CN117953017A - Moving target detection method, system, equipment and medium based on frame difference method - Google Patents
Moving target detection method, system, equipment and medium based on frame difference method Download PDFInfo
- Publication number
- CN117953017A CN117953017A CN202311413244.8A CN202311413244A CN117953017A CN 117953017 A CN117953017 A CN 117953017A CN 202311413244 A CN202311413244 A CN 202311413244A CN 117953017 A CN117953017 A CN 117953017A
- Authority
- CN
- China
- Prior art keywords
- target
- picture
- detected
- moving
- frame difference
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 103
- 238000000034 method Methods 0.000 title claims abstract description 101
- 238000012545 processing Methods 0.000 claims abstract description 45
- 238000001914 filtration Methods 0.000 claims description 35
- 238000012549 training Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 9
- 238000013519 translation Methods 0.000 claims description 4
- 230000010076 replication Effects 0.000 claims description 3
- 230000003068 static effect Effects 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005242 forging Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of target detection, and discloses a method, a system, equipment and a medium for detecting a moving target based on a frame difference method, wherein the method comprises the following steps: obtaining an adjacent picture of an adjacent frame with the target picture to be detected according to the target picture to be detected; obtaining a target suspicious region through a frame difference method according to a target picture to be detected and an adjacent picture; performing color enhancement processing on a target suspicious region of a target picture to be detected; and obtaining a moving target detection result through the moving target detection model according to the target picture to be detected after the color enhancement processing. The invention obtains the frame difference between the picture of the target to be detected and the adjacent picture by using the frame difference method, carries out the detection of the moving target by using the moving target detection model, trains the frame difference sample data of the moving target detection model to be artificial pseudo-difference, can effectively forge the static target into the dynamic target, improves the detection precision of the moving target detection model and rapidly and accurately outputs the detection result of the moving target.
Description
Technical Field
The present invention relates to the field of target detection technologies, and in particular, to a method, a system, an apparatus, and a medium for detecting a moving target based on a frame difference method.
Background
In recent years, different detection models are endless, especially a target detection algorithm based on deep learning, but the target detection model of one stage or two stages is strongly dependent on the size of a data set and the diversity of data. However, no matter how rich the data set is, the data of all scenes will not be contained, and when the environment is complex, the objects and other objects are difficult to distinguish, so that the false detection rate is high, and the problem is particularly serious on small objects.
Commercially available object detection models in the industry are typically implemented based on deep learning methods. For a moving target, the method basically adopts a data set of independent pictures for training, carries out complex pretreatment on the picture data set, comprises rotation, cutting, normalization, scaling and the like, and adopts training skills for training.
Therefore, a new method for detecting a moving object is needed to improve the accuracy of the object detection.
Disclosure of Invention
The invention provides a method, a system, equipment and a medium for detecting a moving target based on a frame difference method, which are used for solving the defect of low accuracy of detecting the moving target in the prior art.
The invention provides a moving target detection method based on a frame difference method, which comprises the following steps:
acquiring a target picture to be detected containing a moving target;
obtaining an adjacent picture of an adjacent frame with the target picture to be detected according to the target picture to be detected;
obtaining a target suspicious region through a frame difference method according to a target picture to be detected and an adjacent picture;
Performing color enhancement processing on a target suspicious region of a target picture to be detected;
According to the target picture to be detected after the color enhancement treatment, a moving target detection result is obtained through a moving target detection model;
the moving target detection model is obtained based on frame difference sample data and moving target label data through training.
According to the method for detecting the moving target based on the frame difference method, the picture of the moving target to be detected and the adjacent picture of the frame adjacent to the picture of the moving target to be detected are obtained from the dynamic video or continuous still pictures shot by the camera at the position where the moving target is required to be detected.
According to the moving target detection method based on the frame difference method provided by the invention, the step of obtaining the frame difference sample data comprises the following steps:
Obtaining a sample picture, wherein the sample picture is provided with a moving target;
carrying out coordinate translation on a moving target on a sample picture to obtain a sample picture copy;
And subtracting pixel values of the corresponding positions of the sample picture and the sample picture copy and taking an absolute value to obtain frame difference sample data.
According to the method for detecting the moving target based on the frame difference method, the method for obtaining the suspicious region of the target according to the picture of the target to be detected and the adjacent picture by the frame difference method comprises the following steps:
Subtracting pixel values of corresponding positions of the target picture to be detected and the adjacent picture and taking an absolute value to obtain a frame difference of the target picture to be detected and the adjacent picture;
obtaining coordinates of a suspected moving object according to frame differences between the to-be-detected object picture and the adjacent picture and a preset frame difference threshold value;
and taking an area surrounded by coordinates of the suspected moving object as an object suspicious area.
According to the method for detecting the moving target based on the frame difference method, the coordinates of the suspected moving target are obtained according to the frame difference between the target picture to be detected and the adjacent picture and the preset frame difference threshold, and the method comprises the following steps:
When the frame difference between the target picture to be detected and the adjacent picture is larger than or equal to a preset frame difference threshold value, setting a pixel value of a corresponding position of the target picture to be detected as a first value;
When the frame difference between the target picture to be detected and the adjacent picture is smaller than a preset frame difference threshold value, setting the pixel value of the corresponding position of the target picture to be detected as a second value;
Wherein the first value is greater than the second value.
According to the moving target detection method based on the frame difference method, the preset frame difference threshold is 50, the first value is 255, and the second value is 0.
According to the moving target detection method based on the frame difference method, the color enhancement processing comprises any one or any combination of the following steps: the contrast processing is increased, the color richness processing is increased, the defogging processing and the sharpening processing are performed.
According to the method for detecting the moving target based on the frame difference method, according to the target picture to be detected after the color enhancement treatment, a moving target detection result is obtained through a moving target detection model, and the method comprises the following steps:
according to the target picture to be detected after the color enhancement treatment, obtaining suspicious moving targets of a target suspicious region and/or suspicious moving targets of other regions in the target picture to be detected through a moving target detection model;
and filtering suspicious moving targets of the suspicious region of the target in the target picture to be detected and/or suspicious moving targets of other regions by using a preset filtering pixel value to obtain a final moving target.
According to the method for detecting the moving target based on the frame difference method, which is provided by the invention, the suspicious moving target of the target suspicious region and/or suspicious moving targets of other regions in the target picture to be detected are filtered by utilizing the preset filtering pixel value, so that a final moving target is obtained, and the method comprises the following steps:
filtering suspicious moving targets of the target suspicious region in the target picture to be detected by using a first preset filtering pixel value to obtain the moving targets of the target suspicious region in the target picture to be detected;
Filtering suspicious moving targets of other areas in the target picture to be detected by using a second preset filtering pixel value to obtain moving targets of other areas in the target picture to be detected;
Combining the target suspicious region and the moving targets of other regions in the target picture to be detected to obtain a final moving target and coordinates and categories thereof;
Wherein the first preset filter pixel value and the second preset filter pixel value are different.
The invention also provides a moving target detection system based on the frame difference method, which comprises the following steps:
an acquisition module for: acquiring a target picture to be detected containing a moving target;
a replication module for: obtaining an adjacent picture of an adjacent frame with the target picture to be detected according to the target picture to be detected;
a frame difference processing module, configured to: obtaining a target suspicious region through a frame difference method according to a target picture to be detected and an adjacent picture;
A color enhancement processing module for: performing color enhancement processing on a target suspicious region of a target picture to be detected;
The mobile object detection module is used for: according to the target picture to be detected after the color enhancement treatment, a moving target detection result is obtained through a moving target detection model;
the moving target detection model is obtained based on frame difference sample data and moving target label data through training.
The invention also provides an electronic device comprising a processor and a memory storing a computer program, wherein the processor is used for realizing any one of the moving target detection methods based on the frame difference method when executing the computer program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements any of the above-described moving object detection methods based on the frame difference method.
The present invention also provides a computer program product comprising a computer program storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of performing any one of the above described moving object detection methods based on a frame difference method.
According to the method, the system, the equipment and the medium for detecting the moving target based on the frame difference method, provided by the invention, the frame difference between the picture of the target to be detected and the adjacent picture is obtained by taking the moving characteristic of the target to be detected into consideration, and the moving target detection result can be obtained rapidly and accurately by detecting the moving target according to the picture of the target to be detected after the color enhancement treatment through the moving target detection model. Compared with the existing complex detection method based on a single original picture, the method, the system, the equipment and the medium for detecting the moving target based on the frame difference method can rapidly detect the small target and the target with the background highly similar, effectively reduce the false detection rate and improve the applicability and the practicability.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following brief description will be given of the drawings used in the embodiments or the description of the prior art, it being obvious that the drawings in the following description are some embodiments of the invention and that other drawings can be obtained from them without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for detecting a moving target based on a frame difference method according to the present invention.
Fig. 2 is a schematic diagram of subtracting pixel values of corresponding positions of a target picture A1 to be detected and an adjacent picture A2 and taking an absolute value to obtain a frame difference between the target picture to be detected and the adjacent picture.
Fig. 3 is a schematic structural diagram of a moving object detection system based on a frame difference method according to the present invention.
Fig. 4 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions thereof will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments, which should not be construed as limiting the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention. In the description of the present invention, it is to be understood that the terminology used is for the purpose of description only and is not to be interpreted as indicating or implying relative importance.
The following describes a moving target detection method, a system, a device and a medium based on a frame difference method with reference to fig. 1 to fig. 4.
Fig. 1 is a flow chart of a moving target detection method based on a frame difference method provided by the invention. Referring to fig. 1, the method for detecting a moving object based on a frame difference method according to the present invention may include:
step S110, obtaining a picture of a target to be detected containing a moving target;
step S120, obtaining an adjacent picture of an adjacent frame with the target picture to be detected according to the target picture to be detected;
step S130, obtaining a target suspicious region through a frame difference method according to a target picture to be detected and an adjacent picture;
Step S140, performing color enhancement processing on a target suspicious region of a target picture to be detected;
And step S150, obtaining a moving target detection result through a moving target detection model according to the target picture to be detected after the color enhancement processing.
It should be noted that, the moving target detection model is obtained based on the frame difference sample data and the moving target label data, and the frame difference sample data can be obtained through the following steps: firstly, obtaining a sample picture from a video or an image shot by a camera, marking a moving target on the sample picture, copying the sample picture, carrying out coordinate translation on the moving target on the copied sample picture to obtain a sample picture copy, subtracting pixel values of corresponding positions of the sample picture and the sample picture copy, taking an absolute value, and further obtaining frame difference sample data, wherein each frame difference sample data is provided with moving target tag data, the moving target tag data comprises coordinates and types of the moving target in the picture, and the types comprise people, animals, vehicles, equipment and the like. When the moving target detection model is trained, the frame difference sample data obtained by copying and translating is adopted to simulate the target motion, the pseudo difference is manufactured artificially, the static target can be pseudo to be a dynamic target, the moving target detection model can effectively learn based on the moving characteristics of the target, and the moving target can be identified more accurately.
It should be noted that, the execution body of the moving target detection method based on the frame difference method provided by the present invention may be any terminal side device meeting the technical requirements, for example, a moving target detection device based on the frame difference method, etc.
In one embodiment, step S110 may acquire a camera video or a shot picture at a position where a moving target needs to be detected through a real-time streaming Protocol (REAL TIME STREAMING Protocol), so as to obtain a target picture to be detected, which is denoted as A1.
In step S120, two consecutive frames of pictures in the camera video may be used as the target picture to be detected and the adjacent picture, and the adjacent picture is denoted as A2.
Since the pixel values of the static object or the background are approximately unchanged at different times, step S130 may subtract the pixel values of the corresponding positions of the to-be-detected object picture and the adjacent picture and take absolute values to obtain the frame difference between the to-be-detected object picture and the adjacent picture (refer to fig. 2), and obtain the coordinates of the suspected moving object according to the frame difference between the to-be-detected object picture and the adjacent picture and the preset frame difference threshold value, for example, when the frame difference between the to-be-detected object picture and the adjacent picture is greater than or equal to the preset frame difference threshold value (for example, 50), the pixel value of the corresponding position of the to-be-detected object picture is set to a first value (for example, 255), and when the frame difference between the to-be-detected object picture and the adjacent picture is less than the preset frame difference threshold value, the pixel value of the corresponding position of the to-be-detected object picture is set to a second value (for example, 0), the pixel point of 255 may be used as the pixel point of the suspected moving object, the coordinates of the suspected moving object may be obtained according to the pixel point of the suspected moving object, the coordinate of the suspected moving object may be amplified by N times (for example, 2 times the coordinate of the suspected moving object), and the region may appear as the suspicious region.
For the target suspicious region, step S140 may perform color enhancement processing, such as contrast enhancement processing, color richness enhancement processing, defogging processing, sharpening processing, etc., on the target suspicious region of the target picture to be detected, so as to improve the picture precision, especially the precision of the suspected moving target on the target picture to be detected, which is beneficial to improving the accuracy of the subsequent detection of the moving target.
Step S150 inputs the target image to be detected after the color enhancement processing into a moving target detection model, which can obtain suspicious moving targets of a target suspicious region and/or suspicious moving targets of other regions in the target image to be detected first, then filters suspicious moving targets of the target suspicious region and/or suspicious moving targets of other regions in the target image to be detected by using preset filtering pixel values, for example, sets a first preset filtering pixel value for the target suspicious region, filters suspicious moving targets of which the pixel value in the target suspicious region is smaller than the first preset filtering pixel value, sets a second preset filtering pixel value different from the first preset filtering pixel value for the moving targets of the target suspicious region in the target image to be detected, filters suspicious moving targets of which the pixel value in other regions is smaller than the second preset filtering pixel value, and the remaining suspicious moving targets are moving targets of other regions in the target image to be detected, and finally obtains the coordinates and the type of the target in the target suspicious region and the final target.
Different preset filtering pixel values are set for the suspicious target area and other areas, because the suspicious target area is subjected to color enhancement processing in step S140, the purpose of filtering the suspicious moving targets of the suspicious target area is to screen real moving targets from the suspicious moving targets in the suspicious target area, and the purpose of filtering the other areas is to screen the suspicious moving targets in the other areas from the background, so that the suspicious moving targets of the target suspicious area and the moving targets of the other areas in the target image to be detected are finally combined, and the final moving target is obtained.
The invention provides a moving target detection method, a system, equipment and a medium based on a frame difference method, which are used for copying a sample picture and translating target coordinates to obtain a sample picture copy, subtracting pixel values of the sample picture and the sample picture copy and taking absolute values to obtain frame difference sample data, artificially manufacturing a pseudo-difference between pictures, forging a static target into a dynamic target, and training a moving target detection model by using the frame difference sample data and corresponding moving target label data to enable the moving target detection model to be combined with the motion characteristics of the moving target to perform deep learning. When the moving target is detected, the frame difference between the picture of the target to be detected and the adjacent picture is obtained by utilizing a frame difference method, and then the moving target detection is carried out according to the picture of the target to be detected after the color enhancement treatment by utilizing a moving target detection model, so that the moving target detection result can be obtained rapidly and accurately. Compared with the existing complex detection method based on a single original picture, the method, the system, the equipment and the medium for detecting the moving target based on the frame difference method can rapidly detect the small target and the target with the background highly similar, effectively reduce the false detection rate and improve the applicability and the practicability.
The moving object detecting system based on the frame difference method provided by the invention is described below, and the moving object detecting system based on the frame difference method described below and the moving object detecting method based on the frame difference method described above can be correspondingly referred to each other.
Referring to fig. 3, a moving object detection system based on a frame difference method according to the present invention may include:
an acquisition module for: acquiring a target picture to be detected containing a moving target;
a replication module for: obtaining an adjacent picture of an adjacent frame with the target picture to be detected according to the target picture to be detected;
a frame difference processing module, configured to: obtaining a target suspicious region through a frame difference method according to a target picture to be detected and an adjacent picture;
A color enhancement processing module for: performing color enhancement processing on a target suspicious region of a target picture to be detected;
The mobile object detection module is used for: according to the target picture to be detected after the color enhancement treatment, a moving target detection result is obtained through a moving target detection model;
the moving target detection model is obtained based on frame difference sample data and moving target label data through training.
The color enhancement process includes any one or any combination of the following: the contrast processing is increased, the color richness processing is increased, the defogging processing and the sharpening processing are performed.
According to the moving target detection system based on the frame difference method provided by the invention, the moving target detection system can comprise a moving target detection model training module, and the moving target detection model training module can comprise:
a sample picture acquisition sub-module for: obtaining a sample picture, wherein the sample picture is provided with a moving target;
a sample picture copy acquisition sub-module for: carrying out coordinate translation on a moving target on a sample picture to obtain a sample picture copy;
a frame difference sample data acquisition sub-module for: subtracting pixel values of corresponding positions of the sample picture and the sample picture copy and taking an absolute value to obtain frame difference sample data;
a model training sub-module for: and training a moving target detection model according to the frame difference sample data and the moving target label data.
According to the moving target detection system based on the frame difference method provided by the invention, the frame difference processing module comprises:
A first processing sub-module for: subtracting pixel values of corresponding positions of the target picture to be detected and the adjacent picture and taking an absolute value to obtain a frame difference of the target picture to be detected and the adjacent picture;
a second processing sub-module for: obtaining coordinates of a suspected moving object according to frame differences between the to-be-detected object picture and the adjacent picture and a preset frame difference threshold value;
A third processing sub-module for: an area surrounded by coordinates of the suspected moving object is taken as an object suspicious area
According to the moving target detection system based on the frame difference method provided by the invention, the second processing sub-module is specifically used for: when the frame difference between the target picture to be detected and the adjacent picture is larger than or equal to a preset frame difference threshold value, setting a pixel value of a corresponding position of the target picture to be detected as a first value; when the frame difference between the target picture to be detected and the adjacent picture is smaller than a preset frame difference threshold value, setting the pixel value of the corresponding position of the target picture to be detected as a second value; wherein the first value is greater than the second value.
In one embodiment, the preset frame difference threshold is 50, the first value is 255, and the second value is 0.
According to the moving target detection system based on the frame difference method provided by the invention, the moving target detection module can comprise:
A detection sub-module for: according to the target picture to be detected after the color enhancement treatment, obtaining suspicious moving targets of a target suspicious region and/or suspicious moving targets of other regions in the target picture to be detected through a moving target detection model;
A filtering sub-module for: and filtering suspicious moving targets of the suspicious region of the target in the target picture to be detected and/or suspicious moving targets of other regions by using a preset filtering pixel value to obtain a final moving target.
According to the moving target detection system based on the frame difference method provided by the invention, the filtering sub-module can comprise:
A first filtering sub-module for: filtering suspicious moving targets of the target suspicious region in the target picture to be detected by using a first preset filtering pixel value to obtain the moving targets of the target suspicious region in the target picture to be detected;
A second filtering sub-module for: filtering suspicious moving targets of other areas in the target picture to be detected by using a second preset filtering pixel value to obtain moving targets of other areas in the target picture to be detected;
A third filtering sub-module for: combining the target suspicious region and the moving targets of other regions in the target picture to be detected to obtain a final moving target and coordinates and categories thereof;
Wherein the first preset filter pixel value and the second preset filter pixel value are different.
Fig. 4 illustrates a physical schematic diagram of an electronic device, as shown in fig. 4, which may include: processor 810, communication interface (Communications Interface) 820, memory 830, and communication bus 840, wherein processor 810, communication interface 820, memory 830 accomplish communication with each other through communication bus 840. The processor 810 may call logic instructions in the memory 830 to perform a moving object detection method based on a frame difference method, the method comprising:
acquiring a target picture to be detected containing a moving target;
obtaining an adjacent picture of an adjacent frame with the target picture to be detected according to the target picture to be detected;
obtaining a target suspicious region through a frame difference method according to a target picture to be detected and an adjacent picture;
Performing color enhancement processing on a target suspicious region of a target picture to be detected;
According to the target picture to be detected after the color enhancement treatment, a moving target detection result is obtained through a moving target detection model;
the moving target detection model is obtained based on frame difference sample data and moving target label data through training.
Further, the logic instructions in the memory 830 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, where the computer program product includes a computer program, where the computer program can be stored on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, the computer can execute the moving target detection method based on the frame difference method provided by the above methods, and the method includes:
acquiring a target picture to be detected containing a moving target;
obtaining an adjacent picture of an adjacent frame with the target picture to be detected according to the target picture to be detected;
obtaining a target suspicious region through a frame difference method according to a target picture to be detected and an adjacent picture;
Performing color enhancement processing on a target suspicious region of a target picture to be detected;
According to the target picture to be detected after the color enhancement treatment, a moving target detection result is obtained through a moving target detection model;
the moving target detection model is obtained based on frame difference sample data and moving target label data through training.
In still another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the frame difference method-based moving object detection method provided by the above methods, the method comprising:
acquiring a target picture to be detected containing a moving target;
obtaining an adjacent picture of an adjacent frame with the target picture to be detected according to the target picture to be detected;
obtaining a target suspicious region through a frame difference method according to a target picture to be detected and an adjacent picture;
Performing color enhancement processing on a target suspicious region of a target picture to be detected;
According to the target picture to be detected after the color enhancement treatment, a moving target detection result is obtained through a moving target detection model;
the moving target detection model is obtained based on frame difference sample data and moving target label data through training.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The method for detecting the moving target based on the frame difference method is characterized by comprising the following steps of:
acquiring a target picture to be detected containing a moving target;
obtaining an adjacent picture of an adjacent frame with the target picture to be detected according to the target picture to be detected;
obtaining a target suspicious region through a frame difference method according to a target picture to be detected and an adjacent picture;
Performing color enhancement processing on a target suspicious region of a target picture to be detected;
According to the target picture to be detected after the color enhancement treatment, a moving target detection result is obtained through a moving target detection model;
the moving target detection model is obtained based on frame difference sample data and moving target label data through training.
2. The method for detecting a moving object based on a frame difference method according to claim 1, wherein the step of obtaining frame difference sample data comprises:
Obtaining a sample picture, wherein the sample picture is provided with a moving target;
carrying out coordinate translation on a moving target on a sample picture to obtain a sample picture copy;
And subtracting pixel values of the corresponding positions of the sample picture and the sample picture copy and taking an absolute value to obtain frame difference sample data.
3. The method for detecting a moving target based on a frame difference method according to claim 2, wherein the obtaining the target suspicious region according to the target picture to be detected and the adjacent picture by the frame difference method comprises:
Subtracting pixel values of corresponding positions of the target picture to be detected and the adjacent picture and taking an absolute value to obtain a frame difference of the target picture to be detected and the adjacent picture;
obtaining coordinates of a suspected moving object according to frame differences between the to-be-detected object picture and the adjacent picture and a preset frame difference threshold value;
and taking an area surrounded by coordinates of the suspected moving object as an object suspicious area.
4. The method for detecting a moving object based on a frame difference method according to claim 3, wherein the obtaining coordinates of a suspected moving object according to a frame difference between a target picture to be detected and an adjacent picture and a preset frame difference threshold comprises:
When the frame difference between the target picture to be detected and the adjacent picture is larger than or equal to a preset frame difference threshold value, setting a pixel value of a corresponding position of the target picture to be detected as a first value;
When the frame difference between the target picture to be detected and the adjacent picture is smaller than a preset frame difference threshold value, setting the pixel value of the corresponding position of the target picture to be detected as a second value;
Wherein the first value is greater than the second value.
5. The frame difference method-based moving object detection method according to any one of claims 1 to 4, wherein the color enhancement processing includes any one or any combination of the following: the contrast processing is increased, the color richness processing is increased, the defogging processing and the sharpening processing are performed.
6. The method for detecting a moving target based on a frame difference method according to any one of claims 1 to 4, wherein the obtaining a moving target detection result according to the target picture to be detected after the color enhancement processing by a moving target detection model includes:
according to the target picture to be detected after the color enhancement treatment, obtaining suspicious moving targets of a target suspicious region and/or suspicious moving targets of other regions in the target picture to be detected through a moving target detection model;
and filtering suspicious moving targets of the suspicious region of the target in the target picture to be detected and/or suspicious moving targets of other regions by using a preset filtering pixel value to obtain a final moving target.
7. The method for detecting a moving object based on a frame difference method according to claim 6, wherein filtering suspicious moving objects of a suspicious region of an object in an object picture to be detected and/or suspicious moving objects of other regions by using a preset filtering pixel value to obtain a final moving object comprises:
filtering suspicious moving targets of the target suspicious region in the target picture to be detected by using a first preset filtering pixel value to obtain the moving targets of the target suspicious region in the target picture to be detected;
Filtering suspicious moving targets of other areas in the target picture to be detected by using a second preset filtering pixel value to obtain moving targets of other areas in the target picture to be detected;
Combining the target suspicious region and the moving targets of other regions in the target picture to be detected to obtain a final moving target and coordinates and categories thereof;
Wherein the first preset filter pixel value and the second preset filter pixel value are different.
8. A moving object detection system based on a frame difference method, comprising:
an acquisition module for: acquiring a target picture to be detected containing a moving target;
a replication module for: obtaining an adjacent picture of an adjacent frame with the target picture to be detected according to the target picture to be detected;
a frame difference processing module, configured to: obtaining a target suspicious region through a frame difference method according to a target picture to be detected and an adjacent picture;
A color enhancement processing module for: performing color enhancement processing on a target suspicious region of a target picture to be detected;
The mobile object detection module is used for: according to the target picture to be detected after the color enhancement treatment, a moving target detection result is obtained through a moving target detection model;
the moving target detection model is obtained based on frame difference sample data and moving target label data through training.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the frame difference method based moving object detection method according to any one of claims 1 to 7 when executing the program.
10. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the moving object detection method based on the frame difference method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311413244.8A CN117953017A (en) | 2023-10-27 | 2023-10-27 | Moving target detection method, system, equipment and medium based on frame difference method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311413244.8A CN117953017A (en) | 2023-10-27 | 2023-10-27 | Moving target detection method, system, equipment and medium based on frame difference method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117953017A true CN117953017A (en) | 2024-04-30 |
Family
ID=90795078
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311413244.8A Pending CN117953017A (en) | 2023-10-27 | 2023-10-27 | Moving target detection method, system, equipment and medium based on frame difference method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117953017A (en) |
-
2023
- 2023-10-27 CN CN202311413244.8A patent/CN117953017A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Single image rain streak decomposition using layer priors | |
| CN110599387A (en) | Method and device for automatically removing image watermark | |
| US11961237B2 (en) | Foreground data generation method and method for applying same, related apparatus, and system | |
| CN111695421B (en) | Image recognition method and device and electronic equipment | |
| CN111340716A (en) | Image deblurring method for improving dual-discrimination countermeasure network model | |
| CN113657528B (en) | Image feature point extraction method and device, computer terminal and storage medium | |
| CN109801231B (en) | Image processing method of electrophoresis electronic paper detection equipment | |
| CN111415304A (en) | Underwater vision enhancement method and device based on cascade deep network | |
| CN114926374B (en) | Image processing method, device and equipment based on AI and readable storage medium | |
| CN112766028B (en) | Face fuzzy processing method and device, electronic equipment and storage medium | |
| CN114187201A (en) | Model training method, image processing method, device, equipment and storage medium | |
| CN108122209B (en) | License plate deblurring method based on countermeasure generation network | |
| CN110188752B (en) | Deblurring recognition system and deblurring recognition method for blurred license plate under monitoring video | |
| CN104102911A (en) | Image processing for AOI (automated optical inspection)-based bullet appearance defect detection system | |
| CN117953017A (en) | Moving target detection method, system, equipment and medium based on frame difference method | |
| CN116152191A (en) | Display screen crack defect detection method, device and equipment based on deep learning | |
| CN113256541B (en) | Method for removing water mist from drilling platform monitoring picture by machine learning | |
| CN111935480B (en) | Detection method for image acquisition device and related device | |
| CN113379631B (en) | Image defogging method and device | |
| CN110751163A (en) | Target positioning method and device, computer readable storage medium and electronic equipment | |
| CN113554685A (en) | Method and device for detecting moving target of remote sensing satellite, electronic equipment and storage medium | |
| Beckmann et al. | Fooling State-of-the-Art Deepfake Detection with High-Quality Deepfakes | |
| CN112070954A (en) | Living body identification method, living body identification device, living body identification equipment and storage medium | |
| CN114511591B (en) | Track tracking method and device, electronic equipment and storage medium | |
| CN115908184B (en) | Automatic removal method and device for mole pattern |
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 |