CN111246203A - Camera blur detection method and device - Google Patents
Camera blur detection method and device Download PDFInfo
- Publication number
- CN111246203A CN111246203A CN202010072735.0A CN202010072735A CN111246203A CN 111246203 A CN111246203 A CN 111246203A CN 202010072735 A CN202010072735 A CN 202010072735A CN 111246203 A CN111246203 A CN 111246203A
- Authority
- CN
- China
- Prior art keywords
- fuzzy
- detected
- camera
- template
- photos
- 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.)
- Pending
Links
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
Abstract
The invention aims to provide a camera blur detection method and a device, the camera blur detection model is trained on the basis of the preset number of clear template photos and the preset number of blur template photos, whether the photo to be detected is blurred is judged on the basis of the camera blur detection model, whether the camera to be detected is a shooting blur camera is further judged on the basis of the result of whether the photo to be detected is blurred, if the photo to be detected is judged to be blurred, the camera to be detected is judged to be a camera with a blurred shooting problem, otherwise, the camera to be detected is judged to be a camera without a problem with a clear shooting, and therefore the shooting performance of the camera to be detected can be accurately and efficiently judged.
Description
Technical Field
The invention relates to the field of computers, in particular to a camera blur detection method and device.
Background
The existing cameras on intelligent terminals such as mobile phones and the like mostly carry out fuzzy detection through manpower, the detection process is time-consuming and labor-consuming, and the problems of inaccuracy exist.
Disclosure of Invention
The invention aims to provide a camera blurring detection method and a device.
According to an aspect of the present invention, there is provided a camera blur detection method, including:
acquiring a preset number of clear template pictures and fuzzy template pictures obtained by shooting template images;
training a camera fuzzy detection model based on the preset number of clear template photos and fuzzy template photos;
controlling a camera to be detected to shoot the template image to obtain a picture to be detected;
judging whether the photo to be detected is fuzzy or not based on the camera fuzzy detection model;
and if the to-be-detected photo is judged to be fuzzy, judging that the to-be-detected camera is a camera with a fuzzy shooting problem.
Further, in the above method, training a camera blur detection model based on the preset number of clear template photos and blur template photos includes:
sequentially cutting each clear template photo into a plurality of small clear photos according to a preset size and a preset step length, wherein two small clear photos adjacent to each other in the cutting sequence have a partial overlapping area; sequentially segmenting each fuzzy template photo into a plurality of small fuzzy photos according to a preset size and a preset step length, wherein two small fuzzy photos adjacent in the segmentation sequence have a partial overlapping area;
acquiring a plurality of small background pictures with the preset size;
and putting the plurality of small block clear photos representing clear categories, the plurality of small block fuzzy photos representing fuzzy categories and the plurality of small block background photos representing background categories into a convolutional neural network model for training to obtain the camera fuzzy detection model.
Further, in the above method, determining whether the to-be-detected photo is blurred based on the camera blur detection model includes:
sequentially cutting each photo to be detected into a plurality of small photos to be detected according to the preset size and step length, wherein two small photos to be detected which are adjacent in the cutting sequence have a partial overlapping area;
inputting each small photo to be detected into the camera fuzzy detection model to obtain the probability of each small photo to be detected relative to the clear category, the fuzzy category and the background category;
if the probability of a small block of the photo to be detected relative to the clear category is larger than a preset probability threshold value, judging that the small block of the photo to be detected is fuzzy;
and if the number of the small to-be-detected pictures judged to be fuzzy exceeds a preset number threshold, judging that the to-be-detected pictures are fuzzy.
Further, in the above method, the template image includes black stripes arranged at preset intervals on the white background, and the black stripes in the template image are in multiple rows.
Further, in the above method, a first preset included angle is formed between the odd rows of black stripes in the template image and the forward direction of the horizontal direction, and a second preset included angle is formed between the even rows of black stripes in the template image and the forward direction of the horizontal direction, where the second preset included angle is 180 degrees — the first preset included angle.
According to another aspect of the present invention, there is also provided a camera blur detection apparatus, wherein the apparatus includes:
the template acquisition module is used for acquiring a preset number of clear template photos and fuzzy template photos obtained by shooting the template images;
the training module is used for training a camera fuzzy detection model based on the preset number of the clear template photos and the fuzzy template photos;
the shooting module is used for controlling the camera to be detected to shoot the template image to obtain a picture to be detected;
the judging module is used for judging whether the photo to be detected is fuzzy or not based on the camera fuzzy detection model; and if the to-be-detected photo is judged to be fuzzy, judging that the to-be-detected camera is a camera with a fuzzy shooting problem.
Further, in the above apparatus, the training module is configured to segment each clear template photograph into a plurality of small clear photographs in sequence according to a preset size and a preset step length, where two small clear photographs adjacent to each other in the segmentation sequence have a partial overlapping area; sequentially segmenting each fuzzy template photo into a plurality of small fuzzy photos according to a preset size and a preset step length, wherein two small fuzzy photos adjacent in the segmentation sequence have a partial overlapping area; acquiring a plurality of small background pictures with the preset size; and putting the plurality of small block clear photos representing clear categories, the plurality of small block fuzzy photos representing fuzzy categories and the plurality of small block background photos representing background categories into a convolutional neural network model for training to obtain the camera fuzzy detection model.
Further, in the above apparatus, the determining module is configured to segment each photo to be detected into a plurality of small photos to be detected according to a preset size and a preset step length, where two small photos to be detected that are adjacent in the segmentation sequence have a partially overlapping area; inputting each small photo to be detected into the camera fuzzy detection model to obtain the probability of each small photo to be detected relative to the clear category, the fuzzy category and the background category; if the probability of a small block of the photo to be detected relative to the clear category is larger than a preset probability threshold value, judging that the small block of the photo to be detected is fuzzy; and if the number of the small to-be-detected pictures judged to be fuzzy exceeds a preset number threshold, judging that the to-be-detected pictures are fuzzy.
Further, in the above apparatus, the template image includes black stripes arranged at preset intervals on the white background, and the black stripes in the template image are in multiple rows.
Further, in the above apparatus, the odd rows of black stripes in the template image form a first preset included angle with the forward direction of the horizontal direction, and the even rows of black stripes in the template image form a second preset included angle with the forward direction of the horizontal direction, where the second preset included angle is 180 degrees — the first preset included angle.
According to another aspect of the present invention, there is also provided a computing-based device, including:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
acquiring a preset number of clear template pictures and fuzzy template pictures obtained by shooting template images;
training a camera fuzzy detection model based on the preset number of clear template photos and fuzzy template photos;
controlling a camera to be detected to shoot the template image to obtain a picture to be detected;
judging whether the photo to be detected is fuzzy or not based on the camera fuzzy detection model;
and if the to-be-detected photo is judged to be fuzzy, judging that the to-be-detected camera is a camera with a fuzzy shooting problem.
According to another aspect of the present invention, there is also provided a computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, cause the processor to:
acquiring a preset number of clear template pictures and fuzzy template pictures obtained by shooting template images;
training a camera fuzzy detection model based on the preset number of clear template photos and fuzzy template photos;
controlling a camera to be detected to shoot the template image to obtain a picture to be detected;
judging whether the photo to be detected is fuzzy or not based on the camera fuzzy detection model;
and if the to-be-detected photo is judged to be fuzzy, judging that the to-be-detected camera is a camera with a fuzzy shooting problem.
Compared with the prior art, the method and the device have the advantages that the camera fuzzy detection model is trained on the basis of the preset number of the clear template pictures and the fuzzy template pictures, whether the pictures to be detected are fuzzy is judged on the basis of the camera fuzzy detection model, whether the pictures to be detected are fuzzy is judged on the basis of the result that the pictures to be detected are fuzzy, whether the cameras to be detected are shooting fuzzy cameras is judged, if the pictures to be detected are fuzzy, the cameras to be detected are judged to be shooting fuzzy cameras, and if the pictures to be detected are not fuzzy, the cameras to be shot clearly are judged to be problem-free cameras, so that the shooting performance of.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments made with reference to the following drawings:
FIG. 1 shows a flow diagram of a camera blur detection method according to an embodiment of the invention;
FIG. 2 illustrates a template image diagram according to an embodiment of the invention.
The same or similar reference numbers in the drawings identify the same or similar elements.
Detailed Description
The present invention is described in further detail below with reference to the attached drawing figures.
In a typical configuration of the present application, the terminal, the device serving the network, and the trusted party each include one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory computer readable media (transient media), such as modulated data signals and carrier waves.
As shown in fig. 1, the present invention provides a camera blur detection method, including:
step S1, acquiring a preset number of clear template pictures and fuzzy template pictures obtained by shooting template images;
here, the template image captured in the clear template photograph is completely clear, and the template image captured in the blurred template photograph is wholly or partially blurred;
a template image for static display can be arranged on a backlight source;
the camera can be a camera on an intelligent terminal such as a mobile phone and a PAD;
step S2, training a camera fuzzy detection model based on the preset number of clear template photos and fuzzy template photos;
step S3, controlling a camera to be detected to shoot the template image to obtain a picture to be detected;
after waiting for 10 seconds, controlling a camera to be detected on the terminal such as the mobile phone to automatically focus and adjust light, and controlling the camera to be detected to shoot a template image to obtain a picture to be detected;
step S4, judging whether the photo to be detected is fuzzy or not based on the camera fuzzy detection model;
and step S5, if the photo to be detected is judged to be fuzzy, the camera to be detected is judged to be a camera with a fuzzy shooting problem.
The camera fuzzy detection model is trained based on the preset number of the clear template pictures and the fuzzy template pictures, whether the picture to be detected is fuzzy is judged based on the camera fuzzy detection model, whether the camera to be detected is a shooting fuzzy camera is judged based on the result that whether the picture to be detected is fuzzy, if the picture to be detected is judged to be fuzzy, the camera to be detected is judged to be a shooting fuzzy camera, and if not, the camera to be detected is judged to be a clear shooting camera without problems, so that the shooting performance of the camera to be detected can be accurately and efficiently judged.
In an embodiment of the camera blur detection method of the present invention, in step S2, training a camera blur detection model based on the preset number of clear template photos and blur template photos includes:
step S21, sequentially cutting each clear template photo into a plurality of small clear photos according to the preset size and step length, wherein the two small clear photos adjacent in the cutting sequence have partial overlapping areas; sequentially segmenting each fuzzy template photo into a plurality of small fuzzy photos according to a preset size and a preset step length, wherein two small fuzzy photos adjacent in the segmentation sequence have a partial overlapping area;
according to the preset size and step length, the method can be divided into two adjacent small clear photos with partial overlapping areas in the dividing sequence, and can be divided into two adjacent small fuzzy photos with partial overlapping areas in the dividing sequence, so that the accurate training of a subsequent model is facilitated;
step S22, obtaining a plurality of small background pictures with the preset size;
and step S23, putting the plurality of small block clear photos representing clear types, the plurality of small block fuzzy photos representing fuzzy types and the plurality of small block background photos representing background types into a convolutional neural network model for training to obtain the camera fuzzy detection model.
In this embodiment, the three types of photos, namely the multiple small block clear photos representing the clear category, the multiple small block fuzzy photos representing the fuzzy category, and the multiple small block background photos representing the background category, are respectively put into the convolutional neural network model for training, so that the camera fuzzy detection model can be obtained through efficient and reliable training.
In an embodiment of the camera blur detection method of the present invention, the step S4 of determining whether the to-be-detected picture is blurred based on the camera blur detection model includes:
step S41, sequentially cutting each photo to be detected into a plurality of small photos to be detected according to the preset size and step length, wherein two small photos to be detected which are adjacent in the cutting sequence have a partial overlapping area;
the cutting mode of the photo to be detected is the same as that of the template photo during the previous model training;
step S42, inputting each small photo to be detected into the camera fuzzy detection model to obtain the probability of each small photo to be detected relative to the clear category, the fuzzy category and the background category;
step S43, if the probability of a small block to be detected relative to the clear type is larger than a preset probability threshold, judging that the small block to be detected is fuzzy;
and step S44, if the number of the small to-be-detected pictures judged to be fuzzy exceeds a preset number threshold, judging that the to-be-detected pictures are fuzzy.
Whether the probability of each small block of the photo to be detected relative to the clear category is larger than a preset probability threshold value or not is judged, and whether the number of the blurred small blocks of the photo to be detected exceeds a preset number threshold value or not is judged, so that whether the photo to be detected is blurred or not can be judged reliably and efficiently.
In an embodiment of the camera blur detection method of the present invention, as shown in fig. 2, the template image includes black stripes arranged at preset intervals on a white background, and the black stripes in the template image are in multiple rows.
In the invention, the template image is displayed as the black stripes arranged on the white background at preset intervals, so that whether each black stripe is clear or fuzzy or not can be easily identified in the subsequent process of training the model and identifying the photo to be detected through the model.
As shown in fig. 2, by providing a plurality of rows of black stripes spaced apart from each other on the white background, the black stripes spaced apart from each other can be distributed over the entire field of view as much as possible when taking a picture, so as to improve the effect of the picture taken by each wide-angle camera.
In an embodiment of the camera blur detection method of the present invention, a first preset included angle is formed between odd-numbered rows of black stripes in the template image and the forward direction of the horizontal direction, and a second preset included angle is formed between even-numbered rows of black stripes in the template image and the forward direction of the horizontal direction, where the second preset included angle is 180 degrees — the first preset included angle.
Here, as shown in fig. 2, the black stripes are arranged in an oblique longitudinal direction with a preset included angle with the horizontal direction, so that image recognition of black and white stripe regions is facilitated, and the recognition efficiency and reliability are improved.
As shown in fig. 2, the black stripes of the first row and the third row in the template image form an included angle of 60 degrees with the forward direction of the horizontal direction, and the black stripes of the second row and the fourth row in the template image form an included angle of 120 degrees with the forward direction of the horizontal direction, so that the position of stripe blurring can be identified more efficiently subsequently, and the power line 1 of the backlight source can be connected to provide an illumination light source for the template image.
As shown in fig. 2, the black stripes of each row may be spaced apart by 10 mm, the black stripes of the same row may be spaced apart by 8 mm, and each black stripe may have a width of 8 mm.
The invention provides a camera blur detection device, comprising:
the template acquisition module is used for acquiring a preset number of clear template photos and fuzzy template photos obtained by shooting the template images;
here, the template image captured in the clear template photograph is completely clear, and the template image captured in the blurred template photograph is wholly or partially blurred;
a template image for static display can be arranged on a backlight source;
the camera can be a camera on an intelligent terminal such as a mobile phone and a PAD;
the training module is used for training a camera fuzzy detection model based on the preset number of the clear template photos and the fuzzy template photos;
the shooting module is used for controlling the camera to be detected to shoot the template image to obtain a picture to be detected;
after waiting for 10 seconds, controlling a camera to be detected on the terminal such as the mobile phone to automatically focus and adjust light, and controlling the camera to be detected to shoot a template image to obtain a picture to be detected;
the judging module is used for judging whether the photo to be detected is fuzzy or not based on the camera fuzzy detection model; and if the to-be-detected photo is judged to be fuzzy, judging that the to-be-detected camera is a camera with a fuzzy shooting problem.
The camera fuzzy detection model is trained based on the preset number of the clear template pictures and the fuzzy template pictures, whether the picture to be detected is fuzzy is judged based on the camera fuzzy detection model, whether the camera to be detected is a shooting fuzzy camera is judged based on the result that whether the picture to be detected is fuzzy, if the picture to be detected is judged to be fuzzy, the camera to be detected is judged to be a shooting fuzzy camera, and if not, the camera to be detected is judged to be a clear shooting camera without problems, so that the shooting performance of the camera to be detected can be accurately and efficiently judged.
In an embodiment of the camera blur detection device, the training module is configured to segment each clear template photo into a plurality of small clear photos in sequence according to a preset size and a preset step length, wherein two small clear photos adjacent to each other in the segmentation sequence have a partial overlapping region; sequentially segmenting each fuzzy template photo into a plurality of small fuzzy photos according to a preset size and a preset step length, wherein two small fuzzy photos adjacent in the segmentation sequence have a partial overlapping area; acquiring a plurality of small background pictures with the preset size; and putting the plurality of small block clear photos representing clear categories, the plurality of small block fuzzy photos representing fuzzy categories and the plurality of small block background photos representing background categories into a convolutional neural network model for training to obtain the camera fuzzy detection model.
According to the preset size and step length, the method can be divided into two adjacent small clear photos with partial overlapping areas in the dividing sequence, and can be divided into two adjacent small fuzzy photos with partial overlapping areas in the dividing sequence, so that the accurate training of a subsequent model is facilitated;
in the embodiment, the three types of photos, namely the plurality of small block clear photos representing the clear category, the plurality of small block fuzzy photos representing the fuzzy category and the plurality of small block background photos representing the background category, are respectively put into the convolutional neural network model for training, so that the camera fuzzy detection model can be obtained through efficient and reliable training.
In an embodiment of the camera blur detection method of the present invention, the determination module is configured to segment each to-be-detected picture into a plurality of small to-be-detected pictures in sequence according to a preset size and a preset step length, where two small to-be-detected pictures adjacent in the segmentation sequence have a partially overlapping area; inputting each small photo to be detected into the camera fuzzy detection model to obtain the probability of each small photo to be detected relative to the clear category, the fuzzy category and the background category; if the probability of a small block of the photo to be detected relative to the clear category is larger than a preset probability threshold value, judging that the small block of the photo to be detected is fuzzy; and if the number of the small to-be-detected pictures judged to be fuzzy exceeds a preset number threshold, judging that the to-be-detected pictures are fuzzy.
The cutting mode of the photo to be detected is the same as that of the template photo during the previous model training;
whether the probability of each small block of the photo to be detected relative to the clear category is larger than a preset probability threshold value or not is judged, and whether the number of the blurred small blocks of the photo to be detected exceeds a preset number threshold value or not is judged, so that whether the photo to be detected is blurred or not can be judged reliably and efficiently.
In an embodiment of the camera blur detection method of the present invention, as shown in fig. 2, the template image includes black stripes arranged at preset intervals on a white background, and the black stripes in the template image are in multiple rows.
In the invention, the template image is displayed as the black stripes arranged on the white background at preset intervals, so that whether each black stripe is clear or fuzzy or not can be easily identified in the subsequent process of training the model and identifying the photo to be detected through the model.
As shown in fig. 2, by providing a plurality of rows of black stripes spaced apart from each other on the white background, the black stripes spaced apart from each other can be distributed over the entire field of view as much as possible when taking a picture, so as to improve the effect of the picture taken by each wide-angle camera.
In an embodiment of the camera blur detection method of the present invention, a first preset included angle is formed between odd-numbered rows of black stripes in the template image and the forward direction of the horizontal direction, and a second preset included angle is formed between even-numbered rows of black stripes in the template image and the forward direction of the horizontal direction, where the second preset included angle is 180 degrees — the first preset included angle.
Here, as shown in fig. 2, the black stripes are arranged in an oblique longitudinal direction with a preset included angle with the horizontal direction, so that image recognition of black and white stripe regions is facilitated, and the recognition efficiency and reliability are improved.
As shown in fig. 2, the black stripes of the first row and the third row in the template image form an included angle of 60 degrees with the forward direction of the horizontal direction, and the black stripes of the second row and the fourth row in the template image form an included angle of 120 degrees with the forward direction of the horizontal direction, so that the position of stripe blurring can be identified more efficiently subsequently, and the power line 1 of the backlight source can be connected to provide an illumination light source for the template image.
As shown in fig. 2, the black stripes of each row may be spaced apart by 10 mm, the black stripes of the same row may be spaced apart by 8 mm, and each black stripe may have a width of 8 mm.
According to another aspect of the present invention, there is also provided a computing-based device, including:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
acquiring a preset number of clear template pictures and fuzzy template pictures obtained by shooting template images;
training a camera fuzzy detection model based on the preset number of clear template photos and fuzzy template photos;
controlling a camera to be detected to shoot the template image to obtain a picture to be detected;
judging whether the photo to be detected is fuzzy or not based on the camera fuzzy detection model;
and if the to-be-detected photo is judged to be fuzzy, judging that the to-be-detected camera is a camera with a fuzzy shooting problem.
According to another aspect of the present invention, there is also provided a computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, cause the processor to:
acquiring a preset number of clear template pictures and fuzzy template pictures obtained by shooting template images;
training a camera fuzzy detection model based on the preset number of clear template photos and fuzzy template photos;
controlling a camera to be detected to shoot the template image to obtain a picture to be detected;
judging whether the photo to be detected is fuzzy or not based on the camera fuzzy detection model;
and if the to-be-detected photo is judged to be fuzzy, judging that the to-be-detected camera is a camera with a fuzzy shooting problem.
For details of embodiments of each device and storage medium of the present invention, reference may be made to corresponding parts of each method embodiment, and details are not described herein again.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
It should be noted that the present invention may be implemented in software and/or in a combination of software and hardware, for example, as an Application Specific Integrated Circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present invention may be executed by a processor to implement the steps or functions described above. Also, the software programs (including associated data structures) of the present invention can be stored in a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. Further, some of the steps or functions of the present invention may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.
In addition, some of the present invention can be applied as a computer program product, such as computer program instructions, which when executed by a computer, can invoke or provide the method and/or technical solution according to the present invention through the operation of the computer. Program instructions which invoke the methods of the present invention may be stored on a fixed or removable recording medium and/or transmitted via a data stream on a broadcast or other signal-bearing medium and/or stored within a working memory of a computer device operating in accordance with the program instructions. An embodiment according to the invention herein comprises an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to perform a method and/or solution according to embodiments of the invention as described above.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the apparatus claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Claims (12)
1. A camera blur detection method, wherein the method comprises:
acquiring a preset number of clear template pictures and fuzzy template pictures obtained by shooting template images;
training a camera fuzzy detection model based on the preset number of clear template photos and fuzzy template photos;
controlling a camera to be detected to shoot the template image to obtain a picture to be detected;
judging whether the photo to be detected is fuzzy or not based on the camera fuzzy detection model;
and if the to-be-detected photo is judged to be fuzzy, judging that the to-be-detected camera is a camera with a fuzzy shooting problem.
2. The method of claim 1, wherein training a camera blur detection model based on the preset number of clear and blurred template photographs comprises:
sequentially cutting each clear template photo into a plurality of small clear photos according to a preset size and a preset step length, wherein two small clear photos adjacent to each other in the cutting sequence have a partial overlapping area; sequentially segmenting each fuzzy template photo into a plurality of small fuzzy photos according to a preset size and a preset step length, wherein two small fuzzy photos adjacent in the segmentation sequence have a partial overlapping area;
acquiring a plurality of small background pictures with the preset size;
and putting the plurality of small block clear photos representing clear categories, the plurality of small block fuzzy photos representing fuzzy categories and the plurality of small block background photos representing background categories into a convolutional neural network model for training to obtain the camera fuzzy detection model.
3. The method of claim 2, wherein determining whether the photo to be detected is blurred based on the camera blur detection model comprises:
sequentially cutting each photo to be detected into a plurality of small photos to be detected according to the preset size and step length, wherein two small photos to be detected which are adjacent in the cutting sequence have a partial overlapping area;
inputting each small photo to be detected into the camera fuzzy detection model to obtain the probability of each small photo to be detected relative to the clear category, the fuzzy category and the background category;
if the probability of a small block of the photo to be detected relative to the clear category is larger than a preset probability threshold value, judging that the small block of the photo to be detected is fuzzy;
and if the number of the small to-be-detected pictures judged to be fuzzy exceeds a preset number threshold, judging that the to-be-detected pictures are fuzzy.
4. The method of claim 1, wherein the template image comprises black stripes arranged at preset intervals on a white background, the black stripes in the template image being in a plurality of rows.
5. The method according to claim 4, wherein the black stripes in the odd rows of the template image form a first preset angle with the forward direction of the horizontal direction, and the black stripes in the even rows of the template image form a second preset angle with the forward direction of the horizontal direction, wherein the second preset angle is 180 degrees — the first preset angle.
6. A camera blur detection apparatus, wherein the apparatus comprises:
the template acquisition module is used for acquiring a preset number of clear template photos and fuzzy template photos obtained by shooting the template images;
the training module is used for training a camera fuzzy detection model based on the preset number of the clear template photos and the fuzzy template photos;
the shooting module is used for controlling the camera to be detected to shoot the template image to obtain a picture to be detected;
the judging module is used for judging whether the photo to be detected is fuzzy or not based on the camera fuzzy detection model; and if the to-be-detected photo is judged to be fuzzy, judging that the to-be-detected camera is a camera with a fuzzy shooting problem.
7. The device of claim 6, wherein the training module is configured to segment each clear template photo into a plurality of small clear photos in sequence according to a preset size and a preset step length, wherein two small clear photos adjacent to each other in the segmentation sequence have a partial overlapping area; sequentially segmenting each fuzzy template photo into a plurality of small fuzzy photos according to a preset size and a preset step length, wherein two small fuzzy photos adjacent in the segmentation sequence have a partial overlapping area; acquiring a plurality of small background pictures with the preset size; and putting the plurality of small block clear photos representing clear categories, the plurality of small block fuzzy photos representing fuzzy categories and the plurality of small block background photos representing background categories into a convolutional neural network model for training to obtain the camera fuzzy detection model.
8. The device according to claim 7, wherein the judging module is configured to segment each photo to be detected into a plurality of small photos to be detected according to a preset size and a preset step length, wherein two small photos to be detected adjacent in the segmentation sequence have a partially overlapped region; inputting each small photo to be detected into the camera fuzzy detection model to obtain the probability of each small photo to be detected relative to the clear category, the fuzzy category and the background category; if the probability of a small block of the photo to be detected relative to the clear category is larger than a preset probability threshold value, judging that the small block of the photo to be detected is fuzzy; and if the number of the small to-be-detected pictures judged to be fuzzy exceeds a preset number threshold, judging that the to-be-detected pictures are fuzzy.
9. The apparatus of claim 6, wherein the template image comprises black stripes arranged at preset intervals on a white background, the black stripes in the template image being in a plurality of rows.
10. The apparatus according to claim 9, wherein the odd rows of black stripes in the template image form a first preset angle with the forward direction of the horizontal direction, and the even rows of black stripes in the template image form a second preset angle with the forward direction of the horizontal direction, wherein the second preset angle is 180 degrees — the first preset angle.
11. A computing-based device, comprising:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
acquiring a preset number of clear template pictures and fuzzy template pictures obtained by shooting template images;
training a camera fuzzy detection model based on the preset number of clear template photos and fuzzy template photos;
controlling a camera to be detected to shoot the template image to obtain a picture to be detected;
judging whether the photo to be detected is fuzzy or not based on the camera fuzzy detection model;
and if the to-be-detected photo is judged to be fuzzy, judging that the to-be-detected camera is a camera with a fuzzy shooting problem.
12. A computer-readable storage medium having computer-executable instructions stored thereon, wherein the computer-executable instructions, when executed by a processor, cause the processor to:
acquiring a preset number of clear template pictures and fuzzy template pictures obtained by shooting template images;
training a camera fuzzy detection model based on the preset number of clear template photos and fuzzy template photos;
controlling a camera to be detected to shoot the template image to obtain a picture to be detected;
judging whether the photo to be detected is fuzzy or not based on the camera fuzzy detection model;
and if the to-be-detected photo is judged to be fuzzy, judging that the to-be-detected camera is a camera with a fuzzy shooting problem.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010072735.0A CN111246203A (en) | 2020-01-21 | 2020-01-21 | Camera blur detection method and device |
JP2022506070A JP2022542948A (en) | 2020-01-21 | 2020-10-14 | Camera blur inspection method and apparatus |
PCT/CN2020/120886 WO2021147383A1 (en) | 2020-01-21 | 2020-10-14 | Camera blur detection method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010072735.0A CN111246203A (en) | 2020-01-21 | 2020-01-21 | Camera blur detection method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111246203A true CN111246203A (en) | 2020-06-05 |
Family
ID=70872961
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010072735.0A Pending CN111246203A (en) | 2020-01-21 | 2020-01-21 | Camera blur detection method and device |
Country Status (3)
Country | Link |
---|---|
JP (1) | JP2022542948A (en) |
CN (1) | CN111246203A (en) |
WO (1) | WO2021147383A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021147383A1 (en) * | 2020-01-21 | 2021-07-29 | 上海万物新生环保科技集团有限公司 | Camera blur detection method and apparatus |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116028258B (en) * | 2023-03-22 | 2023-08-18 | 国网智联电商有限公司 | Equipment fault diagnosis method and system based on deep learning |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1992916A (en) * | 2005-12-28 | 2007-07-04 | 华晶科技股份有限公司 | Method of detecting image definition |
CN104780310A (en) * | 2015-01-27 | 2015-07-15 | 深圳市中瀛鑫科技股份有限公司 | Image blurring detection method and system and camera |
CN104899255A (en) * | 2015-05-15 | 2015-09-09 | 浙江大学 | Image database establishing method suitable for training deep convolution neural network |
CN105160678A (en) * | 2015-09-02 | 2015-12-16 | 山东大学 | Convolutional-neural-network-based reference-free three-dimensional image quality evaluation method |
CN106096605A (en) * | 2016-06-02 | 2016-11-09 | 史方 | A kind of image obscuring area detection method based on degree of depth study and device |
CN106920229A (en) * | 2017-01-22 | 2017-07-04 | 北京奇艺世纪科技有限公司 | Image obscuring area automatic testing method and system |
CN107948510A (en) * | 2017-11-27 | 2018-04-20 | 北京小米移动软件有限公司 | The method, apparatus and storage medium of Focussing |
CN109167998A (en) * | 2018-11-19 | 2019-01-08 | 深兰科技(上海)有限公司 | Detect method and device, the electronic equipment, storage medium of camera status |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE10022009C2 (en) * | 1999-11-26 | 2002-12-05 | Inb Vision Ag | Method and device for determining and at least partially correcting the errors of an image display system |
JP2012247743A (en) * | 2011-05-31 | 2012-12-13 | Konica Minolta Advanced Layers Inc | Chart for checking resolution and method for checking resolution |
CN110678875B (en) * | 2017-05-31 | 2023-07-11 | 宝洁公司 | System and method for guiding a user to take a self-photograph |
CN107644209A (en) * | 2017-09-21 | 2018-01-30 | 百度在线网络技术(北京)有限公司 | Method for detecting human face and device |
CN109886359B (en) * | 2019-03-25 | 2021-03-16 | 西安电子科技大学 | Small target detection method and detection system based on convolutional neural network |
CN111246203A (en) * | 2020-01-21 | 2020-06-05 | 上海悦易网络信息技术有限公司 | Camera blur detection method and device |
-
2020
- 2020-01-21 CN CN202010072735.0A patent/CN111246203A/en active Pending
- 2020-10-14 WO PCT/CN2020/120886 patent/WO2021147383A1/en active Application Filing
- 2020-10-14 JP JP2022506070A patent/JP2022542948A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1992916A (en) * | 2005-12-28 | 2007-07-04 | 华晶科技股份有限公司 | Method of detecting image definition |
CN104780310A (en) * | 2015-01-27 | 2015-07-15 | 深圳市中瀛鑫科技股份有限公司 | Image blurring detection method and system and camera |
CN104899255A (en) * | 2015-05-15 | 2015-09-09 | 浙江大学 | Image database establishing method suitable for training deep convolution neural network |
CN105160678A (en) * | 2015-09-02 | 2015-12-16 | 山东大学 | Convolutional-neural-network-based reference-free three-dimensional image quality evaluation method |
CN106096605A (en) * | 2016-06-02 | 2016-11-09 | 史方 | A kind of image obscuring area detection method based on degree of depth study and device |
CN106920229A (en) * | 2017-01-22 | 2017-07-04 | 北京奇艺世纪科技有限公司 | Image obscuring area automatic testing method and system |
CN107948510A (en) * | 2017-11-27 | 2018-04-20 | 北京小米移动软件有限公司 | The method, apparatus and storage medium of Focussing |
CN109167998A (en) * | 2018-11-19 | 2019-01-08 | 深兰科技(上海)有限公司 | Detect method and device, the electronic equipment, storage medium of camera status |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021147383A1 (en) * | 2020-01-21 | 2021-07-29 | 上海万物新生环保科技集团有限公司 | Camera blur detection method and apparatus |
Also Published As
Publication number | Publication date |
---|---|
JP2022542948A (en) | 2022-10-07 |
WO2021147383A1 (en) | 2021-07-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107087107B (en) | Image processing apparatus and method based on dual camera | |
WO2021147385A1 (en) | Screen detection method and apparatus | |
US8374454B2 (en) | Detection of objects using range information | |
CN110705532B (en) | Method, device and equipment for identifying copied image | |
CN111325716A (en) | Screen scratch fragmentation detection method and equipment | |
WO2019056527A1 (en) | Capturing method and device | |
CN111175318A (en) | Screen scratch fragmentation detection method and equipment | |
CN112511767B (en) | Video splicing method and device, and storage medium | |
CN113065374B (en) | Two-dimensional code identification method, device and equipment | |
CN111246203A (en) | Camera blur detection method and device | |
CN111210473A (en) | Mobile phone contour positioning method and equipment | |
CN111225204A (en) | Camera shake detection method and device | |
CN114782412A (en) | Image detection method, and training method and device of target detection model | |
TW201421990A (en) | Device, method and computer readable storage medium thereof for detecting object | |
CN114418861B (en) | Camera image splicing processing method and system | |
US8218823B2 (en) | Determining main objects using range information | |
CN111272388A (en) | Method and device for detecting camera flash lamp | |
CN112862671A (en) | Video image editing and repairing method, device and storage medium | |
CN110688926B (en) | Subject detection method and apparatus, electronic device, and computer-readable storage medium | |
CN110223320B (en) | Object detection tracking method and detection tracking device | |
CN112991175B (en) | Panoramic picture generation method and device based on single PTZ camera | |
CN111242116B (en) | Screen positioning method and device | |
CN110661969B (en) | Image acquisition method and device for display screen, electronic equipment and medium | |
CN116152691A (en) | Image detection method, device, equipment and storage medium | |
CN113421275A (en) | Image processing method, image processing device, computer equipment and storage medium |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: Room 1101-1103, No. 433, Songhu Road, Yangpu District, Shanghai Applicant after: Shanghai wanwansheng Environmental Protection Technology Group Co.,Ltd. Address before: Room 1101-1103, No. 433, Songhu Road, Yangpu District, Shanghai Applicant before: SHANGHAI YUEYI NETWORK INFORMATION TECHNOLOGY Co.,Ltd. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200605 |