend server is reduced. Efficiency is effectively improved.
  • the judging module is used for judging whether the quantity of the target data reaches a threshold; and if so, overload is incurred.
  • control module comprises: a first control unit for choosing at least one front device randomly and sending a notice for transmission control to each of the chosen front device; or in another embodiment, the control module comprises a second control unit for choosing at least one front device of which the quantity of transmitted target data reaches a threshold, and sending a notice for transmission control to each of the chosen front device. In the third embodiment, the control module comprises a third control unit for choosing at least one group of front devices of which the quantity of transmitted target data reaches a threshold, and sending a notice for transmission control to at least one front device in each of the chosen group.
  • the receipt module is further used for receiving status information of transmission from the front device which has received the notice for transmission control, after the control module sends a notice for transmission control to at least one front device.
  • the backend server comprises:
  • an notice module for prompting notice if the result of analysis on the target data shows suspect situation.
  • an embedded system board for video surveillance wherein said embedded system board comprises:
  • an embedded processing module 501 dedicated to specific tasks, used for identifying target data from the video stream;
  • a transmission module 502 for transmitting the target data to the backend server for surveillance analysis.
  • the processing module is used for identifying the target images from the video stream and the transmission module is used for transmitting the video frames including the target images to the backend server for surveillance analysis, or
  • the processing module is used for identifying the target images from the video stream, cropping the target images from the corresponding video frames, and the transmission module is used for transmitting the cropped target images to the backend server for surveillance analysis.
  • the transmission module further comprises: a receipt unit for receiving a notice for transmission control from the backend server; and
  • control unit for controlling the target data transmission to the backend server according to the notice.
  • the control unit is used for stopping the target data transmission at a designated period or until receiving the notice for continuing transmission from the backend server according to the notice; or
  • control unit is used for transmitting the target data by reducing the quantity of the target data according to the notice.
  • the transmission module is further used for sending status information of transmission to the backend server after controlling the target data transmission to the backend server according to the notice.
  • the transmission module is further used for transmitting the video stream to the backend server.
  • the transmission module is used for transmitting the target data to the backend server for surveillance analysis via wired network or wireless network.
  • the target images comprise at least one kind of the images which include face images, human images, crowd images and object images.
  • the processing module is embedded, wherein, the processing module is dedicated to specific tasks.
  • the embedded system board can perform process function such as identifying target data from the video stream.
  • all functional units are capable of being integrated in one processing module, or each of the units exists individually, or two or more than two units are integrated in one module.
  • the integrated module may be realized in the format of a hardware or software functional module.
  • the integrated module can be sold or used as an individual product and also can be stored in the readable memory medium of a computer.
  • the above memory medium may be a read-only memory, disk, optical disk, etc. All above devices or systems are capable of executing the method in the corresponding embodiments.

Abstract

The present invention discloses an embedded system board, a method, a front device, a backend server and a system for video surveillance which belong to the technical field of video surveillance. The method comprises steps wherein: a method for video surveillance, wherein said method comprises: capturing video stream; identifying target data from the video stream; and transmitting the target data to the backend server for surveillance analysis. The front device comprises: a capture module, a processing module and a transmission module. The backend server comprises: a receipt module and an analysis module. The system comprises: a front device and a backend server. The present invention realizes the transmission of the target data about video surveillance from the front device to the backend server, so that the backend server can perform surveillance analysis on the target data. Moreover, it is low cost and the investment is one-off, and it is also easy and convenient to install and maintain.

Description

EMBEDDED SYSTEM BOARD, METHOD, FRONT DEVICE, BACKEND SERVER AND SYSTEM FOR VIDEO SURVEILLANCE
BACKGROUND OF THE INVENTION
Technical Field
The present invention relates to the technical field of video surveillance, in particular, to an embedded system board, a method, a front device, a backend server and a system for video surveillance. Description of Related Art
Public safety involves the prevention of and protection from events that could endanger the safety of the general public from significant danger, injury, harm or damage, such as crimes or man-made disasters. Public safety is the most concern for all the people living in the society.
As related arts in surveillance system, CN201010296729.X discloses a face recognition method and system. In this invention, a front- side terminal collects face video and transmits it to a backend server through the 3G network. The backend server receives the face video and recognizes faces with the face video.
CN201110104053.4 discloses a traffic image capturing method through the network. In this invention, a camera captures the data frame with car image by analyzing the video of traffic flow, then the camera encodes the data frame and transmits the encoded data frame to a storage center for storage.
However, the above related arts both have a problem: When receiving an increasing amount of data from different front-side terminals, the backend server need more time for processing data, the efficiency becomes lower.
BRIEF SUMMARY OF THE INVENTION An object of the present invention is to provide an embedded system board, a method, a front device, a backend server and a system for video surveillance. The technical solution is as follows:
A method for video surveillance, wherein said method comprises:
capturing video stream;
identifying target data from the video stream; and
transmitting the target data to the backend server for surveillance analysis.
The step wherein identifying target data from the video stream and transmitting the target data to the backend server for surveillance analysis comprises:
identifying the target images from the video stream and transmitting the video frames including the target images to the backend server for surveillance analysis, or
identifying the target images from the video stream, cropping the target images from the corresponding video frames, and transmitting the cropped target images to the backend server for surveillance analysis.
The above method further comprises:
receiving a notice for transmission control from the backend server; and controlling the target data transmission to the backend server according to the notice.
The step wherein controlling the target data transmission to the backend server according to the notice comprises:
stopping the target data transmission at a designated period or until receiving the notice for continuing transmission from the backend server according to the notice; or
transmitting the target data by reducing the quantity of the target data according to the notice.
The above method further comprises: sending status information of transmission to the backend server after the step of controlling the target data transmission to the backend server according to the notice.
The above method further comprises:
transmitting the video stream to the backend server.
The step wherein transmitting the target data to the backend server for surveillance analysis comprises:
transmitting the target data to the backend server for surveillance analysis via wired network or wireless network.
Wherein, the target images comprise at least one kind of the images which include face images, human images, crowd images and object images.
A method for video surveillance, wherein said method comprises:
receiving target data from at least one front device which captures video stream and identifies target data from the video stream;
performing surveillance analysis on the target data.
The above method further comprises:
judging whether overload is incurred according to the received target data; and if so, sending a notice for transmission control to at least one front device.
The step wherein judging whether overload is incurred according to the received target data comprises:
judging whether the quantity of the target data reaches a threshold; and if so, overload is incurred.
The step wherein sending a notice for transmission control to at least one front device comprises:
choosing at least one front device randomly and sending a notice for transmission control to each of the chosen front device; or
choosing at least one front device of which the quantity of transmitted target data reaches a threshold, and sending a notice for transmission control to each of the chosen front device; or
choosing at least one group of front devices of which the quantity of transmitted target data reaches a threshold, and sending a notice for transmission control to at least one front device in each of the chosen group.
The above method further comprises:
receiving status information of transmission from the front device which has received the notice for transmission control, after the step of sending a notice for transmission control to at least one front device.
The above method further comprises:
prompting notice if the result of analysis on the target data shows predetermined situation.
A front device for video surveillance, wherein said front device comprises:
a capture module for capturing video stream;
an embedded processing module dedicated to specific tasks, used for identifying target data from the video stream; and
a transmission module for transmitting the target data to the backend server for surveillance analysis.
Wherein, the processing module is used for identifying the target images from the video stream and the transmission module is used for transmitting the video frames including the target images to the backend server for surveillance analysis, or
the processing module is used for identifying the target images from the video stream, cropping the target images from the corresponding video frames, and the transmission module is used for transmitting the cropped target images to the backend server for surveillance analysis.
Wherein, the transmission module further comprises: a receipt unit for receiving a notice for transmission control from the backend server; and
a control unit for controlling the target data transmission to the backend server according to the notice.
Wherein, the control unit is used for stopping the target data transmission at a designated period or until receiving the notice for continuing transmission from the backend server according to the notice; or
the control unit is used for transmitting the target data by reducing the quantity of the target data according to the notice.
Wherein, the transmission module is further used for sending status information of transmission to the backend server after controlling the target data transmission to the backend server according to the notice.
Wherein, the transmission module is further used for transmitting the video stream to the backend server.
Wherein, the transmission module is used for transmitting the target data to the backend server for surveillance analysis via wired network or wireless network.
Wherein, the target images comprise at least one kind of the images which include face images, human images, crowd images and object images.
A backend server for video surveillance, wherein said backend server comprises: a receipt module for receiving target data from at least one front device which captures video stream and identifies target data from the video stream; and
an analysis module for performing surveillance analysis on the target data.
The backend server further comprises:
a judging module for judging whether overload is incurred according to the received target data; and
a control module for sending a notice for transmission control to at least one front device if the judging module judges overload is incurred according to the received target data.
The judging module is used for judging whether the quantity of the target data reaches a threshold; and if so, overload is incurred.
The control module comprises:
a first control unit for choosing at least one front device randomly and sending a notice for transmission control to each of the chosen front device; or
a second control unit for choosing at least one front device of which the quantity of transmitted target data reaches a threshold, and sending a notice for transmission control to each of the chosen front device; or
a third control unit for choosing at least one group of front devices of which the quantity of transmitted target data reaches a threshold, and sending a notice for transmission control to at least one front device in each of the chosen group.
The receipt module is further used for receiving status information of transmission from the front device which has received the notice for transmission control, after the control module sends a notice for transmission control to at least one front device.
The backend server further comprises:
an notice module for prompting notice if the result of analysis on the target data shows predetermined situation.
A system for video surveillance, wherein comprises the above front device and the above backend server.
An embedded system board for video surveillance, wherein said embedded system board comprises:
an embedded processing module dedicated to specific tasks, used for identifying target data from the video stream; and
a transmission module for transmitting the target data to the backend server for surveillance analysis. Wherein, the processing module is used for identifying the target images from the video stream and the transmission module is used for transmitting the video frames including the target images to the backend server for surveillance analysis, or
the processing module is used for identifying the target images from the video stream, cropping the target images from the corresponding video frames, and the transmission module is used for transmitting the cropped target images to the backend server for surveillance analysis.
The transmission module further comprises:
a receipt unit for receiving a notice for transmission control from the backend server; and
a control unit for controlling the target data transmission to the backend server according to the notice.
The control unit is used for stopping the target data transmission at a designated period or until receiving the notice for continuing transmission from the backend server according to the notice; or
the control unit is used for transmitting the target data by reducing the quantity of the target data according to the notice.
The transmission module is further used for sending status information of transmission to the backend server after controlling the target data transmission to the backend server according to the notice.
The transmission module is further used for transmitting the video stream to the backend server.
The transmission module is used for transmitting the target data to the backend server for surveillance analysis via wired network or wireless network.
The target images comprise at least one kind of the images which include face images, human images, crowd images and object images. The processing module is embedded, wherein, the processing module is dedicated to specific tasks.
The technical solution provided by the present invention realizes the transmission of the target data for video surveillance from the front device to the backend server, so that the backend server can perform surveillance analysis on the target data. Moreover, the above technical solution is low cost and the investment is one-off, and it is also easy and convenient to install and maintain.
It can be simply realized that the front device can transmit the target images or transmit the data frames having the target images to the backend server. In addition, the front device can reduce the load of the backend server by transmitting the target images to the backend server.
When the backend server is overload, the backend server sends a notice for transmission control to at least one front device, so that the front device can control the target data transmission to reduce the load of the backend server, which greatly reduces the time for the backend server to perform the surveillance analysis and effectively improves the efficiency.
The surveillance analysis on the target data includes face recognition, human behavior tracking, human detection, crowd detection and object detection etc. It provides more intelligence information for the supervisor to investigate. According to the invention, the backend server notices the supervisor immediately for any unusual or suspect events, which is helpful to safeguard the public security.
By using a capture module and a processing module, the front device not only can capture video stream, but also can perform process function such as identifying target data from the video stream. By transmitting the target data to the backend server, the target data can be analyzed for public safety.
The front device can be installed in all necessary buildings, and the supervisor can know the surveillance information from the backend server, therefore it can realize a large-scale search and save a lot of manpower and time in monitoring and identifying the suspect cases. As a result, the public can have a safe environment without employing more guards but just by installing a video surveillance system. In addition, the above technical solution can be used in lots of surveillance fields which include police, banking, immigration, properties management, retail store, etc.
BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS
Figure 1 is a schematic view of the system for video surveillance in an embodiment ;
Figure 2 is a schematic view wherein the two channels used by the front device for transmission in another embodiment;
Figure 3 is a schematic view showing a configuration of a front device in one embodiment;
Figure 4 is a schematic view showing a configuration of a front device in another embodiment;
Figure 5 is a flowchart of the method for video surveillance in another embodiment;
Figure 6 is a flowchart of the method for video surveillance in another embodiment;
Figure 7 is a schematic view wherein the two channels used by the front device for transmission in another embodiment;
Figure 8 is a schematic view of the front device for video surveillance in another embodiment;
Figure 9 is a schematic view of the backend server for video surveillance in another embodiment;
Figure 10 is a schematic view of an embedded system board for video surveillance in another embodiment.
DETAILED DESCRIPTION OF THE INVENTION
To make the objective, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described by way of example, with reference to the accompanying drawings.
As shown in figure 1, a video surveillance system comprises at least one front device 11, and a backend server 12. The front device 11 can be a camera or any device that can capture video input. It also embeds with a microprocessor, a microcontroller or a digital signal processor(DSP) that provides image data processing function. For example, the camera can be a high density 3G camera. It is designed for capturing the video stream with high resolution and able to perform different functions such as capturing video stream, detecting target and cropping target image. The front device 11 and the backend server 12 can be connected via wired network such as a Wide Area Network(WAN), or wireless network such as 3G network. Optionally, the video surveillance system can also comprise external storages; the front device 11 provides a connection for user to connect the front device to an external storage device for long term data storage.
Under one mode, the front device captures the video streaming and the video streaming will be processed by two channels as shown in Figure 2: One Channel will encode the video streaming with H.264 and transmitted the encoded video streaming via mobile or fixed network. Another channel will identify the target data such as the face image from the video streaming file and crop each face image identified. The cropped face images will then be encrypted and transmitted to the backend server for further processing via mobile or fixed network.
The objective for connecting to the backend server is to store all the images. This also enables monitoring from one control center. As shown in figure 3, in one mode, a front device comprises lens, a CCD and a mainboard, the front device is not integrated with an existing CCTV camera.
As shown in figure 4, in another mode, a front device comprises a camera and a mainboard, the front device is integrated with an existing CCTV camera.
As shown in Figure 5, the surveillance system performs the follow method: step 201: at least one front device captures video stream, identifies target data from the video stream, and transmits the target data to the backend server for surveillance analysis. Step 202: a backend server receives target data from at least one front device which captures video stream and identifies target data from the video stream; performs surveillance analysis on the target data.
By capturing video stream and processing function such as identifying target data from the video stream, the front device can process data for video surveillance. By transmitting the target data to the backend server, the target data can be analyzed for public safety.
As shown in figure 6, more detailed method for video surveillance is provided.
First, in Step 301, at least one front device captures video stream and identifies the target data from the video stream. In one embodiment, the front device can be installed in any necessary places such as rail station, airport, subway, or buildings. The front device captures video stream in real time. The captured video stream can be stored in either the front device or the external storages as video stream file. The microprocessor embedded inside the front device can identify target data from the video stream file. The target data can be video frames which include at least one target image. For example, the target data can be one video frame shows a face image of a suspect of terrorist. Moreover, in another embodiment, the front device can also crop the target images from the corresponding video frames. For example, the microprocessor embedded inside the front device can process cropping to get the face image from the video frame that shows a face image of a suspect of terrorist. So the target data can also be target image itself. The target images comprise at least one kind of the images which include face images, human images, crowd images and object images etc.
The target data can be stored in the front device and then transmitted to the backend server when necessary.
Next, in step 302, the target data is transmitted to the backend server. The target data can be encrypted before transmitting in order to guarantee data safety. By connecting to different front devices, the backend server can store all the target data from more than one front device in one backend server for later analysis. This enables overall monitoring from one control center.
The target data will be sent to the backend server only if the target presents at the front device. For example, by transmitting the video frames including target images to the backend server, the server will not have to identify the target images from the video stream, and therefore the transmission of the video stream is not necessary. Thus the workload of the server and the data transfer between the front device and the backend server could be reduced. Furthermore, by transmitting only the cropped target images to the backend server, the backend server will not have to locate target images in the corresponding video frames, so that the workload of the server and the data transfer between the front device and the backend server could be reduced even more. The advantage of less data transfer is especially useful when in the mobile network environment.
In order to have a real time monitoring, the video stream captured by the front device can be also transmitted to the backend server and displayed in a monitoring center. As shown in figure 7, the video stream captured by the front device will be processed by two channels. One channel is used to transmit the target data, another channel is used to transmit the video stream. Either the video stream captured or the target data identified by the front device can be transmitted via wired network or wireless network with advanced encoding and data compression technology.
In the next step 303, the backend server receives target data from at least one front device, and performs surveillance analysis on the target data. The backend server can perform surveillance analysis on the target data by using various engines/algorithms; the engines/algorithms are not limited in this invention. The surveillance analysis includes but is not limited to face matching, human behavior tracking, object detection, human detection and crowd detection. Once the surveillance analysis shows suspect case, for example, the face image of one suspect of terrorist is matched, an notice will be prompt for the supervisor to take appropriate action. Since the notice will be prompt automatically after the surveillance analysis, the supervisor does not need to keep monitoring the screen manually. This saves a lot of manpower and enhances the public security.
The video stream will be also received if it is transmitted and will be store and displayed in the monitoring center.
Upon receiving target data from different front devices, in step 304, the backend server judges whether overload is incurred according to the received target data, and if so, enter the next step 305; otherwise, return step 303, the backend server can keep receiving the target data as usual. In this step, the backend server judges whether the quantity of the target data reaches a preset threshold within a predetermined time, and if so, the overload is incurred. The quantity of the target data can be the numbers of the target images or the total size of the target images, or the numbers of the video frames or the total size of the video frames.
When overload is incurred in the backend server, step 305 will be performed. In this step, the backend server sends a notice for transmission control to at least one front device. There are various ways for the backend server to choose a front device to which the notice is sent. In one embodiment, the backend server chooses at least one front device randomly and sends a notice for transmission control to each of the chosen front device; or in another embodiment, the backend server chooses at least one front device of which the quantity of transmitted target data within a predetermined time reaches the preset threshold, and sends a notice for transmission control to each of the chosen front device. In the third embodiment, the backend server can rank the quantity of transmitted target data from high to low for each front device, and choose the front devices with high rank. For example, when the backend server receives 10 cropped face images as image data from front device A, 20 from device B, 30 from device C, the backend server can choose top 2 front devices B and C as the target for sending notice for transmission control. With the increased number of front devices, the front devices can be grouped according to their attributes. Then the front devices may be managed by group. Yet in another embodiment, the backend server chooses at least one group of front devices of which the quantity of transmitted target data within a predetermined time reaches the preset threshold, and sends a notice for transmission control to each or at least one front device in each of the chosen group.
Same as what is stated in the previous step, the quantity of the target data can be the numbers of the target images or the total size of the target images, or the numbers of the video frames or the total size of the video frames. The quantity of the target data can be calculated either by the front devices and sent to the server, or by the backend server after receiving target data from the front devices.
In step 306, the front device receives the notice for transmission control from the backend server, and controls the target data transmission to the backend server according to the notice. In this step, when the notice is received, the target data transmission to the backend server can be controlled in various ways. For example, in one embodiment, the front device stops the target data transmission at a designated period or until receiving the notice for continuing transmission from the backend server according to the notice; or in another embodiment, the front device transmits the target data by reducing the quantity of the target data according to the notice. There are various ways of reducing quantity of the target data. For example, for the same target data, the front device can reduce the frequency of sending the target data; or the front device can reduce the size of the target data by compressing target data; or the front device can extract the features of the target data and transmits the features to the backend server instead of transmitting the target data. The various ways of target data transmission control can be stated in the notice sent from the backend server, or triggered by the front device itself.
By sending a notice for transmission control to at least one front device, target data flow from front devices is controlled by the backend server, and the workload and processing time of the backend server is reduced. Efficiency is effectively improved.
Further but not necessary, in step 307, the front device sends its status information of transmission to the backend server after controlling the target data transmission to the backend server according to the notice. It is to be noted, to save signaling overhead, the front device may don't have to transmit its status information of transmission to the backend server. And the front device can decide by itself whether or when to transmit its status information of transmission to the backend server. Furthermore, the status information can also be displayed on the display unit. The display unit can be a standalone unit or a unit in the front device or in the backend server.
In the invention, the following definitions are applicable throughout (including above). The status information of transmission refers to the information which includes but is not limited to: whether the front device is transmitting the target data, the quantity of the target data, what kind of strategy the front device is using to control the target data transmission etc. The quantity of the target data includes but is not limited to: the numbers of the target images, or the total size of the target images, or the frequency of the target images transmission, or the numbers of the video frames, or the total size of the video frames, or the frequency of the video frames.
With the status information of transmission, the backend server can understand the transmission status of the front devices, so that the backend server can control the transmission of the front device precisely.
The front device can be installed in all necessary buildings, and the supervisor can know the surveillance information from the backend server, therefore it can realize a large-scale search and save a lot of manpower and time in monitoring and identifying the suspect cases. As a result, the public can have a safe environment without employing more guards but just by installing a video surveillance system. In addition, the above technical solution can be used in lots of surveillance fields which include police, banking, immigration, properties management, retail store, etc.
The above method realizes the transmission of the target data about video surveillance from the front device to the backend server, so that the backend server can perform surveillance analysis on the target data. Moreover, the above technical solution is low cost and the investment is one-off, and it is also easy and convenient to install and maintain.
As shown in figure 8, a front device for video surveillance comprises:
a capture module 501 for capturing video stream;
an embedded processing module 502 dedicated to specific tasks, used for identifying target data from the video stream; and
a transmission module 503 for transmitting the target data to the backend server for surveillance analysis.
The front device can be a camera. It is built on an embedded system board. An embedded system is a computer system designed for specific control functions within a larger system, often with real-time computing constraints. It is embedded as part of a complete device often including hardware and mechanical parts. Embedded systems contain processing cores that are typically microprocessors, microcontrollers or digital signal processors (DSP). So the processing module 502 may be a module including a microprocessor, microcontroller or digital signal processor (DSP).
In one embodiment, the processing module 502 is used for identifying the target images from the video stream and the transmission module is used for transmitting the video frames including the target images to the backend server for surveillance analysis, or
In another embodiment, the processing module is used for identifying the target images from the video stream, cropping the target images from the corresponding video frames, and the transmission module is used for transmitting the cropped target images to the backend server for surveillance analysis. By transmitting only the cropped target images to the backend server, the backend server will not have to locate target images in the corresponding video frames, so that the workload of the server and the data transfer between the front device and the backend server could be reduced even more. The advantage of less data transfer is especially useful when in the mobile network environment.
Wherein, the transmission module further comprises:
a receipt unit for receiving a notice for transmission control from the backend server; and
a control unit for controlling the target data transmission to the backend server according to the notice.
Moreover, the control unit is used for stopping the target data transmission at a designated period or until receiving the notice for continuing transmission from the backend server according to the notice; or
the control unit is used for transmitting the target data by reducing the quantity of the target data according to the notice.
Wherein, the transmission module is further used for sending status information of transmission to the backend server after controlling the target data transmission to the backend server according to the notice.
Further but not necessary, the transmission module is further used for transmitting the video stream to the backend server.
In another embodiment, the transmission module is used for transmitting the target data to the backend server for surveillance analysis via wired network or wireless network.
Wherein, the processing module is a microprocessor, microcontroller or digital signal processor.
In one embodiment, the front device can be installed in any necessary places such as rail station, airport, subway, or buildings. The front device captures video stream in real time.
In the invention, the following definitions are applicable throughout (including above). The target images comprise at least one kind of the images which include face images, human images, crowd images and object images.
By using a front device with a capture module and a processing module, the front device can not only capture video stream, but also perform process function such as identifying target data from the video stream.
Since the embedded system is dedicated to specific tasks, design engineers can optimize it to reduce the size and cost of the product and increase the reliability and performance. With this embedded solution, it is different from other windows based or workstation based solution. As shown in figure 9, a backend server for video surveillance comprises:
a receipt module 601 for receiving target data from at least one front device which captures video stream and identifies target data from the video stream; and an analysis module 602 for performing surveillance analysis on the target data. In addition, the backend server further comprises:
a judging module for judging whether overload is incurred according to the received target data; and
a control module for sending a notice for transmission control to at least one front device if the judging module judges overload is incurred according to the received target data.
By sending a notice for transmission control to at least one front device, target data flow from front devices is controlled by the backend server, and the workload and processing time of the backend server is reduced. Efficiency is effectively improved.
Wherein, the judging module is used for judging whether the quantity of the target data reaches a threshold; and if so, overload is incurred.
In one embodiment, the control module comprises: a first control unit for choosing at least one front device randomly and sending a notice for transmission control to each of the chosen front device; or in another embodiment, the control module comprises a second control unit for choosing at least one front device of which the quantity of transmitted target data reaches a threshold, and sending a notice for transmission control to each of the chosen front device. In the third embodiment, the control module comprises a third control unit for choosing at least one group of front devices of which the quantity of transmitted target data reaches a threshold, and sending a notice for transmission control to at least one front device in each of the chosen group.
In one embodiment, the receipt module is further used for receiving status information of transmission from the front device which has received the notice for transmission control, after the control module sends a notice for transmission control to at least one front device.
Further but not necessary, the backend server comprises:
an notice module for prompting notice if the result of analysis on the target data shows suspect situation.
Once the surveillance analysis shows suspect situation, for example, the face image of one suspect of terrorist is matched, an notice will be prompt for the supervisor to take appropriate action. Since the notice will be prompt automatically after the surveillance analysis, the supervisor does not need to keep monitoring the screen manually. This saves a lot of manpower and enhances the public security.
As shown in figure 10, an embedded system board for video surveillance, wherein said embedded system board comprises:
an embedded processing module 501 dedicated to specific tasks, used for identifying target data from the video stream; and
a transmission module 502 for transmitting the target data to the backend server for surveillance analysis.
Wherein, the processing module is used for identifying the target images from the video stream and the transmission module is used for transmitting the video frames including the target images to the backend server for surveillance analysis, or
the processing module is used for identifying the target images from the video stream, cropping the target images from the corresponding video frames, and the transmission module is used for transmitting the cropped target images to the backend server for surveillance analysis.
The transmission module further comprises: a receipt unit for receiving a notice for transmission control from the backend server; and
a control unit for controlling the target data transmission to the backend server according to the notice.
The control unit is used for stopping the target data transmission at a designated period or until receiving the notice for continuing transmission from the backend server according to the notice; or
the control unit is used for transmitting the target data by reducing the quantity of the target data according to the notice.
The transmission module is further used for sending status information of transmission to the backend server after controlling the target data transmission to the backend server according to the notice.
The transmission module is further used for transmitting the video stream to the backend server.
The transmission module is used for transmitting the target data to the backend server for surveillance analysis via wired network or wireless network.
The target images comprise at least one kind of the images which include face images, human images, crowd images and object images.
The processing module is embedded, wherein, the processing module is dedicated to specific tasks.
By using an embedded system board with a processing module, the embedded system board can perform process function such as identifying target data from the video stream.
Since the embedded system is dedicated to specific tasks, design engineers can optimize it to reduce the size and cost of the product and increase the reliability and performance. With this embedded solution, it is different from other windows based or workstation based solution. Finally, those skilled in the art can appreciate that all or part of the flows of the methods in the above embodiments can be completed by related hardware under the instructions of computer programs, and the programs are capable of being stored in the readable memory medium of a computer and may include the flows of all methods in the above embodiments, wherein the memory medium may be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), etc.
In the embodiments of current invention, all functional units are capable of being integrated in one processing module, or each of the units exists individually, or two or more than two units are integrated in one module. The integrated module may be realized in the format of a hardware or software functional module. In case of being realized in the software functional module, the integrated module can be sold or used as an individual product and also can be stored in the readable memory medium of a computer. The above memory medium may be a read-only memory, disk, optical disk, etc. All above devices or systems are capable of executing the method in the corresponding embodiments.
The above descriptions are only preferable embodiments of the present invention, which shall not limit the present invention. Any amendment, equivalent replacement, improvement, etc. within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

What is claimed is:
1. A method for video surveillance, wherein said method comprises:
capturing video stream;
identifying target data from the video stream; and
transmitting the target data to the backend server for surveillance analysis.
2. The method according to claim 1, the step wherein identifying target data from the video stream and transmitting the target data to the backend server for surveillance analysis comprises:
identifying the target images from the video stream and transmitting the video frames including the target images to the backend server for surveillance analysis, or
identifying the target images from the video stream, cropping the target images from the corresponding video frames, and transmitting the cropped target images to the backend server for surveillance analysis.
3. The method according to claim 1, further comprises:
receiving a notice for transmission control from the backend server; and controlling the target data transmission to the backend server according to the notice.
4. The method according to claim 3, the step wherein controlling the target data transmission to the backend server according to the notice comprises:
stopping the target data transmission at a designated period or until receiving the notice for continuing transmission from the backend server according to the notice; or
transmitting the target data by reducing the quantity of the target data according to the notice.
5. The method according to claim 3, further comprises:
sending status information of transmission to the backend server after the step of controlling the target data transmission to the backend server according to the notice.
6. The method according to claim 1, further comprises:
transmitting the video stream to the backend server.
7. The method according to claim 1, the step wherein transmitting the target data to the backend server for surveillance analysis comprises:
transmitting the target data to the backend server for surveillance analysis via wired network or wireless network.
8. The method according to claim 2, the target images comprise at least one kind of the images which include face images, human images, crowd images and object images.
9. A method for video surveillance, wherein said method comprises:
receiving target data from at least one front device which captures video stream and identifies target data from the video stream;
performing surveillance analysis on the target data.
10. The method according to claim 9, further comprises:
judging whether overload is incurred according to the received target data; and if so, sending a notice for transmission control to at least one front device.
11. The method according to claim 10, the step wherein judging whether overload is incurred according to the received target data comprises:
judging whether the quantity of the target data reaches a threshold; and if so, overload is incurred.
12. The method according to claim 10, the step wherein sending a notice for transmission control to at least one front device comprises:
choosing at least one front device randomly and sending a notice for transmission control to each of the chosen front device; or
choosing at least one front device of which the quantity of transmitted target data reaches a threshold, and sending a notice for transmission control to each of the chosen front device; or
choosing at least one group of front devices of which the quantity of transmitted target data reaches a threshold, and sending a notice for transmission control to at least one front device in each of the chosen group.
13. The method according to claim 10, further comprises:
receiving status information of transmission from the front device which has received the notice for transmission control, after the step of sending a notice for transmission control to at least one front device.
14. The method according to claim 9, further comprises:
prompting notice if the result of analysis on the target data shows suspect situation.
15. A front device for video surveillance, wherein said front device comprises: a capture module for capturing video stream;
an embedded processing module dedicated to specific tasks, used for identifying target data from the video stream; and
a transmission module for transmitting the target data to the backend server for surveillance analysis.
16. The front device according to claim 15,
the processing module is used for identifying the target images from the video stream and the transmission module is used for transmitting the video frames including the target images to the backend server for surveillance analysis, or the processing module is used for identifying the target images from the video stream, cropping the target images from the corresponding video frames, and the transmission module is used for transmitting the cropped target images to the backend server for surveillance analysis.
17. The front device according to claim 15, the transmission module further comprises:
a receipt unit for receiving a notice for transmission control from the backend server; and
a control unit for controlling the target data transmission to the backend server according to the notice.
18. The front device according to claim 17,
the control unit is used for stopping the target data transmission at a designated period or until receiving the notice for continuing transmission from the backend server according to the notice; or
the control unit is used for transmitting the target data by reducing the quantity of the target data according to the notice.
19. The front device according to claim 17,
the transmission module is further used for sending status information of transmission to the backend server after controlling the target data transmission to the backend server according to the notice.
20. The front device according to claim 15,
the transmission module is further used for transmitting the video stream to the backend server.
21. The front device according to claim 15,
the transmission module is used for transmitting the target data to the backend server for surveillance analysis via wired network or wireless network.
22. The front device according to claim 16, the target images comprise at least one kind of the images which include face images, human images, crowd images and object images.
23. A backend server for video surveillance, wherein said backend server comprises:
a receipt module for receiving target data from at least one front device which captures video stream and identifies target data from the video stream; and a analysis module for performing surveillance analysis on the target data.
24. The backend server according to claim 23, further comprises:
a judging module for judging whether overload is incurred according to the received target data; and
a control module for sending a notice for transmission control to at least one front device if the judging module judges overload is incurred according to the received target data.
25. The backend server according to claim 24,
the judging module is used for judging whether the quantity of the target data reaches a threshold; and if so, overload is incurred.
26. The backend server according to claim 24, the control module comprises: a first control unit for choosing at least one front device randomly and sending a notice for transmission control to each of the chosen front device; or
a second control unit for choosing at least one front device of which the quantity of transmitted target data reaches a threshold, and sending a notice for transmission control to each of the chosen front device; or
a third control unit for choosing at least one group of front devices of which the quantity of transmitted target data reaches a threshold, and sending a notice for transmission control to at least one front device in each of the chosen group.
27. The backend server according to claim 24,
the receipt module is further used for receiving status information of transmission from the front device which has received the notice for transmission control, after the control module sends a notice for transmission control to at least one front device.
28. The backend server according to claim 23, further comprises:
an notice module for prompting notice if the result of analysis on the target data shows suspect situation.
29. A system for video surveillance, wherein comprises a front device according to the claims 15 to 22 and a backend server according to the claims 23 to 28.
30. An embedded system board for video surveillance, wherein said embedded system board comprises:
an embedded processing module dedicated to specific tasks, used for identifying target data from the video stream; and
a transmission module for transmitting the target data to the backend server for surveillance analysis.
31. The embedded system board according to claim 30,
the processing module is used for identifying the target images from the video stream and the transmission module is used for transmitting the video frames including the target images to the backend server for surveillance analysis, or the processing module is used for identifying the target images from the video stream, cropping the target images from the corresponding video frames, and the transmission module is used for transmitting the cropped target images to the backend server for surveillance analysis.
32. The embedded system board according to claim 30, the transmission module further comprises:
a receipt unit for receiving a notice for transmission control from the backend server; and
a control unit for controlling the target data transmission to the backend server according to the notice.
33. The embedded system board according to claim 32,
the control unit is used for stopping the target data transmission at a designated period or until receiving the notice for continuing transmission from the backend server according to the notice; or the control unit is used for transmitting the target data by reducing the quantity of the target data according to the notice.
34. The embedded system board according to claim 32,
the transmission module is further used for sending status information of transmission to the backend server after controlling the target data transmission to the backend server according to the notice.
35. The embedded system board according to claim 30,
the transmission module is further used for transmitting the video stream to the backend server.
36. The embedded system board according to claim 30,
the transmission module is used for transmitting the target data to the backend server for surveillance analysis via wired network or wireless network.
37. The embedded system board according to claim 31, the target images comprise at least one kind of the images which include face images, human images, crowd images and object images.
38. The embedded system board according to claim 30, the processing module is embedded, wherein, the processing module is dedicated to specific tasks.
PCT/CN2012/075970 2012-05-23 2012-05-23 Embedded system board, method, front device, backend server and system for video surveillance WO2013173994A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2012/075970 WO2013173994A1 (en) 2012-05-23 2012-05-23 Embedded system board, method, front device, backend server and system for video surveillance

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2012/075970 WO2013173994A1 (en) 2012-05-23 2012-05-23 Embedded system board, method, front device, backend server and system for video surveillance

Publications (1)

Publication Number Publication Date
WO2013173994A1 true WO2013173994A1 (en) 2013-11-28

Family

ID=49623018

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2012/075970 WO2013173994A1 (en) 2012-05-23 2012-05-23 Embedded system board, method, front device, backend server and system for video surveillance

Country Status (1)

Country Link
WO (1) WO2013173994A1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110580447A (en) * 2019-08-06 2019-12-17 深圳市华付信息技术有限公司 Flight support node identification system based on convolutional neural network and machine learning
CN110889569A (en) * 2018-09-10 2020-03-17 杭州萤石软件有限公司 Computing power allocation method and device
CN114125502A (en) * 2021-11-19 2022-03-01 武汉中科通达高新技术股份有限公司 Video stream management method and device
CN110580447B (en) * 2019-08-06 2024-04-26 深圳华付技术股份有限公司 Flight guarantee node identification system based on convolutional neural network and machine learning

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080180520A1 (en) * 2007-01-26 2008-07-31 Chao-Hung Chang System and method for variable-resolution image saving
CN101453639A (en) * 2007-11-29 2009-06-10 展讯通信（上海）有限公司 Encoding, decoding method and system for supporting multi-path video stream of ROI region
US7577199B1 (en) * 2003-06-19 2009-08-18 Nvidia Corporation Apparatus and method for performing surveillance using motion vectors
CN101588490A (en) * 2009-06-24 2009-11-25 杭州华三通信技术有限公司 Method, system and apparatus for adjusting video quality grade

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7577199B1 (en) * 2003-06-19 2009-08-18 Nvidia Corporation Apparatus and method for performing surveillance using motion vectors
US20080180520A1 (en) * 2007-01-26 2008-07-31 Chao-Hung Chang System and method for variable-resolution image saving
CN101453639A (en) * 2007-11-29 2009-06-10 展讯通信（上海）有限公司 Encoding, decoding method and system for supporting multi-path video stream of ROI region
CN101588490A (en) * 2009-06-24 2009-11-25 杭州华三通信技术有限公司 Method, system and apparatus for adjusting video quality grade

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110889569A (en) * 2018-09-10 2020-03-17 杭州萤石软件有限公司 Computing power allocation method and device
CN110580447A (en) * 2019-08-06 2019-12-17 深圳市华付信息技术有限公司 Flight support node identification system based on convolutional neural network and machine learning
CN110580447B (en) * 2019-08-06 2024-04-26 深圳华付技术股份有限公司 Flight guarantee node identification system based on convolutional neural network and machine learning
CN114125502A (en) * 2021-11-19 2022-03-01 武汉中科通达高新技术股份有限公司 Video stream management method and device
CN114125502B (en) * 2021-11-19 2023-11-24 武汉中科通达高新技术股份有限公司 Video stream management method and device

Similar Documents

Publication Publication Date Title
US10123051B2 (en) Video analytics with pre-processing at the source end
CN107911653B (en) Intelligent video monitoring module, system, method and storage medium for residence
CN204156985U (en) There is high-definition camera equipment and the supervisory control system of face recognition comparison function
CN108364374A (en) Face access control device based on deep learning and method
US20110109742A1 (en) Broker mediated video analytics method and system
WO2013189465A2 (en) Method, device and system for obtaining the number of persons
WO2021223665A1 (en) Method and device for reducing invalid warnings
CN109711318B (en) Multi-face detection and tracking method based on video stream
CN104581081A (en) Passenger-flow analysis method based on video information
US10657783B2 (en) Video surveillance method based on object detection and system thereof
CN111178241A (en) Intelligent monitoring system and method based on video analysis
CN111402532A (en) Comprehensive security video management control system
KR101420006B1 (en) System and Method for Camera Image Service based on Distributed Processing
WO2022048129A1 (en) Object recognition method, apparatus, and system
CN112419639A (en) Video information acquisition method and device
WO2013173994A1 (en) Embedded system board, method, front device, backend server and system for video surveillance
CN103454228B (en) Adopt the flue gas blackness supervisory system of motion detecting technology
CN109614916B (en) Real-time monitoring and early warning computer system for station passenger state based on face recognition
CN108197614A (en) A kind of examination hall monitor camera and system based on face recognition technology
CN101694734B (en) Embedded intelligent digital hard disk video recorder for ATM machine
CN116246416A (en) Intelligent analysis early warning platform and method for security protection
CN115100572A (en) System and method for analyzing abnormal behaviors of campus
CN114973135A (en) Head-shoulder-based sequential video sleep post identification method and system and electronic equipment
CN208015894U (en) A kind of video analytic system based on full-view camera
CN110519562B (en) Motion detection method, device and system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 12877206

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 12877206

Country of ref document: EP

Kind code of ref document: A1