CN111091097A - Method, device, equipment and storage medium for identifying remnants - Google Patents
Method, device, equipment and storage medium for identifying remnants Download PDFInfo
- Publication number
- CN111091097A CN111091097A CN201911328225.9A CN201911328225A CN111091097A CN 111091097 A CN111091097 A CN 111091097A CN 201911328225 A CN201911328225 A CN 201911328225A CN 111091097 A CN111091097 A CN 111091097A
- Authority
- CN
- China
- Prior art keywords
- suspected
- value
- remnant
- average
- determining
- 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
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000012545 processing Methods 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 12
- 235000021190 leftovers Nutrition 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 230000007613 environmental effect Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000013178 mathematical model Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010295 mobile communication Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a storage medium for identifying a legacy object. The method comprises the following steps: acquiring first image data and second image data; calculating a difference between the first image data and the second image data; determining a carry-over region according to the difference value; calculating a contour gradient value of the carry-over area; if the contour gradient value is smaller than a first preset threshold value, the remaining area is a first foreign matter; if the contour gradient value is larger than the first preset threshold value, the remaining area is a second type of foreign matter. According to the identification method, the identification device, the identification equipment and the storage medium of the abandoned object, whether the abandoned object is a real abandoned object or not is judged by calculating the contour gradient value of the area of the abandoned object.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for identifying a legacy object.
Background
With the development of mobile communication services, the coverage area of mobile communication is continuously enlarged, outdoor communication equipment is distributed dispersedly and widely, local machine rooms are large in number and positions, manual routing inspection consumes a large amount of manpower and cost overhead, and problems are difficult to find and process in time. The problem condition that equipment trouble and computer lab appear before the summary, when discovering to appear unidentified relic around the equipment and in the computer lab, produce the potential safety hazard easily.
The existing detection algorithms for the remains mainly comprise two types, wherein the first type is that training is carried out based on collection of a large number of environment pictures and the remaining pictures, and whether the remaining exists in a single picture of a scene to be detected is judged by using a model obtained by training; and the second method is to detect the real-time video of the scene to be detected by establishing a vestigial mathematical model.
The working environment to be detected is outdoor communication equipment and a machine room which have a large number of monitoring nodes and large monitoring environment change.
The first method has the problems that models need to be established again aiming at different monitoring nodes of the working environment, the number of training pictures is large, the models need to be retrained when the camera shooting angle changes, the workload in the early stage and the difficulty in later maintenance are high, and therefore the first method is not generally selected to detect the remnants.
The second method only considers the mathematical model of the remnant, so that the method is more suitable for monitoring outdoor environments with a large number of monitoring nodes and large environmental change.
However, the second method only considers whether the current picture changes relative to the background picture, so that the problems of poor environmental interference resistance and sensitivity to the ambient light exist, the local light intensity increase (highlight, facula and the like) or the local light intensity decrease (dark spot and the like) generated by sunlight or lamplight cannot be accurately distinguished, and the influence of the ambient light is large.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for identifying a remaining object, wherein a suspected remaining object area obtained by a difference background Gaussian accumulation method is judged again, whether the suspected remaining object area is a real remaining object or not is judged by detecting a brightness gradient mean value of the suspected remaining object area along the contour direction, and a false identification result caused by ambient light is reduced or eliminated.
In a first aspect, a method for identifying a carry-over is provided, the method comprising:
determining a first to-be-detected environment picture, wherein the first to-be-detected environment picture comprises suspected leftovers;
inputting an environment picture to be detected including suspected remnants into a light spot and dark spot identification model, and determining an average gradient value of the suspected remnants, wherein the average gradient value is an average value of gradient values of a first direction of a contour line of the suspected remnants;
and when the average gradient value is larger than a preset threshold value, determining that the suspected remnant is a remnant.
In some implementations of the first aspect, comprising:
and when the average gradient value is smaller than or equal to a preset threshold value, determining that the suspected remnant is a light spot or a dark spot.
In some implementations of the first aspect, determining the average gradient value for the suspected carryover comprises:
determining the gradient value of each line segment on the contour line of the suspected remnant in the first direction;
and determining the average value of the gradient values of each line segment in the first direction, and taking the average value of the gradient values of each line segment in the first direction as the average gradient value.
In some implementations of the first aspect, determining the first to-be-detected picture includes:
acquiring a second to-be-detected environment picture;
and classifying the second environment picture to be detected by using a preset remnant detection model, and determining the first environment picture to be detected comprising the suspected remnant.
In some implementations of the first aspect, before inputting the picture of the environment to be detected including the suspected remnant to the light spot and dark spot identification model and determining the average gradient value of the suspected remnant, the method further includes:
and training a light spot and dark spot identification model.
In some implementations of the first aspect,
the preset carryover detection model includes a model using a differential background gaussian integration method.
In a second aspect, there is provided a legacy identification device, the device comprising:
the processing module is used for determining a first to-be-detected environment picture, and the first to-be-detected environment picture comprises suspected remnants;
the processing module is further used for inputting the to-be-detected environment picture comprising the suspected leftovers into the light spot and dark spot identification model, and determining the average gradient value of the suspected leftovers, wherein the average gradient value is the average value of the gradient values of the suspected leftovers in the first direction;
and the processing module is further used for determining the suspected remnant to be a remnant when the average gradient value is larger than a preset threshold value.
In some implementations of the second aspect, the processing module is further configured to determine that the suspected remnant is a spot or a dark spot when the average gradient value is less than or equal to a preset threshold value.
In some implementations of the second aspect,
the processing module is further used for determining the gradient value of each line segment on the contour line of the suspected remnant in the first direction;
and the processing module is further used for determining an average value of the gradient values of each line segment in the first direction, and taking the average value of the gradient values of each line segment in the first direction as an average gradient value.
In some implementations of the second aspect,
the processing module is also used for acquiring a second to-be-detected environment picture;
and the processing module is further used for classifying the second environment picture to be detected by using a preset remnant detection model and determining the first environment picture to be detected comprising suspected remnants.
In some implementations of the second aspect, a training module is included,
and the training module is used for training the light spot and dark spot recognition model.
In some implementations of the second aspect,
the preset carryover detection model includes a model using a differential background gaussian integration method.
In a third aspect, there is provided a legacy identification device, the device comprising:
a processor and a memory storing computer program instructions;
the processor, when executing the computer instructions, implements the first aspect and a method of identifying a carryover in any possible implementation of the first aspect.
In a fourth aspect, a computer storage medium is provided, where computer instructions are stored on the computer storage medium, and the computer instructions, when executed by a processor, implement the first aspect and the method for identifying a legacy in any possible implementation manner of the first aspect.
The embodiment of the invention provides a method, a device, equipment and a storage medium for identifying a remaining object, wherein a suspected remaining object area obtained by a difference background Gaussian accumulation method is judged again, whether the suspected remaining object area is a real remaining object or not is judged by detecting a brightness gradient mean value of the suspected remaining object area along the contour direction, and a false identification result caused by ambient light is reduced or eliminated.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a diagram of a mathematical model of a gradient direction of a carry-over contour according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for identifying a carry-over according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an ambient light-induced model misidentification of a difference background Gaussian accumulation algorithm according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an apparatus for identifying a carry-over according to an embodiment of the present invention;
fig. 5 is a block diagram of an exemplary hardware architecture of a computing device provided by an embodiment of the present invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In the prior art, when the outdoor communication equipment and the machine room are subjected to the leave-behind object detection, a leave-behind object mathematical model (difference background Gaussian accumulation method) is used for detecting a real-time video of a scene to be detected. Because the outdoor environment changes with time, when sunlight exists or outside light exists, light spots or dark spots appear on outdoor communication equipment and a machine room due to the sunlight or the light. In addition, the difference background gaussian accumulation method only considers whether the current picture changes relative to the background picture, and the occurrence of the light spots or dark spots can be considered as the remnant, so that the light spots or dark spots are mistaken as the remnant in the prior art.
In order to solve the problems that in the prior art, the environmental interference resistance is poor, the environmental light is sensitive, and the problem that the local light intensity increase (highlight, light spots and the like) or the local light intensity decrease (dark spots and the like) generated by sunlight or lamplight cannot be accurately distinguished is solved, the technical scheme of the application judges the suspected residual object area obtained by the difference background Gaussian accumulation method again, judges whether the suspected residual object area is a real residual object or not by detecting the brightness gradient mean value of the suspected residual object area along the contour direction, and reduces or eliminates the false recognition result caused by the environmental light.
The embodiment of the invention provides a method, a device, equipment and a storage medium for identifying a legacy object, and is described with reference to the accompanying drawings.
FIG. 1 is a mathematical model of the gradient direction of a carry-over contour according to an embodiment of the present invention, eiMay be the vertical direction of a part of the contour line and x is an angle plus or minus the vertical direction of a part of the contour line.
The method for identifying the legacy object according to the embodiment of the present invention is described below with reference to fig. 1 and 2.
As shown in fig. 2, fig. 2 is a schematic flow chart illustrating a method for identifying a legacy object according to an embodiment of the present invention. The identification method of the legacy may include:
s201: and determining a first to-be-detected environment picture.
The first to-be-detected environment picture comprises suspected remnants.
Specifically, when a monitored area is monitored, a difference background Gaussian accumulation method is used to compare a currently acquired picture with a historical background picture and perform Gaussian accumulation, so as to determine a suspected remnant in a monitored scene.
S202: and inputting the to-be-detected environment picture comprising the suspected remnants into a light spot and dark spot identification model, and determining the average gradient value of the suspected remnants.
The average gradient value is the average value of the gradient values of the suspected remnant contour line in the first direction.
Specifically, the light spot and dark spot identification model calculates an average gradient value of the first direction of the contour line of the suspected remnant in the to-be-detected environment picture. Optionally, in one example, the first direction may be an average gradient value in a vertical direction of a contour line of the suspected remnant. As shown in fig. 1, the average gradient value is an average value of gradient values in a perpendicular direction to a tangent line of the edge line of the suspected remnant. Alternatively, the first direction may be a vertical direction of a part of the contour line, or may be a direction of plus or minus x degrees from the vertical direction of the part of the contour line.
Alternatively, describing the vertical direction of a certain portion of the contour line, the sum of the gradients of the contour lines of the suspected remains can be calculated by formula (1).
Wherein l is the contour line of the suspected remnant.
The gradient is the sum of the gradients of the contour line along the perpendicular direction of the contour line.
eiIs the vertical direction of a certain part of the contour line.
The average gradient value of suspected carryover can be determined by equation (2).
arg congradient＝congradient/lleng(2)
Wherein llengthIs the length of the contour of the suspected vestige.
The arg gradient is the average gradient value per unit length along the vertical direction of the contour line.
The gradient is the sum of the gradients of the contour line along the perpendicular direction of the contour line.
S203: and when the average gradient value is larger than a preset threshold value, determining that the suspected remnant is a remnant.
Specifically, the preset threshold may be a training result of the light spot and dark spot identification model, or may be a preset numerical value, and when the average gradient value is less than or equal to the preset threshold, it may be determined that the suspected remnant is the light spot or the dark spot.
Specifically, when a suspected remaining area is obtained by using a previous differential background gaussian accumulation algorithm model, because of the influence of ambient light (sunlight, street lamps, etc.), the differential background gaussian accumulation algorithm model cannot accurately distinguish light spots, dark spots and remaining objects, and the light spots or dark spots caused by the ambient light are considered as the suspected remaining objects. According to the method for identifying the remnant, the light spot and dark spot identification model can calculate the average gradient value in the vertical direction of the contour line of the suspected remnant area, when the average gradient value is larger than the preset threshold value, the suspected remnant area is determined to be the remnant, and when the average gradient value is smaller than or equal to the preset threshold value, the suspected remnant area is determined to be the light spot or the dark spot. So as to determine the real remnant among the light spots, dark spots and remnants, and reduce or eliminate the false recognition result caused by the ambient light.
In addition, when the light spot and dark spot identification model calculates the average gradient value of the contour line of the suspected residue area, the average gradient value in the direction of adding or subtracting x degrees in the vertical direction of the contour line can be calculated, and x can be adjusted according to the actual situation.
As shown in fig. 3, fig. 3 is a schematic diagram illustrating a differential background gaussian accumulation algorithm model misrecognition caused by ambient light according to an embodiment of the present invention.
As can be seen from fig. 3, on the contour line of the vestige (real vestige) region, the contour line tends to be clearly visible, and there is a sudden change in the gradient. But the outline of the spot or dark spot area is not clear and there is a slow change in the gradient. The light spot and dark spot identification model judges the average gradient value of the unit length of the contour line along the first direction (including the vertical direction and the vertical +/-x-degree direction) of the contour line according to the characteristic. When the average gradient value is larger than a preset threshold value, determining that the suspected remaining area is a remaining object; and when the average gradient value is smaller than or equal to a preset threshold value, determining that the suspected remaining area is a light spot or a dark spot and no remaining exists. The light spots and the dark spots are distinguished from the light spots, the dark spots and the remnants, the real remnants are determined, and false identification results caused by ambient light are reduced or eliminated.
Specifically, the determination process may use formula (3) and formula (4) to perform the determination.
arg congradient≤Threshod (3)
arg congradient>Threshod (4)
The arg gradient may be an average gradient value of a unit length along a vertical direction of the contour line.
Threshod is a preset threshold.
Threshod can be obtained according to empirical values and can also be obtained through an optimization process of a light spot and dark spot identification model.
And when the average gradient value is smaller than or equal to a preset threshold value, determining that the suspected remaining area is a spot or a dark spot.
For example, since outdoor carry-over monitoring environments are complex, the carry-over and the environmental background are easily interfered by the intensity of the environmental light to generate false identification when being separated. When the street lamp is turned on at night in an outdoor environment, the street lamp light with large sudden change of the light intensity in the ambient light is easily identified as a left object, and an error alarm is generated. And a tree shadow generated when sunlight is intensified, in which case a light spot or a dark spot in the tree shadow is easily erroneously recognized as a carry-over. In the time period that the illumination changes obviously at night and in the daytime, more false alarms are given for the detection of the abandoned object, and the identification rate of the abandoned object is lower.
In the environment where street lamps and other environments possibly generating light spots and dark spots exist in the field of view monitored by the remains, by using the method for identifying the remains in the embodiment, the mean value of the brightness gradient of the suspected remaining area along the contour direction can be detected to judge whether the remaining area is a real remaining object, and the false identification result caused by ambient light is reduced or eliminated.
Corresponding to the embodiment of the identification method of the remnant, the embodiment of the invention also provides an identification device of the remnant.
As shown in fig. 4, fig. 4 is a schematic structural diagram illustrating an apparatus for identifying a carry-over according to an embodiment of the present invention.
The identification means of the legacy may include a processing module 401, a training module 402, wherein,
the processing module 401 is configured to determine a first to-be-detected environment picture, where the first to-be-detected environment picture includes a suspected legacy.
The processing module 401 is further configured to input the to-be-detected environment picture including the suspected remnant to the light spot and dark spot identification model, and determine an average gradient value of the suspected remnant, where the average gradient value is an average value of gradient values in the first direction of the contour line of the suspected remnant.
The processing module 401 is further configured to determine that the suspected remnant is a remnant when the average gradient value is greater than a preset threshold.
The processing module 401 is further configured to determine that the suspected residue is a light spot or a dark spot when the average gradient value is smaller than or equal to a preset threshold.
The processing module 401 is further configured to determine a gradient value of each line segment on the contour line of the suspected remnant in the first direction.
The processing module 401 is further configured to determine an average value of the gradient values of each line segment in the first direction, and use the average value of the gradient values of each line segment in the first direction as an average gradient value.
The processing module 401 is further configured to obtain a second to-be-detected environment picture;
the processing module 401 is further configured to classify the second to-be-detected environment picture by using a preset remnant detection model, and determine a first to-be-detected environment picture including suspected remnants.
And a training module 402 for training the light spot and dark spot identification model.
The preset carryover detection model includes a model using a differential background gaussian integration method.
The device for identifying the remnant provided by the embodiment of the invention can judge whether the remnant is a real remnant or not by detecting the brightness gradient mean value of the suspected remnant area along the contour direction, and reduce or eliminate the false identification result caused by the ambient light.
Fig. 5 is a block diagram illustrating an exemplary hardware architecture of a computing device capable of implementing the identification method of the legacy of the present embodiment. As shown in fig. 5, computing device 500 includes an input device 501, an input interface 502, a central processor 503, a memory 504, an output interface 505, and an output device 506. The input interface 502, the central processing unit 503, the memory 504, and the output interface 505 are connected to each other through a bus 510, and the input device 501 and the output device 506 are connected to the bus 510 through the input interface 502 and the output interface 505, respectively, and further connected to other components of the computing device 500.
Specifically, the input device 501 receives input information from the outside and transmits the input information to the central processor 503 through the input interface 502; the central processor 503 processes input information based on computer-executable instructions stored in the memory 504 to generate output information, temporarily or permanently stores the output information in the memory 504, and then transmits the output information to the output device 506 through the output interface 505; output device 506 outputs the output information outside of computing device 500 for use by a user.
That is, the computing device shown in fig. 5 may also be implemented as a legacy identification device, which may include: a processor and a memory storing computer program instructions; the processor can realize the identification method of the legacy provided by the embodiment of the invention when executing the computer instructions.
Embodiments of the present invention also provide a computer medium having computer instructions stored thereon.
The computer program instructions, when executed by a processor, may implement the method of identifying a carryover provided by embodiments of the present invention.
According to the identification method, the identification device, the identification equipment and the storage medium for the carry-over object provided by the embodiment of the invention, whether the carry-over object is a real carry-over object or not can be judged by detecting the brightness gradient mean value of the suspected carry-over object area along the contour direction, and the error identification result caused by the ambient light is reduced or eliminated.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The functional blocks shown in the above structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
As will be apparent to those skilled in the art, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.
Claims (13)
1. A method of identifying a carryover, the method comprising:
determining a first to-be-detected environment picture, wherein the first to-be-detected environment picture comprises suspected leftovers;
inputting the to-be-detected environment picture comprising the suspected residues into a light spot and dark spot identification model, and determining an average gradient value of the suspected residues, wherein the average gradient value is an average value of gradient values of a first direction of a contour line of the suspected residues;
and when the average gradient value is larger than a preset threshold value, determining that the suspected remnant is a remnant.
2. The method of claim 1, further comprising:
and when the average gradient value is smaller than or equal to the preset threshold value, determining that the suspected remnant is a light spot or a dark spot.
3. The method of claim 1 or 2, wherein determining the average gradient value of the suspected carryover comprises:
determining a gradient value of each line segment on the contour line of the suspected remnant in a first direction;
and determining the average value of the gradient values of each line segment in the first direction, and taking the average value of the gradient values of each line segment in the first direction as the average gradient value.
4. The method according to claim 1, wherein the determining the first to-be-detected picture comprises:
acquiring a second to-be-detected environment picture;
and classifying the second environment picture to be detected by using a preset remnant detection model, and determining the first environment picture to be detected including suspected remnants.
5. The method according to claim 1, wherein before inputting the picture of the environment to be detected including the suspected remains into the spot and dark spot identification model and determining the average gradient value of the suspected remains, the method further comprises:
and training the light spot and dark spot identification model.
6. The method of claim 4,
the preset carryover detection model includes a model using a differential background gaussian integration method.
7. An apparatus for identifying a carry-over, the apparatus comprising:
the processing module is used for determining a first to-be-detected environment picture, and the first to-be-detected environment picture comprises suspected remnants;
the processing module is further configured to input the to-be-detected environment picture including the suspected relict into a light spot and dark spot identification model, and determine an average gradient value of the suspected relict, where the average gradient value is an average value of gradient values of a first direction of a contour line of the suspected relict;
the processing module is further configured to determine that the suspected remnant is a remnant when the average gradient value is greater than a preset threshold value.
8. The apparatus of claim 7, wherein:
the processing module is further configured to determine that the suspected remnant is a light spot or a dark spot when the average gradient value is less than or equal to the preset threshold value.
9. The apparatus of claim 7 or 8, wherein:
the processing module is further configured to determine a gradient value of each line segment on the contour line of the suspected remnant in a first direction;
the processing module is further configured to determine an average value of the gradient values of each line segment in the first direction, and use the average value of the gradient values of each line segment in the first direction as the average gradient value.
10. The apparatus of claim 7, wherein:
the processing module is further used for acquiring a second to-be-detected environment picture;
the processing module is further configured to classify the second to-be-detected environment picture by using a preset remnant detection model, and determine the first to-be-detected environment picture including suspected remnants.
11. The apparatus of claim 7, further comprising a training module to:
and the training module is used for training the light spot and dark spot identification model.
12. An identification device for a carry-over, the device comprising: a processor and a memory storing computer program instructions;
the processor, when executing the computer instructions, implements the method of identifying a carryover according to any one of claims 1-6.
13. A computer storage medium having stored thereon computer instructions which, when executed by a processor, implement the method of identifying a carryover of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911328225.9A CN111091097A (en) | 2019-12-20 | 2019-12-20 | Method, device, equipment and storage medium for identifying remnants |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911328225.9A CN111091097A (en) | 2019-12-20 | 2019-12-20 | Method, device, equipment and storage medium for identifying remnants |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111091097A true CN111091097A (en) | 2020-05-01 |
Family
ID=70396009
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911328225.9A Pending CN111091097A (en) | 2019-12-20 | 2019-12-20 | Method, device, equipment and storage medium for identifying remnants |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111091097A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5157740A (en) * | 1991-02-07 | 1992-10-20 | Unisys Corporation | Method for background suppression in an image data processing system |
| CN102902960A (en) * | 2012-09-25 | 2013-01-30 | 武汉烽火众智数字技术有限责任公司 | Leave-behind object detection method based on Gaussian modelling and target contour |
| CN105488542A (en) * | 2015-12-24 | 2016-04-13 | 福建星网锐捷安防科技有限公司 | Method and device for foreground object detection |
| CN109409315A (en) * | 2018-11-07 | 2019-03-01 | 浩云科技股份有限公司 | A kind of ATM machine panel zone remnant object detection method and system |
| CN110544211A (en) * | 2019-07-26 | 2019-12-06 | 纵目科技（上海）股份有限公司 | method, system, terminal and storage medium for detecting lens attachment |
-
2019
- 2019-12-20 CN CN201911328225.9A patent/CN111091097A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5157740A (en) * | 1991-02-07 | 1992-10-20 | Unisys Corporation | Method for background suppression in an image data processing system |
| CN102902960A (en) * | 2012-09-25 | 2013-01-30 | 武汉烽火众智数字技术有限责任公司 | Leave-behind object detection method based on Gaussian modelling and target contour |
| CN105488542A (en) * | 2015-12-24 | 2016-04-13 | 福建星网锐捷安防科技有限公司 | Method and device for foreground object detection |
| CN109409315A (en) * | 2018-11-07 | 2019-03-01 | 浩云科技股份有限公司 | A kind of ATM machine panel zone remnant object detection method and system |
| CN110544211A (en) * | 2019-07-26 | 2019-12-06 | 纵目科技（上海）股份有限公司 | method, system, terminal and storage medium for detecting lens attachment |
Non-Patent Citations (1)
| Title |
|---|
| 张生军: "《基于视觉的无标记手势识别》", 吉林大学出版社, pages: 51 - 52 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101237089B1 (en) | Forest smoke detection method using random forest classifier method | |
| US9524558B2 (en) | Method, system and software module for foreground extraction | |
| US8498449B2 (en) | Eye detecting device, eye detecting method, and program | |
| EP2357615B1 (en) | Video processing | |
| CN107146217B (en) | Image detection method and device | |
| CN110232359B (en) | Retentate detection method, device, equipment and computer storage medium | |
| CN107220962B (en) | Image detection method and device for tunnel cracks | |
| KR101935010B1 (en) | Apparatus and method for recognizing license plate of car based on image | |
| CN108871290B (en) | visible light dynamic positioning method based on optical flow detection and Bayesian prediction | |
| CN110866515A (en) | Method and device for identifying object behaviors in plant and electronic equipment | |
| CN109724993A (en) | Detection method, device and the storage medium of the degree of image recognition apparatus | |
| CN113240880A (en) | Fire detection method and device, electronic equipment and storage medium | |
| CN111460917B (en) | Airport abnormal behavior detection system and method based on multi-mode information fusion | |
| CN112949785B (en) | Object detection method, device, equipment and computer storage medium | |
| JPH09282452A (en) | Monitor | |
| JP3294468B2 (en) | Object detection method in video monitoring device | |
| JP2002304677A (en) | Method and device for detecting intruder | |
| CN113052019A (en) | Target tracking method and device, intelligent equipment and computer storage medium | |
| CN111091097A (en) | Method, device, equipment and storage medium for identifying remnants | |
| CN111480180B (en) | Method and device for detecting and tracking target and photoelectric equipment | |
| US20220148193A1 (en) | Adaptive object recognition apparatus and method in fixed closed circuit television edge terminal using network | |
| CN115661475A (en) | Image foreign matter identification method, device, equipment and storage medium | |
| KR20160078154A (en) | Customer information provision method, device and computer program | |
| JPH0337356B2 (en) | ||
| KR100744158B1 (en) | Probabilistic visual surveillance system and method |
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 |