CN112995650B - Method and device for detecting video continuity of camera - Google Patents
Method and device for detecting video continuity of camera Download PDFInfo
- Publication number
- CN112995650B CN112995650B CN201911309760.XA CN201911309760A CN112995650B CN 112995650 B CN112995650 B CN 112995650B CN 201911309760 A CN201911309760 A CN 201911309760A CN 112995650 B CN112995650 B CN 112995650B
- Authority
- CN
- China
- Prior art keywords
- video
- dynamic information
- camera
- sequence
- video frames
- 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.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/002—Diagnosis, testing or measuring for television systems or their details for television cameras
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The invention provides a method and a device for detecting video continuity of a camera. In one embodiment, a method for detecting video continuity of a camera may include: receiving a video of a test object captured by a camera over a period of time, the test object having dynamic information that varies according to a first pattern over the period of time; identifying content in each video frame of the video that is related to the dynamic information; determining whether a sequence of video frames of the video follows the first pattern based on the identified content; and if the sequence of video frames does not follow the first pattern, determining that video of the camera is discontinuous.
Description
Technical Field
The present invention relates to cameras, and more particularly, to a method and apparatus for detecting video continuity of a camera.
Background
With the increase of user demands and the development of technology, cameras have been incorporated into aspects of people's life, such as intelligent monitoring with cameras, mobile devices with cameras, cameras/cameras, and the like. In a scenario where intelligent monitoring is performed with a camera, the camera may be installed at a site where monitoring is desired and video is captured, the captured video may be stored in a memory onboard the camera, and/or may be transmitted to a display device for display, either wired or wireless, and/or may be transmitted to a storage device separate from the camera for storage.
In order to improve the video quality of the camera, camera equipment service providers improve video coding and decoding technologies, video transmission technologies and the like, and the purpose of the camera equipment service providers is to improve the video quality experience. Video continuity is one of the key factors affecting the user experience, and especially frame-level continuity may not be accurately judged by the naked eye. Therefore, detecting video continuity of a camera has become an important aspect in camera detection technology.
Disclosure of Invention
The invention provides a method and a device for detecting video continuity of a camera.
In one embodiment, a method for detecting video continuity of a camera may include: receiving a video of a test object captured by a camera over a period of time, the test object having dynamic information that varies according to a first pattern over the period of time; identifying content in each video frame of the video that is related to the dynamic information; determining whether a sequence of video frames of the video follows the first pattern based on the identified content; and if the sequence of video frames does not follow the first pattern, determining that video of the camera is discontinuous.
In one aspect, the sequence of video frames not following the first pattern includes at least one of: in the case where the rate of change of the dynamic information is greater than or equal to the frame rate of the video, successive video frames in the sequence of video frames include the same content related to the dynamic information; the order of the content related to the dynamic information included by two video frames in the sequence of video frames is different from the order of the dynamic information in the first mode; in the event that the rate of change of the dynamic information is equal to the frame rate of the video, the sequence of video frames lacks video frames corresponding to a subset of the dynamic information; under the condition that the change rate of the dynamic information is larger than the frame rate of the video, the video frame sequence lacks video frames corresponding to the dynamic information in the subset acquired by the dynamic information according to the frame rate; and in the case where the rate of change of the dynamic information is less than the frame rate of the video, the number of successive frames in the video including the same content related to the dynamic information exceeds an upper threshold or falls below a lower threshold.
In one aspect, receiving video of a test object captured by a camera over a period of time includes receiving a plurality of video of the test object captured by a plurality of cameras in synchronization, and if the content of corresponding video frames in the video of at least two cameras is inconsistent, determining that the sequence of video frames of at least one of the at least two cameras does not follow the first pattern and that the video of the at least one camera is discontinuous.
In one aspect, the test object is one of: a clock displaying a time change; a timer or counter; and a device for dynamically switching the displayed pictures or text.
In one aspect, the first pattern is known or inferred based on content identified from the sequence of video frames.
In one embodiment, an apparatus for detecting video continuity of a camera may comprise: a video acquisition module that receives video of a test object captured by a camera over a period of time, the test object having dynamic information that varies according to a first pattern over the period of time; an image recognition module that recognizes content related to the dynamic information in each video frame of the video; and a continuity detection module that determines, based on the identified content, whether a sequence of video frames of the video follows the first pattern, and if the sequence of video frames does not follow the first pattern, determines that the video of the camera is discontinuous.
In one aspect, the sequence of video frames not following the first pattern includes at least one of: in the case where the rate of change of the dynamic information is greater than or equal to the frame rate of the video, successive video frames in the sequence of video frames include the same content related to the dynamic information; the order of the content related to the dynamic information included by two video frames in the sequence of video frames is different from the order of the dynamic information in the first mode; in the event that the rate of change of the dynamic information is equal to the frame rate of the video, the sequence of video frames lacks video frames corresponding to a subset of the dynamic information; under the condition that the change rate of the dynamic information is larger than the frame rate of the video, the video frame sequence lacks video frames corresponding to the dynamic information in the subset acquired by the dynamic information according to the frame rate; and in the case where the rate of change of the dynamic information is less than the frame rate of the video, the number of successive frames in the video including the same content related to the dynamic information exceeds an upper threshold or falls below a lower threshold.
In one aspect, the video acquisition module receives a plurality of videos of the test object synchronously captured by a plurality of cameras, and if the content of corresponding video frames in videos of at least two cameras is inconsistent, the continuity detection module determines that the sequence of video frames of at least one of the at least two cameras does not follow the first pattern and that the videos of the at least one camera are discontinuous.
In one aspect, the test object is one of: a clock displaying a time change; a timer or counter; and a device for dynamically switching the displayed pictures or text.
In one aspect, the first pattern is known or inferred based on content identified from the sequence of video frames.
The invention provides a technology for detecting video continuity of a camera, and a detection method and a detection device for judging whether a video provided by the camera has discontinuous phenomena such as frame repetition, frame loss, and/or frame sequence error or not on the basis of operation of the camera. The method saves the labor time in the detection work of the camera, can greatly improve the test efficiency, and has higher accuracy of the test result.
Drawings
Fig. 1 is a schematic diagram of a system architecture for detecting video continuity of a camera according to one embodiment of the present invention.
Fig. 2 is a flow chart of a method for detecting video continuity of a camera in accordance with one embodiment of the present invention.
Fig. 3 is a flow chart of a method for detecting video continuity of a camera in accordance with another embodiment of the present invention.
Fig. 4 is an example of a method for detecting video continuity of a camera according to one embodiment of the invention.
Fig. 5 is a block diagram of an apparatus for detecting video continuity of a camera according to one embodiment of the present invention.
Detailed Description
The invention will be further described with reference to specific examples and figures, which should not be construed as limiting the scope of the invention.
Fig. 1 is a schematic diagram of a system architecture for detecting video continuity of a camera according to one embodiment of the present invention. The camera may be any device capable of taking continuous pictures or video, which may be stand alone or may be embedded in an electronic product. The techniques described herein may be used to perform camera testing before or after the camera is shipped. For example, using the techniques described herein, a camera manufacturer may self-test the quality of a camera, a smart home service provider may verify the video quality before or after the camera is installed, and a user may also routinely monitor the video quality before or after the camera is put into service.
By way of example and not limitation, a stand-alone camera 110 is shown in fig. 1. In accordance with the techniques described herein, a video of the test object 102 may be captured with the camera 110 and analyzed to determine if the video is continuous. The video continuity may indicate whether the video frame sequence records the photographic subject at a specified interval in time order (for example, the interval may be indicated by a frame rate). Normally, the camera 110 is set to take pictures at a frame rate, and the generated video will be continuous. However, in the event of a malfunction of the camera 110, a data transmission error, a data storage error, etc., frame repetition, frame loss, and/or frame sequence error, etc., may occur, resulting in video discontinuity. Frame repetition can lead to video sticking phenomena, while frame loss and frame sequence errors can lead to video frame skipping or flickering. Video discontinuities will affect the user experience. Thus, the techniques described herein may be used to detect one or more video discontinuities.
According to the present invention, the test object 102 may have dynamic information that changes so that the camera 110 can capture a dynamically changing video. Fig. 1 shows test object 102 as a counter, which displays changing numbers, as an example. In other embodiments, test object 102 may be other devices with changing dynamic information, such as a display screen that may set display content, a clock that displays time changes, etc. The camera 110 may capture video of the test object 102 over a period of time and transmit the video to the server 120 via a wired or wireless connection. Server 120 may analyze whether the video is continuous. The user may access the server 120 through a terminal device (e.g., cell phone 132, desktop computer 134, notebook computer 136, etc.) to learn the analysis results.
In another embodiment, the video captured by camera 110 may be stored in an intermediary device (e.g., memory, server 120, database, etc.), from which a processing device (e.g., cell phone 132, desktop computer 134, notebook computer 136, etc.) may receive the video captured by camera 110 for analysis.
In another embodiment, the camera 110 may be integrated into other electronic devices, such as a mobile device with a camera, e.g., a cell phone, tablet device, desktop computer, notebook computer, etc. Thus, the electronic device may analyze the video captured by the camera 110 to determine whether the video is continuous.
In yet another embodiment, whether camera 110 is stand alone or integrated in other electronic devices, video captured by camera 110 may be transmitted over a network or an intermediary device to a server, computer device, mobile device, or cloud service device, etc., for analysis to determine whether the video is continuous.
Fig. 2 is a flow chart of a method 200 for detecting video continuity of a camera in accordance with one embodiment of the present invention. The method may be implemented by a processing device or an application therein, such as a mobile device, a computer device, a server, a cloud service device, etc., or an application installed in such a device.
At step 202, video of a test object captured by a camera over a period of time may be received. In one example, the test object has dynamic information that changes in a first pattern over the period of time. For example, if the test object is a counter or counter, the counter may count or time up incrementally or decrementally by a set step size. If the test object is a clock, the clock may display real-time changes with a set accuracy. In other embodiments, the test object may also be a device that dynamically switches the displayed pictures or text, such as a display screen of an electronic device. In order to improve the detection accuracy, the rate of change of the dynamic information may be greater than or equal to the frame rate at which the camera captures video.
The first mode may be one of various possible modes of variation, such as a number incrementing or decrementing by a set step size, a specified sequence of numbers, a time increment or decrement, a specified sequence of times, a predetermined sequence of displayed pictures or text, and so forth. The changes that occur to the test object should be easily identifiable, e.g. different numbers, different pictures, different text, different colors, etc. Further, the dynamic information containing numbers may be continuously variable (e.g., 1 increment or decrement each time) or discontinuously variable (e.g., 2 increment or decrement each time, 3, 4, 5, 10, etc.), depending on the step size set. The step size of each change of the dynamic information containing time can be set as required, for example, 10 μs, 100 μs, 1ms, 5ms, 10ms, etc. Preferably, the dynamic information of the test object is not repeated during the period of time that a single camera is taking. In another example, the dynamic information of the test object is non-repeatable over a specified number of frames (e.g., 20 frames, 100 frames, etc.) of the camera.
In one embodiment, the camera may transmit the entire video to a processing device or an intermediary device (e.g., memory, server, etc.) after the completion of the shooting for a specified period of time. In another embodiment, video captured by the camera may be transmitted to the processing device in real time. For example, the camera acquires video frames one by one, and each video frame may be transmitted to the processing device after being acquired without waiting for the remaining video frames. In yet another embodiment, video frames captured by the camera may be transmitted to the processing device in batches, for example, every 10 video frames generated for processing.
At step 204, content associated with dynamic information of the test object in each video frame of the video may be identified. Since the video is composed of video frames in sequence, the content related to the dynamic information of the test object in each video frame can be separately identified. For example, various image recognition techniques may be employed to identify content in a video frame that is related to dynamic information, such as numbers, time, pictures, text, and the like. By way of example and not limitation, image recognition techniques may include, for example, template matching, pattern recognition, machine learning, artificial neural networks, and the like, as the invention is not limited in this respect. Step 204 may be implemented with one or more processes, each of which may use single-threaded or multi-threaded. Alternatively, the number of processes and/or the number of threads used by each process may be dynamically adjusted according to the processing load, thereby resulting in higher computing resource utilization, faster response, and smoother program operation. If video frames of video are received frame by frame or in batches, the received video frames may be processed first without waiting for the remaining video frames.
At step 206, it may be determined whether the sequence of video frames of the video follows the first pattern based on the identified content. That is, the test object has dynamic information that changes according to the first pattern, but after being photographed and transmitted by the camera, the video frames may undergo frame repetition, frame loss, and/or frame sequence errors, etc., such that the dynamic information that appears in the video in the order of the video frame sequence no longer follows the first pattern. The first mode may be known or unknown to the device or application performing the method 200.
As described above, in order to improve detection accuracy, the rate of change of the dynamic information of the test object may be greater than or equal to the frame rate at which the video is captured by the camera. In this case, any two consecutive videos among videos photographed by the camera should not include the same dynamic information. Conversely, if successive video frames in the sequence of video frames include the same dynamic information (i.e., frame repetition occurs), it may be determined that the sequence of video frames does not follow the first pattern. In this case, this determination may be made whether the device or application performing the method 200 is aware of the exact first mode.
In another example, if the device or application executing the method 200 knows the exact first pattern, a determination may be made based on a comparison to the first pattern as to whether the dynamic information based on the sequence of video frames conforms to the first pattern. For example, if the order of the dynamic information of two video frames in a sequence of video frames is different from the order of the dynamic information in the first mode (i.e., a frame order error occurred), it may be determined that the sequence of video frames does not follow the first mode. In another embodiment, in the event that the rate of change of the dynamic information of the test object is equal to the video frame rate, if a video frame corresponding to a subset of the dynamic information of the test object is absent from the sequence of video frames (i.e., a frame loss occurred), it may be determined that the sequence of video frames does not follow the first pattern. In another embodiment, the camera may not be able to capture every change in dynamic information of the test object if the rate of change of the dynamic information is greater than the video frame rate. In this case, a subset of the dynamic information may be collected at the frame rate. If a video frame corresponding to the dynamic information in the subset is absent from the sequence of video frames (i.e., a frame loss occurred), it may be determined that the sequence of video frames does not follow the first pattern.
In one embodiment, if the device or application executing method 200 is unaware of the pattern of change of the test object, the pattern of change of the test object may be inferred from the identified content in accordance with the order of the sequence of video frames. For example, if the corresponding content in a video frame that exceeds a threshold (e.g., 95%) changes in some way (e.g., increments by a certain value), a pattern of change of the test object may be deduced and thereby a determination may be made as to whether the sequence of video frames follows the pattern of change.
In one embodiment, the rate of change of the dynamic information of the test object may also be less than the frame rate at which the video is captured by the camera. In this case, the frame rate is more than 1 time the rate of change of the dynamic information, and the video shot by the camera will contain repeated frames, but it can still be determined whether the video of the camera is continuous by determining whether the video frame sequence follows the pattern of change of the test object. For example, if the video frame order is different from the dynamic information order of the test object, it may be determined that a frame order error exists. If the number of repetitions of a certain frame exceeds an upper threshold, it may be determined that a video frame is stuck (or frame repetition) is present. If the number of repetitions of a certain frame is below a lower threshold, it may be determined that there is a video frame loss. For example, the frame rate may be some multiple (e.g., may be rounded) of the rate of change of the dynamic information, the upper threshold may correspond to the multiple plus a first error margin, and the lower threshold may correspond to the multiple minus a second error margin. The first error margin and the second error margin may be greater than or equal to 0. The first error margin and the second error margin may be equal or unequal and may be set as desired, respectively.
At step 208, if the sequence of video frames does not follow the first pattern, a video discontinuity of the camera is determined. If the video of the camera is determined to be discontinuous, the camera can be further detected or adjusted accordingly to repair the video discontinuity problem.
Fig. 3 is a flow chart of a method 300 for detecting video continuity of a camera in accordance with another embodiment of the present invention. The method may be implemented by a device or application capable of video analysis, such as a mobile device, a computer device, a server, a cloud service device, etc., or an application installed in such a device. Steps of method 300 that are similar to those of method 200 shown in fig. 2 are not described in detail.
In step 302, a plurality of videos of a test object having dynamic information that varies according to a first pattern may be received that are synchronously captured by a plurality of cameras. Synchronous shooting means that the cameras are set to capture video frames at the same time at the same frame rate. The first mode may be, for example, a number increasing or decreasing in a set step size, a specified number sequence, a time increasing or decreasing, a specified time sequence, a predetermined sequence of displayed pictures or words, etc. In other embodiments, the first pattern may be a random sequence. The first mode may be known or unknown to the device or application performing the method 200. Preferably, the rate of change of the dynamic information may be greater than or equal to the frame rate at which the video is captured by the camera. In other embodiments, the rate of change of the dynamic information may also be less than the frame rate at which the video is captured by the camera.
At step 304, content associated with dynamic information of the test object in each video frame of the plurality of videos may be identified. For example, various image recognition techniques may be employed to identify content in a video frame that is related to dynamic information, such as numbers, time, pictures, text, and the like.
In step 306, if the content of the corresponding video frames in the video of the at least two cameras is inconsistent, it may be determined that the sequence of video frames of at least one of the at least two cameras does not follow the first pattern. That is, the content related to the dynamic information of the test object in the video frame sequences synchronously photographed by the two cameras should be consistent, and if there is an inconsistency, it may be determined that the video frame sequence of at least one camera does not follow the first pattern, for example, frame repetition, frame loss, and/or frame sequence error may occur in the video frames. In this case, this determination may be made whether the device or application performing the method 300 is aware of the exact first mode.
In step 308, if the sequence of video frames does not follow the first pattern, a determination is made that the video of the camera is discontinuous. If the video of the camera is determined to be discontinuous, the camera can be further detected or adjusted accordingly to repair the video discontinuity problem.
Although fig. 2 and 3 show methods 200 and 300 separately, methods 200 and 300 may be implemented in combination. In another example, step 302 may be an example of step 202 and step 306 may be an example of step 206.
Fig. 4 is an example of a method for detecting video continuity of a camera according to one embodiment of the invention. For ease of illustration, a digital timer 402 is employed as an example test object to detect whether video of the camera 410 is continuous.
In an optional preprocessing stage, a picture of the digital timer 402 may be taken at 420 using the camera 410 to extract image features for each digit. For example, one or more pictures of digital timer 402 may be taken, with the pictures being partitioned into base elements (e.g., containing a single number) to obtain a picture for each of the numbers 0-9. Each digital image feature may be extracted and saved for reference in subsequent image recognition. For other test objects containing text or other content, the image features of the base elements may be similarly obtained for reference in subsequent image recognition.
Image features may include, for example, intuitive features (e.g., geometric features), gray-scale statistical features, transform coefficient features, algebraic features, and the like. In practice, the desired image features may be extracted based on the image recognition algorithm that is employed. By way of example and not limitation, for each of the digital 0-9 pictures obtained during the preprocessing stage, a hash value of the 10 pictures may be calculated and saved to a database. Each digit and hash value can be stored in the database in the form of key value pairs, the picture hash value is set as an index by taking the picture hash value as a key, and the corresponding digit is a value.
During the detection phase, the digital timer 402 may run, for example, beginning at a set initial time and changing in steps (e.g., incrementing or decrementing by one millisecond, 10 milliseconds, etc.). At 432, during operation of the digital timer 402, the camera 410 may capture video of the digital timer 402 over a period of time such that the video includes time variations of the digital timer 402. The rate of change of the digital timer 402 may be greater than or equal to the frame rate of the camera 410.
The video captured by camera 410 may be provided to a processing device (e.g., mobile device, computer, server, etc.), which may employ image recognition techniques to analyze each video frame of the video, thereby recognizing the time stamp contained in each video frame at 434. For example, each video frame may be partitioned into base elements (e.g., containing a single number), and the number represented by each base element identified based on image characteristics. The number identified in each frame may be combined to be the timestamp contained in the video frame. Thus, the time stamps contained in each video frame can be identified, and these time stamps can be organized into a sequence of time stamps in the order of the video frames. For example, in one example, the sequence of timestamps contained in a piece of video captured by camera 410 may be: {00:00:02.01, 00:00:02.02, 00:00:02.03, 00:00:02.05, 00:00:02.06, 00:00:02.07 … … }.
Without employing a preprocessing stage to obtain the image features of the numbers 0-9 as reference information, the processing device may identify the timestamps contained in each video frame by any suitable image recognition technique, such as template matching, pattern recognition, machine learning, artificial neural networks, and the like.
In case a preprocessing stage is employed to obtain image features of the numbers 0-9 as reference information, the processing device may identify the numbers in the video frame by comparing the image features of the base elements in the video frame with the reference information. For example, assuming that hash values of reference images of numerals 0 to 9 are stored as reference information, hash values of basic elements in a video frame photographed by the camera 410 may be calculated and automatically matched with the previously stored hash values, so that numerals in the basic elements in the video frame may be recognized. The number identified in each video frame may be combined to be the timestamp contained in that video frame. The preprocessing stage may simplify the processing of the processing device and may improve recognition accuracy.
At 436, a determination may be made as to whether the video is continuous based on a sequence of time stamps identified from the video captured by camera 410. For example, if the processing device knows the pattern of change of the digital timer 402 (e.g., increments by 1 millisecond), it can be determined whether the sequence of time stamps follows the pattern of change. Referring to the above timestamp sequence {00:00:02.01, 00:00:02.02, 00:00:02.03, 00:00:02.05, 00:00:02.06, 00:00:02.07 … … }, it can be determined that a frame loss occurred when 00:00:02.04 is missing in the timestamp sequence, and thus video discontinuity can be determined.
As another example, if the timestamp sequence identified in the video captured from camera 410 is {00:00:02.01, 00:00:02.02, 00:00:02.03, 00:00:02.03, 00:00:02.05, 00:00:02.06, 00:00:02.07 … … }, it may be determined that a repetition of 00:00:02.03 occurs in the timestamp sequence, i.e., a frame repetition occurs, whereby video discontinuities may be determined.
As yet another example, if the timestamp sequence identified in the video captured from camera 410 is {00:00:02.01, 00:00:02.02, 00:00:02.04, 00:00:02.03, 00:00:02.05, 00:00:02.06, 00:00:02.07 … … }, it may be determined that a sequence error {00:00:02.04, 00:00:02.03} occurred in the timestamp sequence, i.e., a frame sequence error occurred, whereby a video discontinuity may be determined.
Furthermore, it should be appreciated that various video discontinuities may typically occur in video captured by camera 410, such as one or more of frame repetition, frame loss, frame sequence errors occurring simultaneously.
In other embodiments, the rate of change of the digital timer 402 may also be less than the frame rate of the camera 410. In this case, duplicate timestamps will occur in the sequence of timestamps. If the number of repeated consecutive time stamps exceeds an associated threshold range, it may be determined that a frame stuck or dropped frame has occurred. The threshold range may be set accordingly based on the rate of change of the digital timer 402 and the frame rate of the camera 410, and may include a tolerance error.
In one embodiment, if the processing device is unaware of the pattern of change of the digital timer 402, the pattern of change of the digital timer 402 may be inferred from the law of change of the sequence of time stamps. For example, if a timestamp in the sequence of timestamps that exceeds a threshold (e.g., 95%) changes in some manner (e.g., increments by a certain value), the pattern of change of the digital timer 402 may be deduced and thereby identify a timestamp (if any) in the sequence of timestamps that does not correspond to the pattern of change, thereby indicating whether the video is continuous.
In one aspect, the timer is used as a test object, and the displayed time can be an infinite non-repeated value consisting of 0-9, and the accuracy is very high (generally up to mu s level according to the minimum unit time which can be displayed by the timer), and the timer is not influenced by factors such as a network, so that the uninterrupted detection of 7 x 24 hours can be realized. The video continuity information of the camera can be automatically acquired by utilizing the digital comparison in the time stamp sequence, so that the accurate detection is realized. Therefore, the invention is beneficial to improving the working efficiency and the accuracy of the video quality detection of the camera.
Fig. 5 is a block diagram of an apparatus 500 for detecting video continuity of a camera in accordance with one embodiment of the present invention. The apparatus 500 may be a processing device separate from or integrated with the camera. The apparatus 500 may be implemented using a computing device, processor, server, or the like. The device 500 may include a video acquisition module 510 that may receive video of a test object captured by a camera over a period of time. The test object may have dynamic information that changes in accordance with a first pattern over the period of time. For example, the test object may be a clock, timer or counter that displays a time change, a device that dynamically switches the displayed pictures or text, or the like. In one example, the rate of change of the dynamic information may be greater than or equal to the frame rate of the video.
The apparatus 500 may also include an image recognition module 520 that recognizes content associated with the dynamic information in each video frame of the received video. Image recognition module 520 may identify the content associated with the dynamic information contained in each video frame by any suitable image recognition technique.
The apparatus 500 may also include a continuity detection module 530 that determines whether a sequence of video frames of the video follows the first pattern based on the identified content and determines that the video of the camera is discontinuous if the sequence of video frames does not follow the first pattern. The sequence of video frames not following the first pattern may include at least one of: the sequence of video frames includes the same content related to the dynamic information, the sequence of two video frames includes the different content related to the dynamic information from the sequence of the dynamic information in the first mode, the sequence of video frames lacks video frames corresponding to a subset of the dynamic information if the rate of change of the dynamic information is equal to the frame rate of the video, and the sequence of video frames lacks video frames corresponding to the dynamic information in the subset of the dynamic information acquired at the frame rate if the rate of change of the dynamic information is greater than the frame rate of the video.
The first pattern may be known to the apparatus 500 or may be inferred by the apparatus 500 based on content identified from the sequence of video frames. For example, the apparatus 500 may include an optional mode determination module 540 that may receive information about the first mode from other devices or users, or may infer information about the first mode based on content identified from a sequence of video frames.
In another embodiment, the video acquisition module 510 may receive multiple videos of the same test object captured synchronously by multiple cameras. The continuity detection module 530 may determine whether the content associated with the dynamic information for corresponding ones of the videos is consistent. If the content of the corresponding video frames in the videos of the at least two cameras is inconsistent, the continuity detection module 530 may determine that the sequence of video frames of at least one of the at least two cameras does not follow the first pattern and that the video of the at least one camera is discontinuous. In this embodiment, the apparatus 500 may or may not be aware of the first mode.
Although fig. 5 shows a plurality of separate modules of the apparatus 500 for detecting video continuity of a camera, some or all of the modules may be implemented in combination, or one or more of the modules may be split into a plurality of sub-modules. The various modules of apparatus 500 may be implemented using hardware and/or software.
This patent has simplified the processing procedure that detects the video continuity, has overcome the video image and has detected with the unable accurate problem of judging of naked eye, makes camera video quality detect more high-efficient, accurate. The invention can be applied to the intelligent family field, and provides a technology for detecting whether the video of the network camera has discontinuous phenomenon (such as frame repetition, frame loss, frame sequence error and the like) for an intelligent home service provider. For example, using the techniques described herein, a camera manufacturer may self-test the quality of a camera, a smart home service provider may verify the video quality before or after the camera is installed, and a user may also routinely monitor the video quality before or after the camera is put into service. The invention can also be applied to any electronic product with a camera to detect whether the video shot by the camera has a discontinuous phenomenon (such as frame repetition, frame loss, frame sequence error and the like).
The various steps and modules of the techniques described above may be implemented in hardware, software, or a combination thereof. If implemented in hardware, the various illustrative steps, modules, and circuits described in connection with this disclosure may be implemented or performed with a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic component, a hardware component, or any combination thereof. A general purpose processor may be a processor, microprocessor, controller, microcontroller, state machine, or the like. If implemented in software, the various illustrative steps, modules, described in connection with this disclosure may be stored on a computer readable medium or transmitted as one or more instructions or code. Software modules implementing various operations of the present disclosure may reside in storage media such as RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, removable disk, CD-ROM, cloud storage, etc. A storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium, as well as execute corresponding program modules to implement the various steps of the present disclosure. Moreover, software-based embodiments may be uploaded, downloaded, or accessed remotely via suitable communication means. Such suitable communication means include, for example, the internet, world wide web, intranet, software applications, cable (including fiber optic cable), magnetic communications, electromagnetic communications (including RF, microwave and infrared communications), electronic communications, or other such communication means.
It is also noted that the embodiments may be described as a process which is depicted as a flowchart, a flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel or concurrently. Additionally, the order of the operations may be rearranged.
The disclosed methods, apparatus, and systems should not be limited in any way. Rather, the present disclosure encompasses all novel and non-obvious features and aspects of the various disclosed embodiments (both alone and in various combinations and subcombinations with one another). The disclosed methods, apparatus and systems are not limited to any specific aspect or feature or combination thereof, nor do any of the disclosed embodiments require that any one or more specific advantages be present or that certain or all technical problems be solved.
While the embodiments of the present disclosure have been described above with reference to the accompanying drawings, the present disclosure is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many modifications may be made by those of ordinary skill in the art without departing from the spirit of the disclosure and the scope of the claims, which fall within the scope of the present disclosure.
Claims (8)
1. A method for detecting video continuity of a camera, comprising:
receiving video of a test object captured by a camera over a period of time, the test object having dynamic information that varies in a first pattern over the period of time, the test object being one of: a clock displaying a time change; a timer or counter; and means for dynamically switching the displayed pictures or text;
identifying content in each video frame of the video that is related to the dynamic information;
determining whether a sequence of video frames of the video follows the first pattern based on the identified content; and
if the sequence of video frames does not follow the first pattern, a video discontinuity of the camera is determined.
2. The method for detecting video continuity of a camera as recited in claim 1, wherein the sequence of video frames not following the first pattern comprises at least one of:
in the case where the rate of change of the dynamic information is greater than or equal to the frame rate of the video, successive video frames in the sequence of video frames include the same content related to the dynamic information;
the order of the content related to the dynamic information included by two video frames in the sequence of video frames is different from the order of the dynamic information in the first mode;
in the event that the rate of change of the dynamic information is equal to the frame rate of the video, the sequence of video frames lacks video frames corresponding to a subset of the dynamic information;
under the condition that the change rate of the dynamic information is larger than the frame rate of the video, the video frame sequence lacks video frames corresponding to the dynamic information in the subset acquired by the dynamic information according to the frame rate; and
in the case where the rate of change of the dynamic information is smaller than the frame rate of the video, the number of successive frames including the same content related to the dynamic information in the video exceeds an upper limit threshold or falls below a lower limit threshold.
3. The method for detecting video continuity of cameras of claim 1, wherein receiving video of a test object captured by a camera over a period of time comprises receiving a plurality of video of the test object captured by a plurality of cameras synchronously, and if the content of corresponding video frames in the video of at least two cameras is inconsistent, determining that the sequence of video frames of at least one of the at least two cameras does not follow the first pattern and that the video of the at least one camera is discontinuous.
4. The method for detecting video continuity of a camera as recited in claim 1, wherein the first pattern is known or inferred based on content identified from the sequence of video frames.
5. An apparatus for detecting video continuity of a camera, comprising:
a video acquisition module that receives video of a test object captured by a camera over a period of time, the test object having dynamic information that varies according to a first pattern over the period of time, the test object being one of: a clock displaying a time change; a timer or counter; and means for dynamically switching the displayed pictures or text;
an image recognition module that recognizes content related to the dynamic information in each video frame of the video; and
a continuity detection module that determines, based on the identified content, whether a sequence of video frames of the video follows the first pattern, and if the sequence of video frames does not follow the first pattern, determines that video of the camera is discontinuous.
6. The apparatus for detecting video continuity of a camera as recited in claim 5, wherein the sequence of video frames not following the first pattern comprises at least one of:
in the case where the rate of change of the dynamic information is greater than or equal to the frame rate of the video, successive video frames in the sequence of video frames include the same content related to the dynamic information;
the order of the content related to the dynamic information included by two video frames in the sequence of video frames is different from the order of the dynamic information in the first mode;
in the event that the rate of change of the dynamic information is equal to the frame rate of the video, the sequence of video frames lacks video frames corresponding to a subset of the dynamic information;
under the condition that the change rate of the dynamic information is larger than the frame rate of the video, the video frame sequence lacks video frames corresponding to the dynamic information in the subset acquired by the dynamic information according to the frame rate; and
in the case where the rate of change of the dynamic information is smaller than the frame rate of the video, the number of successive frames including the same content related to the dynamic information in the video exceeds an upper limit threshold or falls below a lower limit threshold.
7. The apparatus for detecting video continuity of cameras as recited in claim 5, wherein the video acquisition module receives a plurality of videos of the test object synchronously captured by a plurality of cameras, and if the content of corresponding video frames in videos of at least two cameras is inconsistent, the continuity detection module determines that the sequence of video frames of at least one of the at least two cameras does not follow the first pattern and that the video of the at least one camera is discontinuous.
8. The apparatus for detecting video continuity of a camera as recited in claim 5, wherein the first pattern is known or inferred based on content identified from the sequence of video frames.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911309760.XA CN112995650B (en) | 2019-12-18 | 2019-12-18 | Method and device for detecting video continuity of camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911309760.XA CN112995650B (en) | 2019-12-18 | 2019-12-18 | Method and device for detecting video continuity of camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112995650A CN112995650A (en) | 2021-06-18 |
| CN112995650B true CN112995650B (en) | 2023-10-20 |
Family
ID=76343930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911309760.XA Active CN112995650B (en) | 2019-12-18 | 2019-12-18 | Method and device for detecting video continuity of camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112995650B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114125806B (en) * | 2021-09-24 | 2022-08-23 | 浙江大学 | Wireless camera detection method based on cloud storage mode of wireless network flow |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102065318A (en) * | 2010-12-31 | 2011-05-18 | 北京中科大洋科技发展股份有限公司 | System and method for detecting frame loss and image split of digital video system |
| CN107734329A (en) * | 2017-11-14 | 2018-02-23 | 浙江贝尔技术有限公司 | A kind of detecting system and detection method of baseband digital video frame per second |
| CN108777788A (en) * | 2018-08-01 | 2018-11-09 | 深圳市捷视飞通科技股份有限公司 | Video quality test method, computer equipment and storage medium |
-
2019
- 2019-12-18 CN CN201911309760.XA patent/CN112995650B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102065318A (en) * | 2010-12-31 | 2011-05-18 | 北京中科大洋科技发展股份有限公司 | System and method for detecting frame loss and image split of digital video system |
| CN107734329A (en) * | 2017-11-14 | 2018-02-23 | 浙江贝尔技术有限公司 | A kind of detecting system and detection method of baseband digital video frame per second |
| CN108777788A (en) * | 2018-08-01 | 2018-11-09 | 深圳市捷视飞通科技股份有限公司 | Video quality test method, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112995650A (en) | 2021-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109408384B (en) | Software application testing method and device, processor and electronic device | |
| CN109587008B (en) | Method, device and storage medium for detecting abnormal flow data | |
| CN108322737B (en) | Method and device for measuring camera shooting frame rate | |
| CN113518011A (en) | Abnormality detection method and apparatus, electronic device, and computer-readable storage medium | |
| CN116126580B (en) | Touch display control method, device, equipment and storage medium | |
| CN112631896B (en) | Equipment performance test method and device, storage medium and electronic equipment | |
| CN112995650B (en) | Method and device for detecting video continuity of camera | |
| CN112364918B (en) | Abnormality recognition method, terminal, and computer-readable storage medium | |
| CN116611006B (en) | Fault identification method and device of electric kettle based on user feedback | |
| CN112837640A (en) | Screen dynamic picture testing method, system, electronic equipment and storage medium | |
| CN116467110B (en) | Method and system for detecting damage of tablet personal computer | |
| CN111368104B (en) | Information processing method, device and equipment | |
| CN116363984A (en) | Display screen flicker correction method and correction system | |
| CN110113630A (en) | Video detecting method, device, electronic equipment and storage medium | |
| EP4354297A1 (en) | Data integrity processing method and apparatus, and electronic device | |
| CN111553408B (en) | Automatic test method for video recognition software | |
| CN111209057B (en) | Method and device for quickly adjusting sensing terminal | |
| CN114676422A (en) | Resource access abnormity detection method, device and equipment | |
| CN112949490A (en) | Device action detection method and device, electronic device and readable storage medium | |
| CN113760689A (en) | Interface fault alarm method, device, equipment and storage medium | |
| CN112988475B (en) | Disaster tolerance test method, device, test server and medium | |
| CN113191017B (en) | Virtual measurement model construction method, virtual measurement method, system, electronic device and computer-readable storage medium | |
| CN113358172B (en) | Method, device, equipment and medium for automatically setting electromechanical synchronization of water meter | |
| CN112308417B (en) | Anti-cheating method and system for online evaluation | |
| CN118331872A (en) | Application program pulling method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220128 Address after: Room 1423, No. 1256 and 1258, Wanrong Road, Jing'an District, Shanghai 200072 Applicant after: Tianyi Digital Life Technology Co.,Ltd. Address before: 201702 3rd floor, 158 Shuanglian Road, Qingpu District, Shanghai Applicant before: Tianyi Smart Family Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |