WO2023124385A1 - 摄像装置遮挡检测方法、装置、电子设备、存储介质及计算机程序产品 - Google Patents
摄像装置遮挡检测方法、装置、电子设备、存储介质及计算机程序产品 Download PDFInfo
- Publication number
- WO2023124385A1 WO2023124385A1 PCT/CN2022/124934 CN2022124934W WO2023124385A1 WO 2023124385 A1 WO2023124385 A1 WO 2023124385A1 CN 2022124934 W CN2022124934 W CN 2022124934W WO 2023124385 A1 WO2023124385 A1 WO 2023124385A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image frame
- current image
- camera
- pixel
- preset
- Prior art date
- Legal status (The legal status 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 status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/467—Encoded features or binary features, e.g. local binary patterns [LBP]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Definitions
- Embodiments of the present disclosure relate to the technical field of image processing, and in particular, to a camera device occlusion detection method, device, electronic equipment, storage medium, and computer program product.
- the camera device in the cabin can be used to restrain the driver's driving behavior, thereby reducing the probability of traffic accidents, thereby assisting in improving Driving safety.
- the camera will be blocked, and if the camera is blocked, the driver's behavior cannot be accurately detected. Accuracy is particularly important.
- Embodiments of the present disclosure at least provide a method, device, electronic device, storage medium, and computer program product for occlusion detection of an imaging device, which can not only implement occlusion detection for an imaging device, but also improve detection accuracy.
- An embodiment of the present disclosure provides an occlusion detection method for a camera device, including:
- the preset feature encoding information includes feature encoding of an image frame containing a human face in the video data information.
- An embodiment of the present disclosure provides an occlusion detection device for a camera device, including:
- the video acquisition module is configured to acquire the video data of the driving area of the vehicle through the camera device;
- the face detection module is configured to perform face detection on the current image frame in the video data, and encode the current image frame according to the pixel value in the current image frame if no face is detected , to obtain the feature encoding information of the current image frame;
- the occlusion determination module is configured to determine whether the camera is occluded based on the feature encoding information of the current image frame and preset feature encoding information, wherein the preset feature encoding information includes that the video data contains a human face The feature encoding information of the image frame.
- An embodiment of the present disclosure provides an electronic device, including: a processor, a memory, and a bus.
- the memory stores machine-readable instructions executable by the processor.
- the processor and the The memories communicate with each other through a bus, and when the machine-readable instructions are executed by the processor, the camera-device occlusion detection method as described in any of the foregoing implementation manners is executed.
- An embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is run by a processor, the camera-device occlusion detection method as described in any of the preceding implementation modes is executed. .
- An embodiment of the present disclosure also provides a computer program product, including a computer-readable storage medium storing program codes, and when instructions included in the program codes are executed by a processor of a computer device, the steps of the above method are implemented.
- the current image is processed according to the pixel values in the current image frame. frame to obtain the feature encoding information of the current image frame, and based on the feature encoding information of the current image frame and the preset feature encoding information, it is judged whether the camera is blocked. In the case of a face, further judgment is made on the image, which can improve the accuracy of judgment.
- FIG. 1 shows a schematic flowchart of a method for detecting an occlusion of a camera device provided by an embodiment of the present disclosure
- FIG. 2 shows a schematic flowchart of a method for determining feature coding information of a current image frame provided by an embodiment of the present disclosure
- FIG. 3 shows a schematic flow chart of another camera device occlusion detection method provided by an embodiment of the present disclosure
- FIG. 4 shows a schematic flowchart of a method for outputting prompt information provided by an embodiment of the present disclosure
- FIG. 5 shows a schematic flowchart of another method for occlusion detection of a camera device provided by an embodiment of the present disclosure
- FIG. 6 shows a schematic structural diagram of an occlusion detection device for a camera device provided by an embodiment of the present disclosure
- FIG. 7 shows a schematic structural diagram of another camera device occlusion detection device provided by an embodiment of the present disclosure.
- Fig. 8 shows a schematic diagram of an electronic device provided by an embodiment of the present disclosure.
- the camera device in the cabin can be used to restrain the driver's driving behavior, thereby reducing the probability of traffic accidents, thereby assisting in improving Driving safety.
- the camera may be blocked, and if the camera is blocked, the behavior of the driver cannot be accurately detected.
- the present disclosure provides a camera occlusion detection method, which includes: acquiring video data of the driving area of the vehicle through the camera device; performing face detection on the current image frame in the video data, and In the case of a human face, encode the current image frame according to the pixel values in the current image frame to obtain the feature encoding information of the current image frame; based on the feature encoding information of the current image frame and preset The feature encoding information is used to determine whether the camera is blocked, wherein the preset feature encoding information includes feature encoding information of an image frame containing a human face in the video data.
- the current image frame is encoded according to the pixel values in the current image frame to obtain the feature encoding information of the current image frame, and based on the The feature coding information of the current image frame and the preset feature coding information determine whether the camera is blocked. In this way, the image can be further judged when no face is recognized, thereby improving the accuracy of judgment.
- FIG. 1 it is a schematic flowchart of a method for detecting occlusion of a camera device provided by an embodiment of the present disclosure.
- the method for occlusion detection of a camera device includes the following steps S101 to S103:
- the driving area refers to the area in the vehicle where the driver controls the driving of the vehicle.
- the driver is usually located in the driving area of the vehicle, and the terminal device can acquire the video data of the driving area of the vehicle.
- Video data refers to a continuous image sequence, which is essentially composed of a group of continuous images.
- an image frame is the smallest visual unit that makes up a video, and is a static image.
- a sequence of temporally continuous image frames is synthesized to form a dynamic video.
- it is necessary to extract image frames in the video data.
- frame extraction refers to frame extraction according to the preset interval frame number, for example, extracting a frame of image every 20 frames; it can also perform frame extraction according to the preset time interval, such as every interval of 10 milliseconds (ms) Fetch the image once.
- ms milliseconds
- preset interval frame number and interval time can be set according to actual needs, and are not limited here.
- the video data of the driving area may be captured by a camera device installed inside the vehicle, and then the terminal device acquires the video data captured by the camera device.
- the subject of execution of the camera occlusion detection method may be a terminal device, wherein the terminal device includes but not limited to a vehicle-mounted device, a wearable device, a user terminal, and a handheld device.
- the subject of execution of the camera occlusion detection method may also be a server, wherein the server may be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or may provide Cloud servers for basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data and artificial intelligence platforms.
- server may be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or may provide Cloud servers for basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data and artificial intelligence platforms.
- the camera occlusion detection method may also be implemented in a manner in which a processor invokes computer-readable instructions stored in a memory.
- the current image frame refers to the image frame that needs to be detected and recognized currently.
- the image frame in the video data whose timing is before the current image frame is called the previous image frame, and the image frame whose timing is after the current image frame is called the subsequent image. frame.
- face detection may be performed on the extracted images to determine whether there is a face in the current image frame.
- a human face is detected in the current image frame, it means that the driver is in the driving area at this time, and the camera device is not blocked; Make further judgments to improve the accuracy of judgment.
- the current image frame is further encoded according to the pixel values in the current image frame to obtain feature encoding information of the current image frame.
- the step of encoding the current image frame according to the pixel values in the current image frame may include the following S1021 and S1022:
- the reference pixel threshold is the average pixel value of the current image frame.
- the feature encoding information obtained based on the reference pixel threshold can have a unique correspondence with the current image frame, which can further improve The accuracy of judgment.
- the reference pixel threshold can also be set according to actual conditions, for example, the corresponding reference pixel threshold can be determined according to the overall brightness of the current image, rather than the average pixel value of the current image frame.
- noise reduction processing may be performed on the current image frame, thereby reducing the impact of imaging noise.
- a Gaussian smoothing algorithm may be used to perform noise reduction processing on the current image frame.
- the noise reduction processing may also use a median filtering algorithm or an average filtering algorithm to perform the noise reduction processing, which is not limited here.
- the current image frame can be encoded according to the reference pixel threshold, and the encoding process can be to encode pixels greater than the reference pixel threshold as 1, and encode pixels not greater than the The pixel point of the reference pixel threshold is encoded as 0, and then the feature encoding information is obtained.
- the feature encoding information may be a two-dimensional array or a two-dimensional matrix having the same size as the current image frame to be encoded.
- the average pixel of the current image frame is 100, if the pixel value of a certain pixel in the current image frame is 123, the pixel is coded as 1, and if a certain pixel in the current image frame If the pixel value of the point is 80, the pixel point is coded as 0.
- the encoding of each pixel can be sequentially encoded according to a certain scanning order (for example, first row and second column).
- the coding of each pixel is connected in series to form a one-dimensional array or vector, which is used as the characteristic coding information of the image frame.
- the preset feature encoding information includes the feature encoding information of the image frame containing the human face in the video data, that is, the preset feature encoding information is the feature of the preceding image frame of the current image frame. information is encoded, and the preceding image frame includes a human face. That is, an image including a human face captured after the camera is activated is used as a basis for judging whether the camera is blocked by the camera in subsequent image frames.
- the camera device can be powered on and start to shoot the driving area of the vehicle to obtain video data.
- the stored feature encoding information including the face is used as the preset feature encoding information; and if the first frame image contains a human face, the feature encoding information of the first frame image is used as the preset feature encoding information.
- the preset feature coding information can be updated, that is, the subsequent feature coding information containing faces can replace the features of the first frame of images.
- coded information For example, it may be updated every preset time interval, and the preset interval time is not limited, for example, it may be 1 minute or 2 minutes.
- the feature encoding information of the current image frame may be compared with the preset feature encoding information to determine whether the camera is blocked.
- the Hamming distance between the feature encoding information of the current image frame and the preset feature encoding information may be calculated, and the distance between the feature encoding information of the current image frame and the preset feature encoding information If the Hamming distance is greater than the preset threshold, it is determined that the camera is blocked.
- the current image frame is further encoded according to the pixel values in the current image frame to obtain the feature encoding information of the current image frame, and based on the Describe the feature coding information of the current image frame and the preset feature coding information to judge whether the camera is blocked, so that the image can be further judged when the face is not recognized, and the accuracy of the judgment can be improved. In particular, it is more accurate in judging whether the driver leaves the post.
- FIG. 3 it is a schematic flow chart of another camera device occlusion detection method provided by an embodiment of the present disclosure, including the following S201 to S205:
- this step is similar to the above step S101.
- this step is similar to the above step S102.
- this step is similar to the above step S103.
- the Hamming distance between the feature encoding information of the current image frame and the preset feature encoding information is not greater than the preset threshold, it indicates that there may be a human face in the current image frame, which may be due to some specific The reason (for example, the ambient light is dark) that the face is not recognized during the detection process. Therefore, in order to further improve the accuracy of the judgment, it is necessary to judge the current image frame from other angles to further judge whether the camera is blocked.
- the pixel distribution histogram of the current image frame determines whether the pixel distribution ratio of the preset interval in the pixel distribution histogram is greater than the preset ratio threshold, it is determined that the camera is blocked.
- the distribution of pixel values of each pixel in the current image frame may be counted to obtain a pixel distribution histogram of the current image frame.
- the distribution of the pixel value of each pixel point in the current image frame can be counted according to a plurality of pre-divided pixel intervals, and the plurality of pixel intervals can be [0-19], [20-80], [81 ⁇ 126] and [127 ⁇ 255], etc. It can be understood that, in this implementation manner, the multiple pixel intervals shown are schematic, and in other implementation implementation manners, the multiple pixel intervals may also be divided according to other requirements.
- the preset interval can be obtained through a large number of tests based on the actual use environment of the camera device. For example, the histogram distribution diagram of the image of the scene in the driving area of the vehicle can be calculated, and it can be determined that the camera device is not blocked. There is a clear boundary between the ratio of the number of pixels in the pixel interval [20-80] in the normal image taken and the ratio of the number of pixels in the pixel interval [20-80] in the image taken when the camera is blocked. Therefore, you can Set the default interval to the pixel interval of [20 ⁇ 80].
- the preset interval can also be It is an interval with a lower pixel value or an interval with a higher pixel value, such as a pixel interval of [0-20] or a pixel interval of [130-255], which is not limited here.
- the preset interval is one of the plurality of pixel intervals.
- the preset interval is [20-80]. If it is greater than the preset proportion threshold, it can be determined that the camera device is blocked.
- prompt information may be output to remind the driver to deal with the blocked camera so that the camera can normally capture images of the driver, thereby helping to improve driving safety.
- the prompt information includes, but is not limited to, voice prompt information, graphic prompt information, light prompt information, and the like.
- voice prompt information "The camera is blocked, please confirm" can be output.
- step S206 of outputting prompt information can be performed in the following manners of S2061 and S2062:
- the current image frame determines that the camera is blocked, it is also necessary to determine whether the judgment result of the subsequent frame image is also blocked. It just flashes, and at this time, no prompt information is output; if the judgment result of at least one frame after the frame image is also that the camera is blocked, that is, it is judged that the camera is blocked for multiple consecutive frames of images, it means that the camera is continuously blocked at this time , is intentional occlusion, not false occlusion, and when the continuous occlusion time reaches a preset time (for example, 5 seconds), a prompt message is output for prompting.
- a preset time for example, 5 seconds
- FIG. 5 it is a schematic flowchart of another method for occlusion detection of a camera device provided by an embodiment of the present disclosure, including the following S301 to S310:
- this step is similar to the above step S101.
- this step is similar to the above step S102.
- step S308 is executed to determine The camera is blocked; if the Hamming distance between the feature encoding information of the current image frame and the preset feature encoding information is not greater than the preset threshold, it means that there may be a human face in the current image frame, and further judgment is required. Therefore, Execute step S304.
- this step is similar to the above step S204.
- step S308 is executed to determine that the camera is blocked; if the pixel The proportion of pixel distribution in the preset interval in the distribution histogram is not greater than the preset proportion threshold, indicating that the proportion of effective content in the current image frame is normal, and step S306 needs to be executed for further judgment.
- the maximum connected domain refers to the image area composed of all pixel values with the same pixel value or within a certain error and adjacent to each other, and the maximum connected domain is a closed area.
- the preset area threshold can be set to an area that accounts for 60% of the entire image. If the maximum connected domain is greater than the preset area threshold, step S308 is performed to determine that the camera is blocked; if the maximum connected domain is not larger than the preset area threshold If the area threshold is set, step S310 is executed to determine that the camera is not blocked.
- the average value of the area of the largest connected domain of the multi-frame images before or after the current image frame is also determined, thereby reducing the risk of flickering.
- the probability of misjudgment caused by instantaneously passing in front of the camera device further improves the accuracy of judgment.
- this step is similar to the above step S206.
- the writing order of each step does not mean a strict execution order and constitutes any limitation on the implementation process.
- the specific execution order of each step should be based on its function and possible
- the inner logic is OK.
- the embodiment of the present disclosure also provides a camera device occlusion detection device corresponding to the camera device occlusion detection method, because the principle of solving the problem of the device in the embodiment of the present disclosure is the same as the above-mentioned camera device occlusion detection method in the embodiment of the present disclosure Similarly, the implementation of the device can refer to the implementation of the method.
- FIG. 6 it is a schematic diagram of a camera occlusion detection device 500 provided by an embodiment of the present disclosure.
- the camera occlusion detection device 500 includes:
- the video acquisition module 501 is configured to acquire video data of the driving area of the vehicle through the camera device;
- the face detection module 502 is configured to perform face detection on the current image frame in the video data, and perform face detection on the current image frame according to pixel values in the current image frame if no face is detected. Encoding, to obtain the feature encoding information of the current image frame;
- the occlusion determining module 503 is configured to determine whether the camera is occluded based on the feature encoding information of the current image frame and preset feature encoding information, wherein the preset feature encoding information includes The feature encoding information of the image frame of the face.
- the face detection module 502 is further configured to:
- the reference pixel threshold is an average pixel value of the current image frame.
- the occlusion determining module 503 is further configured to:
- the Hamming distance between the feature encoding information of the current image frame and the preset feature encoding information is greater than a preset threshold, it is determined that the camera is blocked.
- the occlusion determining module 503 is further configured to:
- the occlusion determining module 503 is further configured to:
- the occlusion determining module 503 is further configured to:
- the area of the largest connected domain is greater than a preset area threshold, it is determined that the camera is blocked.
- the device further includes:
- the information output module 504 is configured to output prompt information when it is determined that the camera is blocked.
- the information output module 504 is further configured to:
- the prompt information is output.
- an embodiment of the present disclosure also provides an electronic device.
- FIG. 8 it is a schematic structural diagram of an electronic device 700 provided by an embodiment of the present disclosure, including a processor 701 , a memory 702 , and a bus 703 .
- the memory 702 is used to store execution instructions, including a memory 7021 and an external memory 7022; the memory 7021 here is also called an internal memory, and is used to temporarily store calculation data in the processor 701 and exchange data with an external memory 7022 such as a hard disk.
- the processor 701 exchanges data with the external memory 7022 through the memory 7021 .
- the memory 702 is used to store application program codes for executing the solutions of the present disclosure, and the execution is controlled by the processor 701 . That is, when the electronic device 700 is running, the processor 701 communicates with the memory 702 through the bus 703, so that the processor 701 executes the application program code stored in the memory 702, and then executes the method described in any of the foregoing embodiments.
- memory 702 can be, but not limited to, random access memory (Random Access Memory, RAM), read-only memory (Read Only Memory, ROM), programmable read-only memory (Programmable Read-Only Memory, PROM), can Erasable Programmable Read-Only Memory (EPROM), Electric Erasable Programmable Read-Only Memory (EEPROM), etc.
- RAM Random Access Memory
- ROM read-only memory
- PROM programmable read-only memory
- EPROM Erasable Programmable Read-Only Memory
- EEPROM Electric Erasable Programmable Read-Only Memory
- the processor 701 may be an integrated circuit chip with signal processing capability.
- the above-mentioned processor can be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; it can also be a digital signal processor (Digital Signal Processing, DSP), dedicated integrated Circuit (Application-Specific Integrated Circuit, ASIC), Field Programmable Gate Array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
- DSP Digital Signal Processing
- ASIC Application-Specific Integrated Circuit
- FPGA Field Programmable Gate Array
- a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, and the like.
- the structure illustrated in the embodiment of the present disclosure does not constitute a limitation to the electronic device 700 .
- the electronic device 700 may include more or fewer components than shown in the illustration, or combine certain components, or separate certain components, or arrange different components.
- the illustrated components can be realized in hardware, software or a combination of software and hardware.
- An embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is run by a processor, the steps of the camera-device occlusion detection method in the foregoing method embodiments are executed.
- the storage medium may be a volatile or non-volatile computer-readable storage medium.
- An embodiment of the present disclosure also provides a computer program product, the computer program product carries a program code, and the instructions contained in the program code can be used to execute the steps of the camera device occlusion detection method in the above method embodiment, and refer to the above method implementation example.
- the above-mentioned computer program product may be implemented by means of hardware, software or a combination thereof.
- the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK) and the like.
- the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
- each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
- the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor.
- the technical solution of the present disclosure is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present disclosure.
- the aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disc and other media that can store program codes. .
- the products applying the disclosed technical solution have clearly notified the personal information processing rules and obtained the individual's independent consent before processing personal information.
- the disclosed technical solution involves sensitive personal information the products applying the disclosed technical solution have obtained individual consent before processing sensitive personal information, and at the same time meet the requirement of "express consent". For example, at a personal information collection device such as a camera, a clear and prominent sign is set up to inform that it has entered the scope of personal information collection, and personal information will be collected.
- the personal information processing rules may include Information processor, purpose of personal information processing, processing method, type of personal information processed and other information.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
Abstract
Description
Claims (21)
- 一种摄像装置遮挡检测方法,包括:通过摄像装置获取车辆的驾驶区域的视频数据;对所述视频数据中的当前图像帧进行人脸检测,在未检测到人脸的情况下,根据所述当前图像帧中的像素值对所述当前图像帧进行编码,得到所述当前图像帧的特征编码信息;基于所述当前图像帧的特征编码信息以及预设特征编码信息,确定所述摄像装置是否被遮挡,其中,所述预设特征编码信息包括所述视频数据中包含人脸的图像帧的特征编码信息。
- 根据权利要求1所述的方法,其中,所述根据所述当前图像帧中的像素值对所述当前图像帧进行编码,包括:确定所述当前图像帧的参考像素阈值;依次将所述当前图像帧的每个像素点的像素值与所述参考像素阈值进行比较,将大于所述参考像素阈值的像素点编码为1,将不大于所述参考像素阈值的像素点编码为0,得到所述当前图像帧的特征编码信息。
- 根据权利要求2所述的方法,其中,所述参考像素阈值为所述当前图像帧的平均像素值。
- 根据权利要求1至3任一项所述的方法,其中,所述基于所述当前图像帧的特征编码信息以及预设特征编码信息,确定所述摄像装置是否被遮挡,包括:在所述当前图像帧的特征编码信息与所述预设特征编码信息之间的汉明距离大于预设阈值的情况下,确定所述摄像装置被遮挡。
- 根据权利要求4所述的方法,其中,所述方法还包括:在所述汉明距离不大于所述预设阈值的情况下,确定所述当前图像帧的像素分布直方图;基于所述当前图像帧的像素分布直方图,确定所述摄像装置是否被遮挡。
- 根据权利要求5所述的方法,其中,所述基于所述当前图像帧的像素分布直方图,确定所述摄像装置是否被遮挡,包括:在所述像素分布直方图中的预设区间的像素分布占比大于预设占比阈值的情况下,确定所述摄像装置被遮挡。
- 根据权利要求5或6所述的方法,其中,所述方法还包括:在所述像素分布直方图中的预设区间的像素分布占比不大于所述预设占比阈值的情况下,确定所述当前图像帧的最大连通域;在所述最大连通域的面积大于预设面积阈值的情况下,确定所述摄像装置被遮挡。
- 根据权利要求1至7任一项所述的方法,其中,所述方法还包括:在确定所述摄像装置被遮挡的情况下,输出提示信息。
- 根据权利要求8所述的方法,其中,所述在确定所述摄像装置被遮挡的情况下,输出提示信息,包括:根据所述视频数据中各帧图像的摄像装置检测结果,确定所述摄像装置的持续遮挡时间;在所述持续遮挡时间达到预设时间的情况下,输出所述提示信息。
- 一种摄像装置遮挡检测装置,包括:视频获取模块,配置为通过摄像装置获取车辆的驾驶区域的视频数据;人脸检测模块,配置为对所述视频数据中的当前图像帧进行人脸检测,在未检测到人脸的情况下,根据所述当前图像帧中的像素值对所述当前图像帧进行编码,得到所述 当前图像帧的特征编码信息;遮挡确定模块,配置为基于所述当前图像帧的特征编码信息以及预设特征编码信息,确定所述摄像装置是否被遮挡,其中,所述预设特征编码信息包括所述视频数据中包含人脸的图像帧的特征编码信息。
- 根据权利要求10所述的装置,其中,所述人脸检测模块还配置为:确定所述当前图像帧的参考像素阈值;依次将所述当前图像帧的每个像素点的像素值与所述参考像素阈值进行比较,将大于所述参考像素阈值的像素点编码为1,将不大于所述参考像素阈值的像素点编码为0,得到所述当前图像帧的特征编码信息。
- 根据权利要求11所述的装置,其中,所述参考像素阈值为所述当前图像帧的平均像素值。
- 根据权利要求10至12任一项所述的装置,其中,所述遮挡确定模块还配置为:在所述当前图像帧的特征编码信息与所述预设特征编码信息之间的汉明距离大于预设阈值的情况下,确定所述摄像装置被遮挡。
- 根据权利要求13所述的装置,其中,所述遮挡确定模块还配置为:在所述汉明距离不大于所述预设阈值的情况下,确定所述当前图像帧的像素分布直方图;基于所述当前图像帧的像素分布直方图,确定所述摄像装置是否被遮挡。
- 根据权利要求14所述的装置,其中,所述遮挡确定模块还配置为:在所述像素分布直方图中的预设区间的像素分布占比大于预设占比阈值的情况下,确定所述摄像装置被遮挡。
- 根据权利要求13或14所述的装置,其中,所述遮挡确定模块还配置为:在所述像素分布直方图中的预设区间的像素分布占比不大于所述预设占比阈值的情况下,确定所述当前图像帧的最大连通域;在所述最大连通域的面积大于预设面积阈值的情况下,确定所述摄像装置被遮挡。
- 根据权利要求10至16任一项所述的装置,其中,所述装置还包括:信息输出模块,配置为在确定所述摄像装置被遮挡的情况下,输出提示信息。
- 根据权利要求17所述的装置,其中,所述信息输出模块还配置为:根据所述视频数据中各帧图像的摄像装置检测结果,确定所述摄像装置的持续遮挡时间;在所述持续遮挡时间达到预设时间的情况下,输出所述提示信息。
- 一种电子设备,包括:处理器、存储器和总线,所述存储器存储有所述处理器可执行的机器可读指令,当电子设备运行时,所述处理器与所述存储器之间通过总线通信,所述机器可读指令被所述处理器执行时执行如权利要求1至9任一所述的摄像装置遮挡检测方法。
- 一种计算机可读存储介质,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行如权利要求1至9任一所述的摄像装置遮挡检测方法。
- 一种计算机程序产品,包括存储了程序代码的计算机可读存储介质,所述程序代码包括的指令被计算机设备的处理器运行时,实现权利要求1至9中任一项所述方法中的步骤。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020247023573A KR20240124973A (ko) | 2021-12-31 | 2022-10-12 | 촬영 장치 차폐 검출 방법, 장치, 전자 기기, 저장 매체 및 컴퓨터 프로그램 제품 |
| JP2024538727A JP7781286B2 (ja) | 2021-12-31 | 2022-10-12 | カメラ装置の遮蔽検出方法、装置、電子機器、記憶媒体、並びにコンピュータプログラム |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111668662.2A CN114332720B (zh) | 2021-12-31 | 2021-12-31 | 摄像装置遮挡检测方法、装置、电子设备及存储介质 |
| CN202111668662.2 | 2021-12-31 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023124385A1 true WO2023124385A1 (zh) | 2023-07-06 |
Family
ID=81020389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2022/124934 Ceased WO2023124385A1 (zh) | 2021-12-31 | 2022-10-12 | 摄像装置遮挡检测方法、装置、电子设备、存储介质及计算机程序产品 |
Country Status (4)
| Country | Link |
|---|---|
| JP (1) | JP7781286B2 (zh) |
| KR (1) | KR20240124973A (zh) |
| CN (1) | CN114332720B (zh) |
| WO (1) | WO2023124385A1 (zh) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332720B (zh) * | 2021-12-31 | 2025-04-15 | 上海商汤临港智能科技有限公司 | 摄像装置遮挡检测方法、装置、电子设备及存储介质 |
| CN115205988A (zh) * | 2022-06-22 | 2022-10-18 | 杭州海康威视数字技术股份有限公司 | 一种注册模板的更新方法、装置、生物特征识别系统 |
| CN116977630A (zh) * | 2023-06-20 | 2023-10-31 | 深圳绿米联创科技有限公司 | 图像检测方法、装置、电子设备及计算机可读存储介质 |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180253630A1 (en) * | 2017-03-02 | 2018-09-06 | Denso International America, Inc. | Surrounding View Camera Blockage Detection |
| CN109858441A (zh) * | 2019-01-30 | 2019-06-07 | 广州轨道交通建设监理有限公司 | 一种用于施工现场的异常状态监测方法与装置 |
| CN110557628A (zh) * | 2018-06-04 | 2019-12-10 | 杭州海康威视数字技术股份有限公司 | 一种检测摄像头遮挡的方法、装置及电子设备 |
| US20200034959A1 (en) * | 2018-07-24 | 2020-01-30 | The Regents Of The University Of Michigan | Detection Of Near-Field Occlusions In Images |
| CN111862228A (zh) * | 2020-06-04 | 2020-10-30 | 福瑞泰克智能系统有限公司 | 遮挡检测的方法、系统、计算机设备和可读存储介质 |
| CN111970405A (zh) * | 2020-08-21 | 2020-11-20 | Oppo(重庆)智能科技有限公司 | 摄像头遮挡检测方法、存储介质、电子设备及装置 |
| CN112351271A (zh) * | 2020-09-22 | 2021-02-09 | 北京迈格威科技有限公司 | 一种摄像头的遮挡检测方法、装置、存储介质和电子设备 |
| CN112668636A (zh) * | 2020-12-25 | 2021-04-16 | 展讯通信(上海)有限公司 | 摄像头遮挡检测方法及系统、电子设备及存储介质 |
| CN114332720A (zh) * | 2021-12-31 | 2022-04-12 | 上海商汤临港智能科技有限公司 | 摄像装置遮挡检测方法、装置、电子设备及存储介质 |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019159346A (ja) | 2018-03-07 | 2019-09-19 | オムロン株式会社 | 撮像装置 |
| CN111383201B (zh) * | 2018-12-29 | 2024-03-12 | 深圳Tcl新技术有限公司 | 基于场景的图像处理方法、装置、智能终端及存储介质 |
| CN111428581B (zh) * | 2020-03-05 | 2023-11-21 | 平安科技(深圳)有限公司 | 人脸遮挡检测方法及系统 |
| CN112261402B (zh) * | 2020-09-22 | 2022-08-16 | 北京紫光展锐通信技术有限公司 | 图像检测方法与系统以及摄像头遮挡监控方法与系统 |
| CN112487886A (zh) * | 2020-11-16 | 2021-03-12 | 北京大学 | 一种有遮挡的人脸识别方法、装置、存储介质及终端 |
-
2021
- 2021-12-31 CN CN202111668662.2A patent/CN114332720B/zh active Active
-
2022
- 2022-10-12 WO PCT/CN2022/124934 patent/WO2023124385A1/zh not_active Ceased
- 2022-10-12 JP JP2024538727A patent/JP7781286B2/ja active Active
- 2022-10-12 KR KR1020247023573A patent/KR20240124973A/ko active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180253630A1 (en) * | 2017-03-02 | 2018-09-06 | Denso International America, Inc. | Surrounding View Camera Blockage Detection |
| CN110557628A (zh) * | 2018-06-04 | 2019-12-10 | 杭州海康威视数字技术股份有限公司 | 一种检测摄像头遮挡的方法、装置及电子设备 |
| US20200034959A1 (en) * | 2018-07-24 | 2020-01-30 | The Regents Of The University Of Michigan | Detection Of Near-Field Occlusions In Images |
| CN109858441A (zh) * | 2019-01-30 | 2019-06-07 | 广州轨道交通建设监理有限公司 | 一种用于施工现场的异常状态监测方法与装置 |
| CN111862228A (zh) * | 2020-06-04 | 2020-10-30 | 福瑞泰克智能系统有限公司 | 遮挡检测的方法、系统、计算机设备和可读存储介质 |
| CN111970405A (zh) * | 2020-08-21 | 2020-11-20 | Oppo(重庆)智能科技有限公司 | 摄像头遮挡检测方法、存储介质、电子设备及装置 |
| CN112351271A (zh) * | 2020-09-22 | 2021-02-09 | 北京迈格威科技有限公司 | 一种摄像头的遮挡检测方法、装置、存储介质和电子设备 |
| CN112668636A (zh) * | 2020-12-25 | 2021-04-16 | 展讯通信(上海)有限公司 | 摄像头遮挡检测方法及系统、电子设备及存储介质 |
| CN114332720A (zh) * | 2021-12-31 | 2022-04-12 | 上海商汤临港智能科技有限公司 | 摄像装置遮挡检测方法、装置、电子设备及存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114332720A (zh) | 2022-04-12 |
| JP7781286B2 (ja) | 2025-12-05 |
| KR20240124973A (ko) | 2024-08-19 |
| JP2024544344A (ja) | 2024-11-28 |
| CN114332720B (zh) | 2025-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111274881B (zh) | 驾驶安全的监控方法、装置、计算机设备及存储介质 | |
| CN114332721B (zh) | 摄像装置遮挡检测方法、装置、电子设备及存储介质 | |
| JP7781286B2 (ja) | カメラ装置の遮蔽検出方法、装置、電子機器、記憶媒体、並びにコンピュータプログラム | |
| CN111476234B (zh) | 一种遮挡车牌字符识别方法、装置、存储介质和智能设备 | |
| EP2662827B1 (en) | Video analysis | |
| WO2020258077A1 (zh) | 一种行人检测方法及装置 | |
| CN108388880A (zh) | 一种监测司机开车使用手机的方法及装置 | |
| JP7697219B2 (ja) | 車両の方向指示器の合図の認識装置、認識方法及び電子機器 | |
| CN114782887A (zh) | 基于深度学习的消防通道占用检测方法及装置 | |
| EP4517700A1 (en) | Safety belt wearing detection method and apparatus, electronic device and storage medium | |
| CN104680171B (zh) | 图像中斑马线的检测装置、方法 | |
| CN113947749A (zh) | 一种遗留物检测方法、装置、电子设备及存储介质 | |
| CN111444788A (zh) | 行为识别的方法、装置及计算机存储介质 | |
| CN110913209B (zh) | 摄像头遮挡检测方法、装置、电子设备及监控系统 | |
| CN112070954A (zh) | 活体识别方法、装置、设备及存储介质 | |
| CN113408364B (zh) | 一种临时车牌识别方法、系统、装置及存储介质 | |
| CN113191293B (zh) | 广告检测方法、装置、电子设备、系统及可读存储介质 | |
| CN115861624B (zh) | 摄像头被遮挡的检测方法、装置、设备及存储介质 | |
| Santos et al. | Car recognition based on back lights and rear view features | |
| CN114863472B (zh) | 多级行人检测方法、装置和存储介质 | |
| CN113239738B (zh) | 一种图像的模糊检测方法及模糊检测装置 | |
| CN114550146A (zh) | 图像处理方法、装置、设备及计算机存储介质 | |
| CN110889352A (zh) | 图像模糊化处理方法、计算机装置及计算机可读存储介质 | |
| CN110188645A (zh) | 用于车载场景的人脸检测方法、装置、车辆及存储介质 | |
| CN116229502A (zh) | 基于图像的摔倒行为识别方法及设备 |
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: 22913649 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2024538727 Country of ref document: JP |
|
| ENP | Entry into the national phase |
Ref document number: 20247023573 Country of ref document: KR Kind code of ref document: A |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 22913649 Country of ref document: EP Kind code of ref document: A1 |
|
| 32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 11-12-2024) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 22913649 Country of ref document: EP Kind code of ref document: A1 |