WO2018120673A1 - 智能拍摄方法及装置 - Google Patents

智能拍摄方法及装置 Download PDF

Info

Publication number
WO2018120673A1
WO2018120673A1 PCT/CN2017/088500 CN2017088500W WO2018120673A1 WO 2018120673 A1 WO2018120673 A1 WO 2018120673A1 CN 2017088500 W CN2017088500 W CN 2017088500W WO 2018120673 A1 WO2018120673 A1 WO 2018120673A1
Authority
WO
WIPO (PCT)
Prior art keywords
file
video
video frame
smart
processing module
Prior art date
Application number
PCT/CN2017/088500
Other languages
English (en)
French (fr)
Inventor
张焜翔
周章飞
黄鸥
黄广照
Original Assignee
移康智能科技（上海）股份有限公司
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 移康智能科技（上海）股份有限公司 filed Critical 移康智能科技（上海）股份有限公司
Priority to DE112017006669.7T priority Critical patent/DE112017006669T5/de
Publication of WO2018120673A1 publication Critical patent/WO2018120673A1/zh

Links

Images

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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/61—Control of cameras or camera modules based on recognised objects
    • H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording
    • H04N5/765—Interface circuits between an apparatus for recording and another apparatus
    • H04N5/77—Interface circuits between an apparatus for recording and another apparatus between a recording apparatus and a television camera
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording
    • H04N5/91—Television signal processing therefor
    • 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

Definitions

  • the present application relates to the field of video surveillance, and in particular, to a smart imaging method and apparatus.
  • the storage space is small, which effectively reduces the difficulty of file backup or transfer sharing.
  • an embodiment of the present application provides a smart shooting method, including:
  • the camera When a person in the preset detection area is detected, the camera is turned on for video shooting;
  • a video frame in which a face exists in the captured video is detected. If a video frame in which a face exists is detected, the video frame in which the face exists is added to the first file for storage.
  • An embodiment of the present application further provides a smart camera device, including: a detection module, a control module, a first processing module, and a storage module;
  • the detecting module is configured to detect whether a person is detected in the preset detection area
  • the control module is configured to: when the detecting module detects a person in the preset detection area, turn on the camera to perform video shooting;
  • the first processing module is configured to detect a video frame in which a face exists in the captured video. If a video frame in which a face exists is detected, the video frame in which the face exists is added to the first file of the storage module for storage.
  • the camera when the camera detects a person in a preset detection area, the camera is turned on for video shooting, so that the current situation can be recorded in time, which can not only reduce the public institution and The manual monitoring cost of the enterprise site can avoid the monitoring error caused by the long-term fatigue of the personnel, and greatly improve the monitoring efficiency and monitoring accuracy.
  • the photographing device also detects the video frame of the face in the captured video, so as to capture the video frame with the face and save it, so that the captured video can be saved in the form of a picture, which not only reduces the The storage space that needs to be occupied reduces the difficulty of file backup or transfer sharing, and the saved pictures are pictures with key information of the human body, and the use value is high.
  • the method further includes: acquiring a capture period, and capturing M video frames in the video according to the capture period; wherein M is a positive integer;
  • M is a positive integer
  • the frame is added to the second file for saving; if the video frame with the face is not detected, the second file is used as the final save file.
  • the shooting device selects M video frames to save according to a certain selection rule, thereby not only controlling the size of the saved file, but also avoiding being saved.
  • the file is too large and effective It is ensured that each time a person is detected in the preset detection area, the corresponding file can be saved, and the problem of missing the file is avoided.
  • the smart photographing method further includes: if a video frame of a human face is detected, setting a corresponding time screening interval for each video frame according to a recording time point of each video frame in the second file; According to the time screening interval, in the first file, the video frame whose recording time point is located in the time screening interval is obtained; in the second file, the video frame corresponding to the time screening interval is replaced with the recording obtained in the first file. The time point is located in the video frame within the time screening interval; the second file after replacement is used as the final save file.
  • the first file and the second file are integrated, so that the final saved file can contain both pictures with human key information and pictures with other information, so that the user can understand according to the final saved file. Provides the basis for more effective information.
  • turning on the camera for video shooting may include: controlling the camera to capture a video of a preset duration. In this way, the length of the captured video is ensured, and the basis for detecting a large number of video frames with faces is detected for subsequent detection of a video frame having a face in the captured video.
  • One embodiment of the present application provides a computer readable storage medium comprising computer executable instructions that, when executed by at least one processor, cause the processor to perform the above method.
  • An embodiment of the present application provides an electronic device including: at least one processor; and a memory; wherein the memory stores a program executable by the at least one processor, the instruction being the at least one The processor executes to enable the at least one processor to perform the above method.
  • detecting whether a person is detected in the preset detection area may include: detecting, by using a motion detection technology, whether a person is detected in the preset detection area. In this way, a specific implementation form for detecting whether a person is detected in the preset detection area is provided, which increases the feasibility.
  • FIG. 1 is a flowchart of a smart photographing method according to a first embodiment of the present application
  • FIG. 2 is a flowchart of a smart photographing method according to a second embodiment of the present application.
  • FIG. 3 is a schematic structural diagram of a smart camera according to a third embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of a smart photographing apparatus according to a fourth embodiment of the present application.
  • the inventor has found that at least the following defects exist in the prior art: in the prior art, since the camera can only capture video for a certain period of time, and the movement of the human body is uncertain, it is easy to appear in the video captured by the camera, no one or The situation where the key information of the human body (such as the appearance of the human body) is not photographed, resulting in the use value of the captured video is not high. However, if the time of capturing the camera is changed, and the camera is captured during the entire event of the camera, the captured video file is too large, which increases the difficulty of file backup or transfer sharing.
  • the first embodiment of the present application relates to a smart shooting method, and the specific process is as shown in FIG. 1.
  • the embodiment can be implemented on the basis of the intelligent photographing device.
  • the smart photographing device can be an electronic device such as a smart cat eye, a driving recorder, a monitor, etc.
  • the smart shooting device is taken as an example of the smart cat eye as follows. The steps are as follows:
  • step 101 it is detected whether a person is detected in the preset detection area.
  • the preset detection area may be a detection area of the smart cat's eye, for example, a certain geographical range outside the door.
  • smart cat eyes use built-in human body detection
  • the sensor detects the certain geographical range outside the door and realizes the motion detection function.
  • the smart cat eye uses the motion detection technology to detect whether someone is in the preset detection area, which can not only reduce the manual monitoring cost of the public institution and the enterprise place. Moreover, it can avoid the monitoring errors caused by long-term employee fatigue, and greatly improve the monitoring efficiency and monitoring accuracy.
  • the human body detecting sensor may be an infrared sensor, a human body proximity sensor, or the like that can be used to detect the human body.
  • Step 102 Determine whether a person in the preset detection area is detected. If yes, go to step 103, otherwise go to step 101.
  • the human body detecting sensor of the smart cat's eye detects a certain area within a certain area outside the door, it is determined that a person in the preset detecting area is detected.
  • step 103 the camera is turned on for video shooting.
  • the camera controls the camera to capture the preset duration video, thereby ensuring the length of the captured video, and detecting the video frame of the face in the subsequent captured video. At the same time, it is possible to detect a large number of video frames with faces.
  • the preset duration can be preset by the technician and saved in the smart cat's eye.
  • the smart cat eye uses the human body detecting sensor to detect and judge whether there is a human body to control the opening of the camera.
  • the human body detecting sensor detects the human body
  • the smart cat eye opens the camera in time to shoot, avoiding the camera always turning on and causing more power loss, which can effectively save energy.
  • Step 104 Detecting a video frame of a face in the captured video.
  • the smart cat eye can decompose the captured video in units of frames to obtain N pictures, and the smart cat eye can detect the video frame of the face in the captured video by performing face analysis on the N pictures.
  • N is a positive integer.
  • the smart cat's eye can also be assisted by the human body detecting sensor.
  • the smart cat eye controls the human body detecting sensor to perform face detection when the camera is turned on for video shooting, and the human body detecting sensor detects the face.
  • a control signal is generated, and the smart cat's eye marks the current video recording time point when the control signal is detected. In this way, the smart cat's eye can be checked by recording the recorded video when there is a marked video recording.
  • the method of video frames corresponding to the inter-points indirectly realizes detecting the video frames in which the faces are present in the captured video.
  • Step 105 Determine whether a video frame with a face is detected. If yes, go to step 106, otherwise end the process.
  • the smart cat's eye determines that the video frame of the face is detected.
  • the smart cat's eye detects that the number of video frames of the face is equal to 0, the smart cat's eye determines that the video frame with the face is not detected.
  • Step 106 Add a video frame with a face to the first file for saving.
  • the smart cat's eye can capture the video frames of the face in the captured video, and then add these video frames to the first file for storage.
  • the smart cat's eye can detect a video frame with a face, the video frame is captured and added to the first file for storage.
  • the smart cat eye does not impose any restrictions on the specific form in which the video frame of the face is added to the first file for saving.
  • the photographing apparatus detects a video frame in which a face exists in the captured video, so as to capture the video frame in which the face exists, and save the captured video, so that the captured video can be performed in the form of a picture. Saving not only reduces the storage space required, but also reduces the difficulty of file backup or transfer sharing, and the saved pictures are pictures with key information of the human body, and the use value is high.
  • the second embodiment of the present application relates to a smart photographing method, and the specific process is as shown in FIG. 2 .
  • the second embodiment is improved on the basis of the first embodiment, and the main improvement is: in the second embodiment of the present invention
  • the smart cat's eye will also select M video frames to save according to certain selection rules, so as to ensure that each time a person in the preset detection area is detected, the corresponding file can be saved. The problem of missing documents.
  • Steps 201 to 203 in this embodiment are substantially the same as steps 101 to 103 in the first embodiment, and steps 206 to 208 are substantially the same as steps 104 to 106 in the first embodiment. This is not repeated here.
  • the following sections explain the different parts:
  • Step 204 Obtain a grab cycle, and capture M video frames in the video according to the capture cycle.
  • M is a positive integer.
  • the capture cycle may be preset by a user or a technician and saved in the smart camera, so that the smart camera can acquire the capture cycle by calling a pre-stored capture cycle, thereby Capture M video frames in the video.
  • step 205 M video frames are added to the second file for saving.
  • step 209 the second file is used as the final save file.
  • the smart camera when there is no video frame of the face in the captured video, the smart camera will use the second file as the final save file, thereby not only controlling the size of the saved file, but also avoiding the file being saved too large. The situation, and effectively ensure that each time a person is detected in the preset detection area, the corresponding file can be saved, avoiding the problem of missing files.
  • steps 204 to 205 in the smart photography method is not limited. In actual operation, steps 204 through 205 may be moved after step 206, before step 207.
  • the smart camera determines that the video frame of the face is detected, and causes the smart camera to record the time points of each video frame according to the second file.
  • the video frame sets a corresponding time screening interval, so that the smart camera can filter the time interval according to the time, and in the first file, obtain a video frame whose recording time point is within the time screening interval, so that the time screening interval is included in the second file.
  • Corresponding video frame is replaced with a video frame in the first file in which the acquired recording time point is located in the time screening interval, and is replaced by the second file.
  • the final save file is replaced with a video frame in the first file in which the acquired recording time point is located in the time screening interval.
  • the setting rules of the time screening interval can be preset by a technician and saved in the smart camera.
  • the smart shooting device can set the time screening interval centering on the recording time point of the video frame and the left and right amplitudes of 3 s. In this way, in the second file, the smart camera replaces the video frame corresponding to the time screening interval with the first file in the first file, and the acquired recording time point is located in the video frame in the time screening interval.
  • the second file is integrated to replace part of the video frame in the first file with the second file, so that the smart camera replaces the second file as the final saved file, and the final saved file can include
  • a picture with key information of the human body can also contain pictures with other information, which provides a basis for the user to know more valid information according to the final saved file.
  • a third embodiment of the present invention relates to a smart camera, as shown in FIG. 3, comprising: a detection module 1, a control module 2, a first processing module 3, and a storage module 4.
  • the detecting module 1 is configured to detect whether a person is detected in the preset detection area.
  • the preset detection area may be a detection area of the smart cat's eye, for example, a certain geographical range outside the door.
  • the detection module 1 can be a human body detection sensor built into the smart camera.
  • the intelligent camera adopts the detection module 1 to implement the motion detection function, so that the presence of a person in the preset detection area by the motion detection technology can not only reduce the manual monitoring cost of the public institution and the enterprise place, but also avoid The monitoring errors caused by the long-term value of personnel fatigue have greatly improved the monitoring efficiency and monitoring accuracy.
  • the human body detecting sensor may be an infrared sensor, a human body proximity sensor, or the like that can be used to detect the human body.
  • the control module 2 is configured to turn on the camera for video shooting when the detection module 1 detects a person in the preset detection area.
  • the control module 2 controls the camera to capture a video of a preset duration, thereby ensuring the length of the captured video, and the video of the face existing in the captured video by the first processing module 3
  • the preset duration can be preset by the technician and saved in the smart cat's eye.
  • the first processing module 3 is configured to detect a video frame in which a face exists in the captured video, and if a video frame in which a face exists is detected, add the video frame in which the face exists to the first file in the storage module 4 save.
  • the first processing module 3 may decompose the captured video in units of frames to obtain N pictures, and the first processing module 3 performs face analysis on the N pictures to realize the presence of a face in the captured video.
  • the video frame is detected.
  • N is a positive integer.
  • the first processing module 3 can also perform auxiliary detection by the human body detecting sensor.
  • the first processing module 3 controls the human body detecting sensor to perform face detection when the control module 2 turns on the camera for video shooting, and the human body detecting sensor When a face is detected, a control signal is generated, and the first processing module 3 marks the current video recording time point when the control signal is detected. In this way, the first processing module 3 can indirectly detect the video frame in which the face exists in the captured video by checking the video frame corresponding to the marked video recording time point in the captured video.
  • the first processing module 3 determines that the video frame in which the face exists is detected, and the video frame of the face exists. It is added to the first file of the storage module 4 for saving.
  • the first processing module 3 detects that the number of video frames of the face is equal to 0, the first processing module 3 determines that the video frame in which the face exists is not detected.
  • the first processing module 3 can capture the video frames of the face in the captured video, and then add the video frames to the first file of the storage module 4 for storage.
  • the video frame may be captured and added to the first file of the storage module 4 for storage.
  • the first processing module 3 adds the video frame in which the face exists to the first file of the storage module 4 for saving.
  • This embodiment is an apparatus embodiment corresponding to the first embodiment, and this embodiment can be implemented in cooperation with the first embodiment.
  • the related technical details mentioned in the first embodiment are still effective in this embodiment, and are not described herein again in order to reduce repetition. Accordingly, the related art details mentioned in the embodiment can also be applied to the first embodiment.
  • each module involved in this embodiment is a logic module.
  • a logical unit may be a physical unit, a part of a physical unit, or multiple physical entities. A combination of units is implemented.
  • the unit that is not closely related to the technical problem of the present embodiment is not introduced in this embodiment, but this does not mean that there are no other units in this embodiment.
  • the fourth embodiment of the present application relates to a smart camera device, as shown in FIG.
  • the fourth embodiment is improved on the basis of the third embodiment.
  • the main improvement is that in the fourth embodiment of the present application, the smart camera further includes: a second processing module 5.
  • the second processing module 5 is configured to acquire a capture period, and capture M video frames in the video according to the capture period. Where M is a positive integer.
  • the second processing module 5 is further configured to add M video frames to the second file of the storage module 4 for storage.
  • the capture cycle may be preset by the user or the technician and saved in the second processing module 5, so that the second processing module 5 can acquire the capture cycle by calling the pre-stored capture cycle, thereby Take the period and grab M video frames in the video.
  • the storage module 4 when the first processing module 3 detects that the captured video does not have a video frame of the face, the storage module 4 is further configured to use the second file as the final saved file, thereby controlling not only the saved file.
  • the size of the file avoids the situation that the saved file is too large, and effectively ensures that each time a person is detected in the preset detection area, the corresponding file can be saved, thereby avoiding the problem of missing the file. .
  • the smart camera device may further include: a third processing module.
  • the third processing module is configured to: when the first processing module 3 detects the video frame of the presence of the face, according to the second text In the piece, at the recording time point of each video frame, a corresponding time screening interval is set for each video frame, so that the third processing module can filter the interval according to the time, and in the first file, the recording time point is located in the time screening interval. a video frame, so that the third processing module can replace, in the second file, the video frame corresponding to the time screening interval with the video frame in the first file, the acquired recording time point is located in the time screening interval, and control the storage.
  • Module 4 takes the replaced second file as the final save file.
  • the setting rules of the time screening interval can be preset by the technician and saved in the third processing module.
  • the third processing module may set the time screening interval centering on the recording time point of the video frame and the left and right amplitudes of 3 s.
  • the third processing module replaces the video frame corresponding to the time screening interval with the first time in the first file, and the obtained recording time point is located in the video frame in the time screening interval, which is equivalent to the first
  • the file and the second file are integrated, so that part of the video frame in the first file is replaced with the second file, so that the storage module 4 can replace the second file as the final saved file, and the final saved file can
  • the inclusion of images with key information of the human body, as well as the inclusion of images with other information provides the basis for the user to learn more valid information based on the final saved file.
  • the present embodiment can be implemented in cooperation with the second embodiment.
  • the related technical details mentioned in the second embodiment are still effective in this embodiment, and the technical effects that can be achieved in the second embodiment are also implemented in the present embodiment. To reduce repetition, details are not described herein again. Accordingly, the related art details mentioned in the embodiment can also be applied to the second embodiment.
  • One embodiment of the present application provides a non-volatile computer storage medium storing computer-executable instructions that, when executed by at least one processor, cause the at least one processing The processing method in any of the above embodiments is performed.
  • FIG. 5 is a schematic structural diagram of hardware of an electronic device provided in an embodiment of the present application. As shown in FIG. 5, the device includes:
  • processor PRSs and a memory STM are exemplified by one processor PRS in FIG.
  • the device may further include: an input device IPA and an output device OPA.
  • the processor PRS, the memory STM, the input device IPA, and the output device OPA may be connected by a bus or the like, and the bus connection is taken as an example in FIG.
  • the memory STM is a non-volatile computer readable storage medium that can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to embodiments of the methods of the present application (eg, The detection module 1, the control module 2, the first processing module 3, the second processing module 5, and the storage module 4) shown in FIG. 3 and FIG.
  • the processor PRS performs various functional applications and data processing of the server by executing non-volatile software programs, instructions, and modules stored in the memory STM, that is, the processing method of the above method embodiments.
  • the memory STM may include a storage program area and an storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created by use of the smart photography device, and the like. Further, the memory STM may include a high speed random access memory, and may also include a nonvolatile memory such as at least one magnetic disk storage device, flash memory device, or other nonvolatile solid state storage device. In some embodiments, the memory STM can optionally include memory remotely located relative to the processor PRS, which can be connected to the smart camera via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the input device IPA can receive input digital or character information, as well as key signal input.
  • the output device OPA may include a display device such as a display screen.
  • the one or more modules are stored in the memory STM, and when executed by the one or more processors PRS, perform the processing method in any of the above method embodiments.
  • the electronic device of the embodiment of the present application exists in various forms, including but not limited to:
  • Mobile communication equipment This type of equipment is characterized by its mobile communication function and Sound and data communication are the main goals.
  • Such terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.
  • Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has mobile Internet access.
  • Such terminals include: PDAs, MIDs, and UMPC devices, such as the iPad.
  • Portable entertainment devices These devices can display and play multimedia content. Such devices include: audio, video players (such as iPod), handheld game consoles, e-books, and smart toys and portable car navigation devices.
  • the server consists of a processor, a hard disk, a memory, a system bus, etc.
  • the server is similar to a general-purpose computer architecture, but because of the need to provide highly reliable services, processing power and stability High reliability in terms of reliability, security, scalability, and manageability.
  • the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, ie may be located A place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • a program instructing related hardware may be completed by a program instructing related hardware, and the program is stored in a storage medium, and includes a plurality of instructions for making a device (which may be a single chip microcomputer). , a chip, etc. or a processor performs all or part of the steps of the methods described in various embodiments of the present application.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Television Signal Processing For Recording (AREA)
  • Studio Devices (AREA)

Abstract

本申请涉及视频监控领域，公开了一种智能拍摄方法及装置。本申请一个例子中，智能拍摄方法包括：对预设的检测区域内是否有人进行检测；当检测到预设的检测区域内有人时，开启摄像头进行视频拍摄；对拍摄的视频中存在人脸的视频帧进行检测，如果检测到存在人脸的视频帧，则将存在人脸的视频帧添加至第一文件中进行保存。

Description

智能拍摄方法及装置
交叉引用
本申请引用于2016年12月30日递交的名称为“智能拍摄方法及装置”的第201611265912.7号中国专利申请，其通过引用被全部并入本申请。
技术领域
本申请涉及视频监控领域，特别涉及智能拍摄方法及装置。
背景技术
为了实现安防监控、信息分享的需要，具有摄像、拍照或录音等功能的拍摄装置被广泛使用。尤其在安防监控的应用中，一些拍摄装置通常采用24小时全时录制。这种24小时录制的方式，虽然保证了采集到的信息的连续性和完整性，但是图像、音频或视频信息的总量过大，有效信息所占比例较小，存储空间的利用率很低。
目前，为提高存储空间的利用率，通常会通过移动侦测、报警传感器等技术进行辅助监测，以便于在检测到人体时，触发拍摄装置动作，抓拍一定时长的视频进行保存。
发明内容
本发明部分实施例的目的在于提供一种智能拍摄方法及装置，使得拍摄装置能够选取出拍摄的视频中，存在人脸的视频帧并进行保存，所保存的内容的使用价值较高且需要占用的存储空间较小，有效地降低了文件备份或转移分享的难度。
为解决上述技术问题，本申请的一个实施例提供了一种智能拍摄方法，包括：
对预设的检测区域内是否有人进行检测；
当检测到预设的检测区域内有人时，开启摄像头进行视频拍摄；
对拍摄的视频中存在人脸的视频帧进行检测，如果检测到存在人脸的视频帧，则将存在人脸的视频帧添加至第一文件中进行保存。
本申请的一个实施例还提供了一种智能拍摄装置，包括：检测模块、控制模块、第一处理模块以及存储模块；
检测模块用于对预设的检测区域内是否有人进行检测；
控制模块用于在检测模块检测到预设的检测区域内有人时，开启摄像头进行视频拍摄；
第一处理模块用于对拍摄的视频中存在人脸的视频帧进行检测，如果检测到存在人脸的视频帧，则将存在人脸的视频帧添加至存储模块的第一文件中进行保存。
本申请部分实施例相对于现有技术而言，拍摄装置在检测到预设的检测区域内有人时，便开启摄像头进行视频拍摄，以便于及时地将当前情况记录下来，不仅能降低公共机构和企业场所的人工监控成本，而且能够避免人员长期值守疲劳导致的监察失误，极大地提高了监控效率和监控精度。并且，拍摄装置还对拍摄的视频中存在人脸的视频帧进行检测，以便于抓取出存在人脸的视频帧进行保存，从而能够将拍摄的视频以图片的形式进行保存，不仅缩小了所需要占用的存储空间，降低了文件备份或转移分享的难度，而且所保存的图片都是具有人体关键信息的图片，使用价值较高。
本申请的一个实施例中，开启摄像头进行视频拍摄后，还包括：获取抓取周期，并根据抓取周期，在视频中抓取M张视频帧；其中，M为正整数；将M张视频帧添加至第二文件中进行保存；如果未检测到存在人脸的视频帧，则将第二文件作为最终的保存文件。这样，在拍摄的视频中，不存在人脸的视频帧时，拍摄装置会按照一定的选取规则，选取出M张视频帧进行保存，从而不仅控制了所保存的文件的大小，避免了被保存的文件过大的情况，而且有效地 保证了每次在检测到预设的检测区域内有人时，均能够有对应的文件被保存下来，避免了文件的缺失问题。
本申请的一个实施例中，智能拍摄方法还包括：如果检测到存在人脸的视频帧，则根据第二文件中，各视频帧的录制时间点，为各视频帧设置对应的时间筛选区间；根据时间筛选区间，在第一文件中，获取录制时间点位于时间筛选区间内的视频帧；在第二文件中，将时间筛选区间对应的视频帧，替换成在第一文件中，获取的录制时间点位于时间筛选区间内的视频帧；以替换后的第二文件，作为最终的保存文件。通过这种方式，将第一文件以及第二文件进行整合，使得最终的保存文件既能够包含具有人体关键信息的图片，又能够包含具有其他信息的图片，为用户能够根据最终的保存文件，了解到较多的有效信息提供了基础。
本申请的一个实施例中，开启摄像头进行视频拍摄，可包括：控制摄像头拍摄预设时长的视频。这样，从而保证了所拍摄的视频的长度，为后续对拍摄的视频中存在人脸的视频帧进行检测时，能够检测出数量较多的存在人脸的视频帧提供了基础。
本申请的一个实施例提供了一种计算机可读存储介质，包括计算机可执行指令，所述计算机可执行指令在由至少一个处理器执行时致使所述处理器执行上述方法。
本申请的一个实施例提供了一种电子设备，包括：至少一个处理器；以及存储器；其中，所述存储器存储有可被所述至少一个处理器执行的程序，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行上述方法。
本申请的一个实施例中，对预设的检测区域内是否有人进行检测，可包括：通过移动侦测技术，对预设的检测区域内是否有人进行检测。这样，提供了对预设的检测区域内是否有人进行检测的一种具体实现形式，增加了可行性。
附图说明
一个或多个实施例通过与之对应的附图中的图片进行示例性说明，这些示例性说明并不构成对实施例的限定，附图中具有相同参考数字标号的元件表示为类似的元件，除非有特别申明，附图中的图不构成比例限制。
图1是根据本申请第一实施例中智能拍摄方法的流程图；
图2是根据本申请第二实施例中智能拍摄方法的流程图；
图3是根据本申请第三实施例中智能拍摄装置的结构示意图；
图4是根据本申请第四实施例中智能拍摄装置的结构示意图。
具体实施方式
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明部分实施例进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。
发明人发现目前技术中至少存在如下缺陷：在现有技术中，由于拍摄装置只能抓拍一定时长的视频，且人体移动具有不确定性，因此很容易出现拍摄装置抓拍的视频中，没有人或者没有拍摄到人体关键信息(如，人体相貌)的情况，从而导致抓拍的视频的使用价值不高。但是，如果改变拍摄装置抓拍的时间，让拍摄装置在有人在的整个事件中都进行抓拍，又会导致抓拍到的视频文件过大，增加了文件备份或转移分享的难度。
本申请的第一实施例涉及一种智能拍摄方法，具体流程如图1所示。本实施例可以在智能拍摄装置的基础上进行实施，智能拍摄装置可以是智能猫眼、行车记录仪、监控器等电子设备，以下以智能拍摄装置为智能猫眼为例进行说明，步骤如下：
步骤101，对预设的检测区域内是否有人进行检测。
例如，智能拍摄装置为智能猫眼时，预设的检测区域便可以为智能猫眼的检测区域，如，门外的一定地域范围。例如，智能猫眼利用内置的人体探测传 感器对门外的一定地域范围进行检测，实现移动侦测功能，智能猫眼通过移动侦测技术，对预设的检测区域内是否有人进行检测，不仅能降低公共机构和企业场所的人工监控成本，而且能够避免人员长期值守疲劳导致的监察失误，极大地提高了监控效率和监控精度。其中，人体探测传感器可以是红外线传感器、人体接近传感器等能够用于探测人体的电子器件。
步骤102，判断是否检测到预设的检测区域内有人。若是，则执行步骤103，否则执行步骤101。
例如，当智能猫眼的人体探测传感器检测到门外的一定地域范围内有人时，判定检测到预设的检测区域内有人。
步骤103，开启摄像头进行视频拍摄。
本实施例中，智能猫眼在开启摄像头进行视频拍摄时，会控制摄像头拍摄预设时长的视频，从而能够保证所拍摄的视频的长度，为后续对拍摄的视频中存在人脸的视频帧进行检测时，能够检测出数量较多的存在人脸的视频帧提供了基础。其中，预设时长可以由技术人员预先设置并保存在智能猫眼中。
不难看出，在步骤102至步骤103中，智能猫眼利用人体探测传感器对是否有人体进行检测并判断，以控制摄像头的开启。当人体探测传感器检测到人体时，智能猫眼及时地开启摄像头进行拍摄，避免了摄像头一直开启造成较多的电能损耗，可有效地起到节约电能的作用。
步骤104，对拍摄的视频中存在人脸的视频帧进行检测。
例如，智能猫眼可以将拍摄的视频以帧为单位进行分解，获取N张图片，智能猫眼通过对N张图片进行人脸分析的方式，实现对拍摄的视频中存在人脸的视频帧进行检测。其中，N为正整数。在一个实施例中，智能猫眼还可以通过人体探测传感器进行辅助检测，例如，智能猫眼在开启摄像头进行视频拍摄时，还控制人体探测传感器进行人脸检测，人体探测传感器在检测到人脸时，生成控制信号，智能猫眼在检测到控制信号时，对当前的视频录制时间点进行标记。这样，智能猫眼便能够通过检查拍摄的视频中，存在标记的视频录制时 间点所对应的视频帧的方式，间接地实现对拍摄的视频中存在人脸的视频帧进行检测。
上述仅为一种举例说明，还可以有其他的人脸视屏帧检测例子，本实施例中并不对拍摄的视频中存在人脸的视频帧进行检测的具体实现形式做任何限制。
步骤105，判断是否检测到存在人脸的视频帧。若是，则执行步骤106，否则结束本流程。
例如，当智能猫眼检测到的视频中，存在人脸的视频帧的个数大于0时，则智能猫眼判定检测到存在人脸的视频帧。当智能猫眼检测到视频中，存在人脸的视频帧的个数等于0时，则智能猫眼判定未检测到存在人脸的视频帧。
步骤106，将存在人脸的视频帧添加至第一文件中进行保存。
例如，智能猫眼可以在将拍摄的视频中，存在人脸的视频帧都抓取出来后，将这些视频帧统一添加至第一文件中进行保存。在实际操作时，智能猫眼也可以在检测到一张存在人脸的视频帧时，则将该视频帧抓取出来，添加至第一文件中进行保存。本实施例中，并不对智能猫眼将存在人脸的视频帧添加至第一文件中进行保存的具体形式做任何限制。
与现有技术相比，本实施例中，拍摄装置在检测到预设的检测区域内有人时，便开启摄像头进行视频拍摄，以便于及时地将当前情况记录下来，不仅能降低公共机构和企业场所的人工监控成本，而且能够避免人员长期值守疲劳导致的监察失误，极大地提高了监控效率和监控精度。并且，本发明实施例中，拍摄装置还对拍摄的视频中存在人脸的视频帧进行检测，以便于抓取出存在人脸的视频帧进行保存，从而能够将拍摄的视频以图片的形式进行保存，不仅缩小了所需要占用的存储空间，降低了文件备份或转移分享的难度，而且所保存的图片都是具有人体关键信息的图片，使用价值较高。
本申请的第二实施例涉及一种智能拍摄方法，具体流程如图2所示。第二实施例在第一实施例的基础上加以改进，主要改进之处在于：在本发明第二实 施例中，智能猫眼还会按照一定的选取规则，选取出M张视频帧进行保存，以保证每次在检测到预设的检测区域内有人时，均能够有对应的文件被保存下来，避免了文件的缺失问题。
本实施例中的步骤201至步骤203与第一实施例中的步骤101至步骤103大致相同，步骤206至步骤208与第一实施例中的步骤104至步骤106大致相同，为减少重复，在此不再赘述，以下对不同部分进行说明：
步骤204，获取抓取周期，并根据抓取周期，在视频中抓取M张视频帧。其中，M为正整数。
例如，抓取周期可以由用户或技术人员预先设置并保存在智能拍摄装置中，以便于智能拍摄装置能够通过调用预先存储的抓取周期的方式，获取抓取周期，从而根据抓取周期，在视频中抓取M张视频帧。
步骤205，将M张视频帧添加至第二文件中进行保存。
步骤209，将第二文件作为最终的保存文件。
例如，当拍摄的视频中，不存在人脸的视频帧时，智能拍摄装置会将第二文件作为最终的保存文件，从而不仅控制了所保存的文件的大小，避免了被保存的文件过大的情况，而且有效地保证了每次在检测到预设的检测区域内有人时，均能够有对应的文件被保存下来，避免了文件的缺失问题。
值得一提的是，本实施例中，并不对步骤204至步骤205在智能拍摄方法中的执行顺序进行限制。在实际操作时，步骤204至步骤205可以挪至步骤206之后，步骤207之前执行。
本实施例中，还可以在步骤207的判断结果为是，智能拍摄装置判定检测到存在人脸的视频帧时，令智能拍摄装置根据第二文件中，各视频帧的录制时间点，为各视频帧设置对应的时间筛选区间，以便于智能拍摄装置能够根据时间筛选区间，在第一文件中，获取录制时间点位于时间筛选区间内的视频帧，从而在第二文件中，将时间筛选区间对应的视频帧，替换成在第一文件中，获取的录制时间点位于时间筛选区间内的视频帧，并以替换后的第二文件，作为 最终的保存文件。
例如，时间筛选区间的设置规则可以由技术人员预先设置并保存在智能拍摄装置中。如，智能拍摄装置可以以视频帧的录制时间点为中心，左右幅度3s，设置时间筛选区间。这样，智能拍摄装置在第二文件中，将时间筛选区间对应的视频帧，替换成在第一文件中，获取的录制时间点位于时间筛选区间内的视频帧时，就相当于将第一文件以及第二文件进行整合，令第一文件中的部分视频帧替换到第二文件中，从而使得智能拍摄装置以替换后的第二文件，作为最终的保存文件时，最终的保存文件既能够包含具有人体关键信息的图片，又能够包含具有其他信息的图片，为用户能够根据最终的保存文件，了解到较多的有效信息提供了基础。
上面各种方法的步骤划分，只是为了描述清楚，实现时可以合并为一个步骤或者对某些步骤进行拆分，分解为多个步骤，只要包含相同的逻辑关系，都在本专利的保护范围内；对算法中或者流程中添加无关紧要的修改或者引入无关紧要的设计，但不改变其算法和流程的核心设计都在该专利的保护范围内。
本发明第三实施例涉及一种智能拍摄装置，如图3所示，包括：检测模块1、控制模块2、第一处理模块3以及存储模块4。
检测模块1用于对预设的检测区域内是否有人进行检测。
例如，智能拍摄装置为智能猫眼时，预设的检测区域便可以为智能猫眼的检测区域，如，门外的一定地域范围。在一个例子中，检测模块1可以为智能拍摄装置内置的人体探测传感器。智能拍摄装置通过检测模块1，实现移动侦测功能，以便于通过移动侦测技术，对预设的检测区域内是否有人进行检测，不仅能降低公共机构和企业场所的人工监控成本，而且能够避免人员长期值守疲劳导致的监察失误，极大地提高了监控效率和监控精度。其中，人体探测传感器可以是红外线传感器、人体接近传感器等能够用于探测人体的电子器件。
控制模块2用于在检测模块1检测到预设的检测区域内有人时，开启摄像头进行视频拍摄。
例如，控制模块2在开启摄像头进行视频拍摄时，会控制摄像头拍摄预设时长的视频，从而能够保证所拍摄的视频的长度，为后续第一处理模块3对拍摄的视频中存在人脸的视频帧进行检测时，能够检测出数量较多的存在人脸的视频帧提供了基础。其中，预设时长可以由技术人员预先设置并保存在智能猫眼中。
第一处理模块3用于对拍摄的视频中存在人脸的视频帧进行检测，如果检测到存在人脸的视频帧，则将存在人脸的视频帧添加至存储模块4的第一文件中进行保存。
例如，第一处理模块3可以将拍摄的视频以帧为单位进行分解，获取N张图片，第一处理模块3通过对N张图片进行人脸分析的方式，实现对拍摄的视频中存在人脸的视频帧进行检测。其中，N为正整数。在实际操作时，第一处理模块3还可以通过人体探测传感器进行辅助检测，如，第一处理模块3在控制模块2开启摄像头进行视频拍摄时，控制人体探测传感器进行人脸检测，人体探测传感器在检测到人脸时，生成控制信号，第一处理模块3在检测到控制信号时，对当前的视频录制时间点进行标记。这样，第一处理模块3便能够通过检查拍摄的视频中，存在标记的视频录制时间点所对应的视频帧的方式，间接地实现对拍摄的视频中存在人脸的视频帧进行检测。
例如，当第一处理模块3检测到的视频中，存在人脸的视频帧的个数大于0时，则第一处理模块3判定检测到存在人脸的视频帧，将存在人脸的视频帧添加至存储模块4的第一文件中进行保存。当第一处理模块3检测到视频中，存在人脸的视频帧的个数等于0时，则第一处理模块3判定未检测到存在人脸的视频帧。
本实施例中，第一处理模块3可以在将拍摄的视频中，存在人脸的视频帧都抓取出来后，将这些视频帧统一添加至存储模块4的第一文件中进行保存。在实际操作时，第一处理模块3也可以在检测到一张存在人脸的视频帧时，则将该视频帧抓取出来，添加至存储模块4的第一文件中进行保存。本实施例中， 并不对第一处理模块3将存在人脸的视频帧添加至存储模块4的第一文件中进行保存的具体形式做任何限制。
本实施例为一种与第一实施例相对应的装置实施例，本实施例可与第一实施例互相配合实施。第一实施例中提到的相关技术细节在本实施例中依然有效，为了减少重复，这里不再赘述。相应地，本实施例中提到的相关技术细节也可应用在第一实施例中。
值得一提的是，本实施例中所涉及到的各模块均为逻辑模块，在实际应用中，一个逻辑单元可以是一个物理单元，也可以是一个物理单元的一部分，还可以以多个物理单元的组合实现。此外，为了便于理解本实施例，本实施例中并没有将与解决本实施例的技术问题关系不太密切的单元引入，但这并不表明本实施例中不存在其它的单元。
本申请第四实施例涉及一种智能拍摄装置，如图4所示。第四实施例在第三实施例的基础上加以改进，主要改进之处在于，在本申请第四实施例中，智能拍摄装置还包括：第二处理模块5。第二处理模块5用于获取抓取周期，并根据抓取周期，在视频中抓取M张视频帧。其中，M为正整数。并且，第二处理模块5还用于将M张视频帧添加至存储模块4的第二文件中进行保存。
例如，抓取周期可以由用户或技术人员预先设置并保存在第二处理模块5中，以便于第二处理模块5能够通过调用预先存储的抓取周期的方式，获取抓取周期，从而根据抓取周期，在视频中抓取M张视频帧。
本实施例中，当第一处理模块3检测到拍摄的视频中，不存在人脸的视频帧时，存储模块4还用于将第二文件作为最终的保存文件，从而不仅控制了所保存的文件的大小，避免了被保存的文件过大的情况，而且有效地保证了每次在检测到预设的检测区域内有人时，均能够有对应的文件被保存下来，避免了文件的缺失问题。
值得一提的是，本实施例中，智能拍摄装置还可以包括：第三处理模块。第三处理模块用于在第一处理模块3检测到存在人脸的视频帧时，根据第二文 件中，各视频帧的录制时间点，为各视频帧设置对应的时间筛选区间，以便于第三处理模块能够根据时间筛选区间，在第一文件中，获取录制时间点位于时间筛选区间内的视频帧，从而令第三处理模块能够在第二文件中，将时间筛选区间对应的视频帧，替换成在第一文件中，获取的录制时间点位于时间筛选区间内的视频帧，并控制存储模块4以替换后的第二文件，作为最终的保存文件。
例如，时间筛选区间的设置规则可以由技术人员预先设置并保存在第三处理模块中。如，第三处理模块可以以视频帧的录制时间点为中心，左右幅度3s，设置时间筛选区间。这样，第三处理模块在第二文件中，将时间筛选区间对应的视频帧，替换成在第一文件中，获取的录制时间点位于时间筛选区间内的视频帧时，就相当于将第一文件以及第二文件进行整合，令第一文件中的部分视频帧替换到第二文件中，从而使得存储模块4以替换后的第二文件，作为最终的保存文件时，最终的保存文件既能够包含具有人体关键信息的图片，又能够包含具有其他信息的图片，为用户能够根据最终的保存文件，了解到较多的有效信息提供了基础。
由于第二实施例与本实施例相互对应，因此本实施例可与第二实施例互相配合实施。第二实施例中提到的相关技术细节在本实施例中依然有效，在第二实施例中所能达到的技术效果在本实施方式中也同样可以实现，为了减少重复，这里不再赘述。相应地，本实施例中提到的相关技术细节也可应用在第二实施例中。
本申请一个实施例中提供了一种非易失性计算机存储介质，所述计算机存储介质存储有计算机可执行指令，该计算机可执行指令在由至少一个处理器执行时可使所述至少一个处理器执行上述任意实施例中的处理方法。
图5是本申请一个实施例中提供的电子设备的硬件结构示意图，如图5所示，该设备包括：
一个或多个处理器PRS以及存储器STM，图5中以一个处理器PRS为例。
在一个例子中，该设备还可以包括：输入装置IPA和输出装置OPA。
处理器PRS、存储器STM、输入装置IPA和输出装置OPA可以通过总线或者其他方式连接，图5中以通过总线连接为例。
存储器STM作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本申请方法实施例对应的程序指令/模块(例如，图3和图4中所示的检测模块1、控制模块2、第一处理模块3、第二处理模块5和存储模块4)。处理器PRS通过运行存储在存储器STM中的非易失性软件程序、指令以及模块，从而执行服务器的各种功能应用以及数据处理，即实现上述方法实施例的处理方法。
存储器STM可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储智能拍摄装置的使用所创建的数据等。此外，存储器STM可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中，存储器STM可选包括相对于处理器PRS远程设置的存储器，这些远程存储器可以通过网络连接至智能拍摄装置。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
输入装置IPA可接收输入的数字或字符信息，以及键信号输入。输出装置OPA可包括显示屏等显示设备。
所述一个或者多个模块存储在所述存储器STM中，当被所述一个或者多个处理器PRS执行时，执行上述任意方法实施例中的处理方法。
上述产品可执行本申请实施例所提供的方法，具备执行方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本申请实施例所提供的方法。
本申请实施例的电子设备以多种形式存在，包括但不限于：
(1)移动通信设备：这类设备的特点是具备移动通信功能，并且以提供话 音、数据通信为主要目标。这类终端包括：智能手机(例如iPhone)、多媒体手机、功能性手机，以及低端手机等。
(2)超移动个人计算机设备：这类设备属于个人计算机的范畴，有计算和处理功能，一般也具备移动上网特性。这类终端包括：PDA、MID和UMPC设备等，例如iPad。
(3)便携式娱乐设备：这类设备可以显示和播放多媒体内容。该类设备包括：音频、视频播放器(例如iPod)，掌上游戏机，电子书，以及智能玩具和便携式车载导航设备。
(4)服务器：提供计算服务的设备，服务器的构成包括处理器、硬盘、内存、系统总线等，服务器和通用的计算机架构类似，但是由于需要提供高可靠的服务，因此在处理能力、稳定性、可靠性、安全性、可扩展性、可管理性等方面要求较高。
(5)其他具有数据交互功能的电子装置。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
本领域技术人员可以理解实现上述实施例方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序存储在一个存储介质中，包括若干指令用以使得一个设备(可以是单片机，芯片等)或处理器(processor)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
本领域的普通技术人员可以理解，上述记载的各实施例是实现本发明的部分实施例，而在实际应用中，依然可以对前述各实施例所记载的技术方案进行 修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (12)

  1. 一种智能拍摄方法，包括：
    对预设的检测区域内是否有人进行检测；
    当检测到所述预设的检测区域内有人时，开启摄像头进行视频拍摄；
    对拍摄的视频中存在人脸的视频帧进行检测，如果检测到存在人脸的视频帧，则将所述存在人脸的视频帧添加至第一文件中进行保存。
  2. 根据权利要求1所述的智能拍摄方法，其中所述开启摄像头进行视频拍摄后，还包括：
    获取抓取周期，并根据所述抓取周期，在所述视频中抓取M张视频帧；其中，所述M为正整数；
    将所述M张视频帧添加至第二文件中进行保存；
    如果未检测到存在人脸的视频帧，则将所述第二文件作为最终的保存文件。
  3. 根据权利要求2所述的智能拍摄方法，还包括：
    如果检测到存在人脸的视频帧，则根据所述第二文件中，各视频帧的录制时间点，为各视频帧设置对应的时间筛选区间；
    根据所述时间筛选区间，在所述第一文件中，获取录制时间点位于所述时间筛选区间内的视频帧；
    在所述第二文件中，将所述时间筛选区间对应的视频帧，替换成在所述第一文件中，获取的所述录制时间点位于所述时间筛选区间内的视频帧；
    以替换后的所述第二文件，作为最终的保存文件。
  4. 根据权利要求1到3任一项所述的智能拍摄方法，其中所述开启摄像头进行视频拍摄，包括：
    控制摄像头拍摄预设时长的视频。
  5. 根据权利要求1到4任一项所述的智能拍摄方法，其中所述对预设的检测区域内是否有人进行检测，包括：
    通过移动侦测技术，对预设的检测区域内是否有人进行检测。
  6. 一种智能拍摄装置，包括：检测模块、控制模块、第一处理模块以及存储模块；
    所述检测模块用于对预设的检测区域内是否有人进行检测；
    所述控制模块用于在所述检测模块检测到所述预设的检测区域内有人时，开启摄像头进行视频拍摄；
    所述第一处理模块用于对拍摄的视频中存在人脸的视频帧进行检测，如果检测到存在人脸的视频帧，则将所述存在人脸的视频帧添加至存储模块的第一文件中进行保存。
  7. 根据权利要求6所述的智能拍摄装置，还包括：第二处理模块；
    第二处理模块用于获取抓取周期，并根据所述抓取周期，在所述视频中抓取M张视频帧；其中，所述M为正整数；
    所述第二处理模块还用于将所述M张视频帧添加至所述存储模块的第二文件中进行保存；
    其中，如果所述第一处理模块未检测到存在人脸的视频帧，则所述存储模块将所述第二文件作为最终的保存文件。
  8. 根据权利要求7所述的智能拍摄装置，还包括：第三处理模块；
    所述第三处理模块用于在所述第一处理模块检测到存在人脸的视频帧时，根据所述第二文件中，各视频帧的录制时间点，为各视频帧设置对应的时间筛选区间；
    所述第三处理模块还用于根据所述时间筛选区间，在所述第一文件中，获取录制时间点位于所述时间筛选区间内的视频帧；
    所述第三处理模块还用于在所述第二文件中，将所述时间筛选区间对应的视频帧，替换成在所述第一文件中，获取的所述录制时间点位于所述时间筛选区间内的视频帧，并控制所述存储模块以替换后的所述第二文件，作为最终的保存文件。
  9. 根据权利要求6到8任一项所述的智能拍摄装置，其中，
    所述控制模块用于在所述检测模块检测到所述预设的检测区域内有人时，控制摄像头拍摄预设时长的视频。
  10. 根据权利要求6到9任一项所述的智能拍摄装置，其中，所述检测模块通过移动侦测技术，对预设的检测区域内是否有人进行检测。
  11. 一种计算机可读存储介质，包括计算机可执行指令，所述计算机可执行指令在由至少一个处理器执行时致使所述处理器执行如权利要求1-5任一项所述的方法。
  12. 一种电子设备，包括：
    至少一个处理器；以及存储器；
    其中，所述存储器存储有可被所述至少一个处理器执行的程序，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如权利要求1-5 任一项所述的方法。
PCT/CN2017/088500 2016-12-30 2017-06-15 智能拍摄方法及装置 WO2018120673A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
DE112017006669.7T DE112017006669T5 (de) 2016-12-30 2017-06-15 Intelligentes aufnahmeverfahren und -gerät

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201611265912.7 2016-12-30
CN201611265912.7A CN106791424B (zh) 2016-12-30 2016-12-30 智能拍摄方法及装置

Publications (1)

Publication Number Publication Date
WO2018120673A1 true WO2018120673A1 (zh) 2018-07-05

Family

ID=58951866

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/088500 WO2018120673A1 (zh) 2016-12-30 2017-06-15 智能拍摄方法及装置

Country Status (3)

Country Link
CN (1) CN106791424B (zh)
DE (1) DE112017006669T5 (zh)
WO (1) WO2018120673A1 (zh)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110300066A (zh) * 2019-05-24 2019-10-01 浙江新再灵科技股份有限公司 图片管理服务方法
CN110363080A (zh) * 2019-06-05 2019-10-22 平安科技（深圳）有限公司 基于人脸识别的黄牛识别方法、装置、终端及存储介质
CN111464864A (zh) * 2020-04-02 2020-07-28 Oppo广东移动通信有限公司 倒序视频获取方法、装置、电子设备以及存储介质
CN111539295A (zh) * 2020-04-17 2020-08-14 中移（杭州）信息技术有限公司 人脸识别方法、装置、系统、网络设备及存储介质
CN112040278A (zh) * 2020-09-16 2020-12-04 成都市喜爱科技有限公司 视频处理方法、装置、拍摄终端、服务器及存储介质
CN113723369A (zh) * 2021-11-01 2021-11-30 北京创米智汇物联科技有限公司 控制方法、装置、电子设备及存储介质
CN114283496A (zh) * 2021-12-17 2022-04-05 深圳市安佳威视信息技术有限公司 一种智能防人脸过曝摄像机模组

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106791424B (zh) * 2016-12-30 2019-06-04 移康智能科技（上海）股份有限公司 智能拍摄方法及装置
CN107666573A (zh) * 2017-10-13 2018-02-06 北京奇虎科技有限公司 摄像头场景下对象视频的录制方法及装置、计算设备
CN109905595B (zh) * 2018-06-20 2021-07-06 成都市喜爱科技有限公司 一种拍摄及播放的方法、装置、设备及介质
US11627248B2 (en) 2019-02-03 2023-04-11 Chengdu Sioeye Technology Co., Ltd. Shooting method for shooting device, and electronic equipment
CN111866366A (zh) * 2019-04-30 2020-10-30 百度时代网络技术（北京）有限公司 用于发送信息的方法和装置
CN110225309B (zh) * 2019-06-19 2021-04-23 中信梧桐港供应链管理有限公司 用于仓库监管的视频存储方法、系统及云端服务器
CN110558966A (zh) * 2019-08-12 2019-12-13 平安科技（深圳）有限公司 一种脉搏检测装置
CN111784896B (zh) * 2020-06-17 2021-02-23 深圳南亿科技股份有限公司 一种门禁监控图像存储方法、系统和存储介质
CN112218025A (zh) * 2020-09-02 2021-01-12 北京迈格威科技有限公司 一种数据处理方法、装置、服务器及存储介质
CN112422772B (zh) * 2020-10-23 2023-12-01 深圳市优必选科技股份有限公司 图像获取方法、图像获取装置、终端设备及可读存储介质
CN114359875B (zh) * 2022-03-17 2022-05-17 成都考拉悠然科技有限公司 车辆有效抓拍方法及系统

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201699888U (zh) * 2010-06-24 2011-01-05 柯名会 人脸识别监控装置
CN101951488A (zh) * 2010-09-07 2011-01-19 潘国平 数字视频监控系统对视频进行抽帧备份的方法及系统
CN202383713U (zh) * 2011-09-17 2012-08-15 广州大学 一种人脸图像捕捉与存档装置
CN103297755A (zh) * 2013-05-13 2013-09-11 广东欧珀移动通信有限公司 视频监控方法及视频监控终端
CN104639907A (zh) * 2015-02-04 2015-05-20 惠州Tcl移动通信有限公司 一种基于移动终端的智能安防方法及系统
US20160026855A1 (en) * 2014-07-28 2016-01-28 Centre For Development Of Advanced Computing (C-Dac) Apparatus for Automated Monitoring of Facial Images and a Process Therefor
CN205566477U (zh) * 2016-02-17 2016-09-07 成都理工大学 低功耗人脸监控器
CN106791424A (zh) * 2016-12-30 2017-05-31 移康智能科技（上海）股份有限公司 智能拍摄方法及装置

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201699888U (zh) * 2010-06-24 2011-01-05 柯名会 人脸识别监控装置
CN101951488A (zh) * 2010-09-07 2011-01-19 潘国平 数字视频监控系统对视频进行抽帧备份的方法及系统
CN202383713U (zh) * 2011-09-17 2012-08-15 广州大学 一种人脸图像捕捉与存档装置
CN103297755A (zh) * 2013-05-13 2013-09-11 广东欧珀移动通信有限公司 视频监控方法及视频监控终端
US20160026855A1 (en) * 2014-07-28 2016-01-28 Centre For Development Of Advanced Computing (C-Dac) Apparatus for Automated Monitoring of Facial Images and a Process Therefor
CN104639907A (zh) * 2015-02-04 2015-05-20 惠州Tcl移动通信有限公司 一种基于移动终端的智能安防方法及系统
CN205566477U (zh) * 2016-02-17 2016-09-07 成都理工大学 低功耗人脸监控器
CN106791424A (zh) * 2016-12-30 2017-05-31 移康智能科技（上海）股份有限公司 智能拍摄方法及装置

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110300066A (zh) * 2019-05-24 2019-10-01 浙江新再灵科技股份有限公司 图片管理服务方法
CN110363080A (zh) * 2019-06-05 2019-10-22 平安科技（深圳）有限公司 基于人脸识别的黄牛识别方法、装置、终端及存储介质
CN111464864A (zh) * 2020-04-02 2020-07-28 Oppo广东移动通信有限公司 倒序视频获取方法、装置、电子设备以及存储介质
CN111539295A (zh) * 2020-04-17 2020-08-14 中移（杭州）信息技术有限公司 人脸识别方法、装置、系统、网络设备及存储介质
CN112040278A (zh) * 2020-09-16 2020-12-04 成都市喜爱科技有限公司 视频处理方法、装置、拍摄终端、服务器及存储介质
CN113723369A (zh) * 2021-11-01 2021-11-30 北京创米智汇物联科技有限公司 控制方法、装置、电子设备及存储介质
CN113723369B (zh) * 2021-11-01 2022-02-08 北京创米智汇物联科技有限公司 控制方法、装置、电子设备及存储介质
CN114283496A (zh) * 2021-12-17 2022-04-05 深圳市安佳威视信息技术有限公司 一种智能防人脸过曝摄像机模组

Also Published As

Publication number Publication date
DE112017006669T5 (de) 2020-05-14
CN106791424B (zh) 2019-06-04
CN106791424A (zh) 2017-05-31

Similar Documents

Publication Publication Date Title
WO2018120673A1 (zh) 智能拍摄方法及装置
TWI765304B (zh) 圖像重建方法及圖像重建裝置、電子設備和電腦可讀儲存媒體
CN110659397B (zh) 一种行为检测方法、装置、电子设备和存储介质
US10165201B2 (en) Image processing method and apparatus and terminal device to obtain a group photo including photographer
US20130088616A1 (en) Image Metadata Control Based on Privacy Rules
TW202219792A (zh) 學情分析方法及裝置、電子設備和儲存媒體
KR101606511B1 (ko) 멀티미디어 객체들의 동시 업로드 및 멀티미디어 객체와 메타데이터의 연관
US9563643B2 (en) Automatic metatagging in images
US10332243B2 (en) Tampering detection for digital images
US10805576B2 (en) Systems and methods for generating an audit trail for auditable devices
CN104519316A (zh) 监视系统、监视方法、监视程序、及记录介质
WO2021169616A1 (zh) 非活体人脸的检测方法、装置、计算机设备及存储介质
US20200145573A1 (en) Network device, image processing method, and computer readable medium
WO2020052062A1 (zh) 检测方法和装置
WO2018219304A1 (zh) 照片处理方法、装置、计算机可读存储介质及电子设备
Landa et al. Implementation of a Remote Real-Time Surveillance Security System for Intruder Detection
TWI589158B (zh) 監控資料的原始畫面儲存系統及其儲存方法
US10832369B2 (en) Method and apparatus for determining the capture mode following capture of the content
CN117095456A (zh) 考试行为的检测方法、装置、电子设备和存储介质
CN106973232A (zh) 一种终端摄像头控制方法和装置
WO2023005662A1 (zh) 图像处理方法及装置、电子设备、程序产品及计算机可读存储介质
US20230209172A1 (en) Subject photographing device and method therefor
US20140016013A1 (en) Image capture method
CN111209050A (zh) 用于切换电子设备的工作模式的方法和装置
CN112843678B (zh) 拍摄图像的方法、装置、电子设备及存储介质

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: 17886483

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 17886483

Country of ref document: EP

Kind code of ref document: A1