CN111325773A - Method, device and equipment for detecting moving target and readable storage medium - Google Patents
Method, device and equipment for detecting moving target and readable storage medium Download PDFInfo
- Publication number
- CN111325773A CN111325773A CN201811539983.0A CN201811539983A CN111325773A CN 111325773 A CN111325773 A CN 111325773A CN 201811539983 A CN201811539983 A CN 201811539983A CN 111325773 A CN111325773 A CN 111325773A
- Authority
- CN
- China
- Prior art keywords
- image
- binary image
- moving target
- current frame
- frame
- 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 66
- 239000000203 mixture Substances 0.000 claims abstract description 83
- 238000001514 detection method Methods 0.000 claims abstract description 51
- 230000000877 morphologic effect Effects 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 14
- 238000005286 illumination Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 230000035772 mutation Effects 0.000 description 6
- 238000009826 distribution Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011410 subtraction method Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Abstract
The invention provides a method, a device and equipment for detecting a moving target and a readable storage medium, wherein the method comprises the steps of obtaining a video sequence frame image; adopting a Gaussian mixture model to detect a moving target of the current frame image so as to obtain a first moving target binary image and a current frame background image; detecting a moving target by adopting an improved five-frame difference algorithm according to a current frame background image and a five-frame image corresponding to the current frame image to obtain a second moving target binary image; carrying out OR operation on the first moving target binary image and the second moving target binary image to obtain a total moving target binary image; and carrying out morphological processing on the total moving target binary image to obtain a moving target. The accuracy of the moving target detection of the improved five-frame difference algorithm is improved, the problem of smear is basically eliminated, and the moving targets detected by the two algorithms are subjected to OR operation to obtain all the moving targets detected by the two algorithms, so that the detected moving targets have complete outlines.
Description
Technical Field
The embodiment of the invention relates to the technical field of visual image processing, in particular to a method, a device and equipment for detecting a moving target and a readable storage medium.
Background
With the progress of science and technology, computer-based visual image processing technology has also been rapidly developed. Moving object detection is used as a core content of visual image processing, and is widely applied to multiple fields such as intelligent monitoring, medicine, military and the like.
The existing algorithms for detecting the moving target are various in types. Roughly classified into an optical flow method, a frame difference method, and a background subtraction method. The optical flow method is less used due to the complexity of the algorithm, higher requirement on hardware and the like. The mainstream algorithms for detecting moving objects are frame difference method and background subtraction method.
Although the existing frame difference method represented by a five-frame difference algorithm is improved to a certain extent compared with other inter-frame difference algorithms, the problems of smear, incomplete outline and the like still exist.
Disclosure of Invention
The embodiment of the invention provides a method, a device and equipment for detecting a moving target and a readable storage medium, which solve the problems that in the detection method of the moving target in the prior art, a hole exists, the outline is incomplete, the moving target is easy to be influenced by environmental noise and images of a lighting picture, and ghost images are easy to appear.
In a first aspect, an embodiment of the present invention provides a method for detecting a moving object, including: acquiring a video sequence frame image; adopting a Gaussian mixture model to detect a moving target of the current frame image so as to obtain a first moving target binary image and a current frame background image; detecting a moving target by adopting an improved five-frame difference algorithm according to the current frame background image and the five frame image corresponding to the current frame image to obtain a second moving target binary image; carrying out OR operation on the first moving target binary image and the second moving target binary image to obtain a total moving target binary image; and carrying out morphological processing on the total moving target binary image to obtain a moving target.
In a second aspect, an embodiment of the present invention provides a device for detecting a moving object, including: the image acquisition unit is used for acquiring a video sequence frame image; the Gaussian mixture model detection unit is used for detecting a moving target of the current frame image by adopting a Gaussian mixture model so as to obtain a first moving target binary image and a current frame background image; the improved five-frame difference algorithm detection unit is used for detecting a moving object by adopting an improved five-frame difference algorithm according to the current frame background image and the five frame image corresponding to the current frame image so as to obtain a second moving object binary image; an or operation unit, configured to perform or operation on the first moving target binary image and the second moving target binary image to obtain a total moving target binary image; and the morphology processing unit is used for carrying out morphology processing on the total moving target binary image so as to obtain a moving target.
In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any of the first aspects.
In a fourth aspect, an embodiment of the present invention provides a readable storage medium, including: stored thereon, a computer program to be executed by a processor to implement the method according to any of the first aspect.
The embodiment of the invention provides a method, a device and equipment for detecting a moving target and a readable storage medium, wherein the method comprises the steps of obtaining a video sequence frame image; adopting a Gaussian mixture model to detect a moving target of the current frame image so as to obtain a first moving target binary image and a current frame background image; detecting a moving target by adopting an improved five-frame difference algorithm according to a current frame background image and a five-frame image corresponding to the current frame image to obtain a second moving target binary image; carrying out OR operation on the first moving target binary image and the second moving target binary image to obtain a total moving target binary image; and carrying out morphological processing on the total moving target binary image to obtain a moving target. The method comprises the steps of using a background image of a current frame of a Gaussian mixture model as a background frame of an improved five-frame difference algorithm to identify a moving target, improving the accuracy of detecting the moving target of the improved five-frame difference algorithm, basically eliminating the problem of smear, carrying out OR operation on the moving target detected by the Gaussian mixture model and the moving target detected by the improved five-frame difference algorithm to obtain all the moving targets detected by the two algorithms, and enabling the detected moving targets to be richer and have more complete outlines.
It should be understood that what is described in the summary above is not intended to limit key or critical features of embodiments of the invention, nor is it intended to limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of a method for detecting a moving object according to an embodiment of the present invention;
fig. 2 is a flowchart of a moving object detection method according to a second embodiment of the present invention;
fig. 3 is a flowchart of step 202 of a method for detecting a moving object according to a second embodiment of the present invention;
fig. 4 is a flowchart of step 202d of a method for detecting a moving object according to a second embodiment of the present invention;
fig. 5 is a first flowchart of a moving object detection method step 203 according to a second embodiment of the present invention;
fig. 6 is a second flowchart of the step 203 of the method for detecting a moving object according to the second embodiment of the present invention;
fig. 7 is a flowchart of step 203b of the method for detecting a moving object according to the second embodiment of the present invention;
fig. 8 is a schematic structural diagram of a moving object detection apparatus according to a third embodiment of the present invention;
fig. 9 is a schematic structural diagram of a moving object detection apparatus according to a fourth embodiment of the present invention;
fig. 10 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and the embodiments of the present invention are illustrative only and are not intended to limit the scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, and in the above-described drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For clear understanding of the technical solutions of the present application, the following explains algorithms and terms involved in the present application:
gaussian mixture model: the gaussian mixture model is a model formed based on a gaussian probability density function (normal distribution curve) by accurately quantizing objects with the gaussian probability density function, i.e., the normal distribution curve, and decomposing one object into a plurality of objects. The principle and the process of establishing a Gaussian mixture model for an image background are as follows: the image gray level histogram reflects the frequency of occurrence of a certain gray level in an image, and may also be an estimate of the probability density of the image gray level. If the difference between the target area and the background area contained in the image is large and the background area and the target area have a certain difference in gray level, the gray level histogram of the image is in a double-peak-valley shape, wherein one peak corresponds to the target and the other peak corresponds to the central gray level of the background. For complex images, especially medical images, it is generally multimodal. The segmentation problem of the image can be solved by considering the multimodal nature of the histogram as a superposition of multiple gaussian distributions. In an intelligent monitoring system, the detection of a moving target is central content, and in the detection and extraction of the moving target, a background target is important for the identification and tracking of the target. Modeling is an important link of background target extraction.
And (3) an interframe difference algorithm: the interframe difference algorithm is a method for obtaining the contour of a moving object by performing difference operation on two adjacent frames in a video image sequence, and can be well suitable for the condition that a plurality of moving objects exist and a camera moves. When abnormal object motion occurs in a monitored scene, a frame is obviously different from a frame, the two frames are subtracted to obtain an absolute value of the brightness difference of the two frames, whether the absolute value is greater than a threshold value or not is judged to analyze the motion characteristic of a video or an image sequence, and whether object motion exists in the image sequence or not is determined.
Ghost image: and monitoring moving target pixel points which are left in the video and can not be eliminated for a long time.
Smearing: background pixel points around the moving target are detected as moving target pixel points, so that the moving target is fat.
An application scenario of the moving object detection method provided in the embodiment of the present application is described below. The moving target detection method provided by the embodiment of the application can be applied to intelligent video monitoring so as to detect and track the moving target. The method can also be applied to the medical field, such as the detection of the heart, the motion analysis field, the unmanned vehicle field and the unmanned aerial vehicle field. In this embodiment, an application scenario of the method for detecting a moving object is not limited.
Embodiments of the present application will be described below in detail with reference to the accompanying drawings.
Example one
Fig. 1 is a flowchart of a moving object detection method according to an embodiment of the present invention, and as shown in fig. 1, an execution main body of the moving object detection method according to the embodiment is a moving object detection device, the moving object detection device may be integrated on an electronic device, and the electronic device may be a computer, a mobile terminal, a server, or other devices with independent computing and processing capabilities, and then the moving object detection method according to the embodiment includes the following steps.
Step 101, acquiring a video sequence frame image.
Specifically, in this embodiment, the video capture device may capture a video sequence frame image, and acquire the video sequence frame image from the video capture device. Or after the video sequence frame image is acquired by the video acquisition device, the video sequence frame image is stored in the preset area, and the video sequence frame image is acquired from the preset area, which is not limited in this embodiment.
The video sequence frame images comprise a plurality of frame images. The multi-frame image at least comprises five frames of images, and the detection of the moving object is carried out on the current frame of image by adopting an improved five-frame difference algorithm in the following process.
And 102, detecting a moving target of the current frame image by adopting a Gaussian mixture model to obtain a first moving target binary image and a current frame background image.
The Gaussian mixture model is one of background subtraction methods, is a Gaussian model established for an image background, and uses K Gaussian models to represent the characteristics of a certain pixel point in a video sequence image. The establishment of the gaussian mixture model requires the initialization of parameters of the gaussian mixture model, and the parameters of the gaussian mixture model, the distribution weight values and the arrangement sequence are updated in time in order to ensure the robustness of the change of the background environment.
In this embodiment, a current frame image is input into a gaussian mixture model, the gaussian mixture model determines the type of each pixel point of the current frame image, if the current frame image conforms to the gaussian mixture model, the current frame image is determined as a background pixel point, if the current frame image does not conform to the gaussian mixture model, the current frame image is determined as a moving target pixel point, and a first moving target binary image and the current frame background image are determined according to the type of each pixel point.
The first moving target binary image is a moving target binary image obtained by detecting a moving target of a current frame image by adopting a Gaussian mixture model.
And 103, detecting a moving object by adopting an improved five-frame difference algorithm according to the background image of the current frame and the five-frame image corresponding to the current frame image to obtain a second moving object binary image.
The existing five-frame difference algorithm adopts continuous five-frame images, difference operation is carried out on a current frame image and two previous frame images and two next frame images respectively, binarization processing is carried out on the difference operation result to obtain a corresponding difference binary image, and two difference binary images in the four difference binary images are respectively subjected to AND operation and the AND operation result is subjected to OR operation, and finally morphological processing is carried out to obtain a moving target.
In the improved five-frame difference algorithm provided by this embodiment, the current frame background image output by the gaussian mixture model is introduced, the current frame background image and the current frame image are subjected to difference operation to obtain a difference result, the difference result and the difference result obtained by the five-frame difference algorithm in the prior art are subjected to logic operation, and the moving object detected by the improved five-frame difference algorithm is obtained after morphological processing.
The second moving target binary image is a moving target binary image obtained by detecting a moving target of the current frame image through an improved frame-free difference algorithm.
And 104, performing OR operation on the first moving target binary image and the second moving target binary image to obtain a total moving target binary image.
In this embodiment, an or operation is performed on the binary image of the moving target detected by using the gaussian model and the binary image of the moving target detected by using the improved five-frame difference algorithm, so as to obtain all moving targets in the first moving target binary image and the second moving target binary image.
And 105, performing morphological processing on the total moving target binary image to obtain a moving target.
Specifically, in this embodiment, the morphological processing is composed of morphological algebra operators, and there are 4 basic operations, which are: dilation, erosion, open and close operations.
In this embodiment, a basic operator is used to perform morphological processing on the total moving target binary image to obtain a final moving target, and a result of detecting the moving target is obtained.
In the method for detecting a moving object provided by this embodiment, a video sequence frame image is obtained; adopting a Gaussian mixture model to detect a moving target of the current frame image so as to obtain a first moving target binary image and a current frame background image; detecting a moving target by adopting an improved five-frame difference algorithm according to a current frame background image and a five-frame image corresponding to the current frame image to obtain a second moving target binary image; carrying out OR operation on the first moving target binary image and the second moving target binary image to obtain a total moving target binary image; and carrying out morphological processing on the total moving target binary image to obtain a moving target. The method comprises the steps of using a background image of a current frame of a Gaussian mixture model as a background frame of an improved five-frame difference algorithm to identify a moving target, improving the accuracy of detecting the moving target of the improved five-frame difference algorithm, basically eliminating the problem of smear, carrying out OR operation on the moving target detected by the Gaussian mixture model and the moving target detected by the improved five-frame difference algorithm to obtain all the moving targets detected by the two algorithms, and enabling the detected moving targets to be richer and have more complete outlines.
Example two
Fig. 2 is a flowchart of a moving object detection method according to a second embodiment of the present invention, and as shown in fig. 2, the moving object detection method according to the present embodiment is further detailed in steps 102 to 103 on the basis of the moving object detection method according to the first embodiment of the present invention, and further includes performing a difference operation on a first moving object binary image and a second moving object binary image; and updating the gaussian mixture model according to the binary image after the difference operation, so that the method for detecting the moving target provided by the embodiment includes the following steps.
Step 201, acquiring a video sequence frame image.
Step 202, a gaussian mixture model is adopted to perform moving target detection on the current frame image so as to obtain a first moving target binary image and a current frame background image.
Further, fig. 3 is a flowchart of step 202 of the method for detecting a moving object according to the second embodiment of the present invention, and as shown in fig. 3, the step 202 includes the following steps.
Step 202a, determining whether each pixel point in the current frame image conforms to a gaussian mixture model.
In step 202b, if a certain pixel point accords with the gaussian mixture model, the certain pixel point is determined as a background pixel point.
Step 202c, if a certain pixel point does not conform to the gaussian mixture model, the certain pixel point is determined as a moving target pixel point.
The description is made in connection with steps 202 a-202 c. Further, in this embodiment, the gaussian mixture model is a model for simulating an image background, so that if a certain pixel point in the current frame image is input into the gaussian mixture model and conforms to the gaussian mixture model, the pixel point is determined as a background pixel point, and if the certain pixel point is input into the gaussian mixture model and does not conform to the gaussian mixture model, the pixel point is determined as a moving target pixel point.
Step 202d, determining the first moving target binary image and the current frame background image according to the background pixel points and the moving target pixel points.
Further, fig. 4 is a flowchart of step 202d of the method for detecting a moving object according to the second embodiment of the present invention, and as shown in fig. 4, step 202d includes the following steps.
Step 202d1, converting the background pixel points into zero pixel points, converting the moving target pixel points into non-zero pixel points, and determining the binary image formed by the zero pixel points and the non-zero pixel points as the first moving target binary image.
Specifically, the background pixel point is converted into a zero pixel point, i.e., the pixel value corresponding to the background pixel point is set to 0. And converting the moving target pixel point into a non-zero pixel point, namely setting the pixel value corresponding to the moving target pixel point to be 255. And determining a binary image formed by zero pixel points and non-zero pixel points as a first moving target binary image, wherein in the first moving target binary image, pixel points with the pixel value of 0 are pixel points corresponding to the background, and pixel points with the pixel value of 255 are pixel points corresponding to the moving target.
Step 202d2, replacing the moving target pixel points with initial background pixel points, and determining the image formed by the background pixel points and the initial background pixel points as the current frame background image.
The initial background pixel points are background pixel points corresponding to the positions of the pixel points of the moving target before the moving target enters the scene shot by the current frame image. The initial background pixel point can be obtained from the image before the current frame image.
Further, in this embodiment, after the position of the moving target pixel is replaced with the initial background pixel, an image formed by the background pixel and the initial background pixel is determined as the current frame background image.
And 203, detecting a moving object by adopting an improved five-frame difference algorithm according to the background image of the current frame and the five-frame image corresponding to the image of the current frame to obtain a second moving object binary image.
Further, fig. 5 is a first flowchart of step 203 of the method for detecting a moving object according to the second embodiment of the present invention, and fig. 6 is a second flowchart of step 203 of the method for detecting a moving object according to the second embodiment of the present invention, as shown in fig. 5 and fig. 6, step 203 includes the following steps.
Step 203a, performing difference operation on the current frame image and the current frame background image, except for the current frame image, and performing binarization processing to obtain a corresponding difference binary image.
Specifically, as shown in fig. 6, in the present embodiment, the current frame image is the third frame image of five frame images, denoted by f3The first frame image is denoted by f1The second frame image is denoted by f2The fourth frame image is denoted by f4The fifth frame image is denoted by f5. The background image of the current frame is denoted as fb. The current frame image f3And fbCarrying out difference operation and binarization processing to obtain a difference binary image corresponding to the background image of the current frame; the current frame image f3And f1Carrying out difference operation and binarization processing to obtain a difference binary image corresponding to the first frame image; the current frame image f3And f2Carrying out difference operation and binarization processing to obtain a difference binary image corresponding to the second frame image; the current frame image f3And f4Carrying out difference operation and binarization processing to obtain a difference binary image corresponding to the fourth frame image; the current frame image f3And f5And carrying out difference operation and binarization processing to obtain a difference binary image corresponding to the fifth frame image.
In step 203b, the difference binary image corresponding to the other four frames of images except the current frame of image and the difference binary image of the background image of the current frame are subjected to logic operation to obtain a logic operation binary image.
Further, fig. 7 is a flowchart of step 203b of the method for detecting a moving object according to the second embodiment of the present invention, as shown in fig. 7, in this embodiment, step 203b includes the following steps.
In step 203b1, an or operation is performed between every two of the difference binary images corresponding to the other four frames of images except the current frame of image to obtain a first or operation binary image and a second or operation binary image.
Further, performing an or operation between every two of the differential binary images corresponding to the other four frames except the current frame image to obtain a first or operation binary image and a second or operation binary image, specifically:
and performing OR operation on the differential binary image corresponding to the first frame image and the fifth frame image to obtain a first OR operation binary image, and performing OR operation on the differential binary image corresponding to the second frame image and the fourth frame image to obtain a second OR operation binary image.
Specifically, in this embodiment, the difference binary image corresponding to the first frame image and the fifth frame image is subjected to or operation, and the obtained first or operation binary image includes all non-zero pixel points in the difference binary image corresponding to the first frame image and in the difference binary image corresponding to the second frame image. And performing OR operation on the difference binary image corresponding to the second frame image and the fourth frame image, wherein the obtained second OR operation binary image comprises all non-zero pixel points in the difference binary image corresponding to the second frame image and in the difference binary image corresponding to the fourth frame image.
In step 203b2, the difference binary image corresponding to the current frame background image is respectively and-operated with the first or operation binary image and the second or operation binary image to obtain a first and operation binary image and a second and operation binary image.
Further, in this embodiment, the difference binary image corresponding to the current frame background image is and-operated with the first or operation binary image to obtain a first and operation binary image, and the difference binary image corresponding to the current frame background image is and-operated with the second or operation binary image to obtain a second and operation binary image.
In step 203b3, the first and operation binary image and the second and operation binary image are ored to obtain a third or operation binary image.
Specifically, in this embodiment, the first and operation binary image and the second and operation binary image are subjected to or operation, and the obtained third or operation binary image includes all non-zero pixel values in the first and operation binary image and the second and operation binary image.
Wherein, the third OR operation binary image is a logic operation binary image.
Step 203c, the logical operation binary image is morphologically processed to obtain a second moving object binary image.
Further, in this embodiment, a morphological basic operator is adopted to perform morphological processing on the third or operation binary image, so as to obtain a second moving object binary image.
The method for detecting a moving object provided in this embodiment performs moving object detection according to a current frame background image and a current frame image by using an improved five-frame difference algorithm to obtain a second moving object binary image, performs difference operation on the current frame image and the current frame background image, and performs binarization processing on the four other frames except the current frame image to obtain corresponding difference binary images, performs or operation between every two difference binary images except the current frame image to obtain a first or operation binary image and a second or operation binary image, performs and operation on the difference binary image corresponding to the current frame background image and the first or operation binary image, and performs and operation on the second or operation binary image to obtain a first and operation binary image and a second and operation binary image, performs or operation on the first and operation binary image and the second and operation binary image, the method comprises the steps of obtaining a third or operation binary image, carrying out morphological processing on the third or operation binary image to obtain a second moving target binary image, and carrying out AND operation on the third or operation binary image and a first or operation binary image and a second or operation binary image because a moving target obtained by a current frame background image is accurate, so that the smear problem in the first or operation binary image and the second or operation binary image is eliminated, meanwhile, ghost and illumination sensitive part pixels existing in the conventional five-frame difference algorithm are eliminated, and finally, carrying out OR operation and morphological processing on the result of the AND operation to obtain the second moving target binary image, so that the moving target detected by the improved frame-free difference algorithm is more accurate.
Step 204, performing an or operation on the first moving target binary image and the second moving target binary image to obtain a total moving target binary image.
Step 205, performing morphological processing on the total moving object binary image to obtain a moving object.
In this embodiment, the implementation manners of steps 204 to 205 are the same as the implementation manners of steps 104 to 105 in the first embodiment of the present invention, and are not described in detail herein.
It should be noted that, after step 203, step 206-step 207 may be executed, and there is no strict limitation on the execution order between step 206-step 207 and step 204-step 205.
In step 206, a difference operation is performed on the first moving target binary image and the second moving target binary image.
Further, in this embodiment, a difference operation is performed on the first moving target binary image and the second moving target binary image to obtain a binary image after the difference operation, and in the binary image after the difference operation, there are two difference results, one is a pixel point whose pixel value is zero and the other is a non-zero pixel point whose pixel value is 255. The zero pixel points represent the moving target and the background part with the same background, and the non-zero pixel points represent the parts with different pixel values in the binary image of the moving target obtained by a Gaussian mixture model and an improved five-frame difference algorithm, and can be regarded as a ghost pixel part and a pixel part with sudden illumination change.
And step 207, updating the Gaussian mixture model according to the binary image after the difference operation.
Further, in this embodiment, the gaussian mixture model is updated according to the binary image after the difference operation, specifically:
and updating the Gaussian mixture model according to the non-zero pixel point in the binary image after the difference operation.
Specifically, in this embodiment, non-zero pixel points in the binary image after the difference operation, that is, pixel points of the ghost pixel part and the pixel part where the illumination mutation occurs, are input into the gaussian mixture model, and parameters in the gaussian mixture model are updated by using the ghost pixel points and the pixel points where the illumination mutation occurs, so that the learning rate of the gaussian mixture model can be accelerated, and the updated gaussian mixture model can more quickly remove ghost pixel points and the pixel points where the illumination mutation occurs. The accuracy of the updated Gaussian mixture model in detection of the moving target is higher.
It should be noted that after the gaussian model is updated, the current frame image is continuously acquired, and the method for detecting the moving object in this embodiment is executed according to steps 201 to 207.
Further, in this embodiment, after the gaussian mixture model is updated, the updated gaussian mixture model is used to detect the moving object of the current frame image, which can be higher in accuracy than the moving object detected in the previous frame, and the background image determined by the updated gaussian mixture model is more accurate, so that when the moving object is detected by using the improved five-frame difference algorithm, the detected moving object is more accurate than the moving object detected in the previous frame. Finally, the accuracy of the moving target detected by adopting the two algorithms is improved.
EXAMPLE III
Fig. 8 is a schematic structural diagram of a moving object detection apparatus according to a third embodiment of the present invention, and as shown in fig. 8, the moving object detection apparatus according to the third embodiment of the present invention includes: an image acquisition unit 81, a gaussian mixture model detection unit 82, an improved five-frame difference algorithm detection unit 83, an or operation unit 84, and a morphology processing unit 85.
The image obtaining unit 81 is configured to obtain a frame image of a video sequence. And the gaussian mixture model detecting unit 82 is configured to perform moving target detection on the current frame image by using a gaussian mixture model to obtain a first moving target binary image and a current frame background image. And the improved five-frame difference algorithm detection unit 83 is configured to perform moving object detection according to the current frame background image and the five-frame image corresponding to the current frame image by using an improved five-frame difference algorithm to obtain a second moving object binary image. An or operation unit 84, configured to perform an or operation on the first moving object binary image and the second moving object binary image to obtain a total moving object binary image. And a morphology processing unit 85, configured to perform morphology processing on the total moving object binary image to obtain a moving object.
The detection apparatus for a moving object provided in this embodiment may implement the technical solutions of the method embodiments shown in the first embodiment, and the implementation principles thereof are similar and will not be described herein again.
In the apparatus for detecting a moving object provided in this embodiment, an image obtaining unit obtains a video sequence frame image; the Gaussian mixture model detection unit adopts a Gaussian mixture model to detect a moving target of the current frame image so as to obtain a first moving target binary image and a current frame background image; the improved five-frame difference algorithm detection unit adopts an improved five-frame difference algorithm to detect a moving target according to a current frame background image and a five-frame image corresponding to the current frame image so as to obtain a second moving target binary image; the OR operation unit performs OR operation on the first moving target binary image and the second moving target binary image to obtain a total moving target binary image; the morphology processing unit performs morphology processing on the total moving target binary image to obtain a moving target. The method has the advantages that the current frame background image of the Gaussian mixture model is used as the background frame of the improved five-frame difference algorithm to identify the moving target, so that the accuracy of detecting the moving target of the improved five-frame difference algorithm is improved, the problem of smear is basically eliminated, the moving target detected by the Gaussian mixture model and the moving target detected by the improved five-frame difference algorithm are subjected to OR operation to obtain all the moving targets detected by the two algorithms, and the detected moving targets can be detected to be richer and have more complete outlines.
Example four
Fig. 9 is a schematic structural diagram of a moving object detection apparatus according to a fourth embodiment of the present invention, and as shown in fig. 9, the moving object detection apparatus according to the present embodiment further includes, on the basis of a moving object detection apparatus according to a third embodiment of the present invention: difference arithmetic section 91, gaussian mixture model updating section 92.
The difference operation unit 91 is configured to perform a difference operation on the first moving target binary image and the second moving target binary image. And the gaussian mixture model updating unit 92 is configured to update the gaussian mixture model according to the binary image after the difference operation.
In the moving object detection apparatus provided in this embodiment, the difference operation unit performs difference operation on the first moving object binary image and the second moving object binary image. The Gaussian mixture model updating unit updates the Gaussian mixture model according to the binary image after the difference operation, non-zero pixel points in the binary image after the difference operation, namely pixel points of the ghost pixel part and the pixel part with the illumination mutation are input into the Gaussian mixture model, parameters in the Gaussian mixture model are updated by adopting the ghost pixel points and the pixel point with the illumination mutation, the learning rate of the Gaussian mixture model can be accelerated, and the updated Gaussian mixture model can be enabled to more quickly remove ghost pixel points and the pixel points with the illumination mutation. The accuracy of the updated Gaussian mixture model in detection of the moving target is higher.
Further, the gaussian mixture model updating unit 92 is specifically configured to: and updating the Gaussian mixture model according to the non-zero pixel point in the binary image after the difference operation.
Further, the gaussian mixture model detecting unit 82 specifically includes: a pixel point judging module 82a, a background pixel point determining module 82b, a moving target pixel point determining module 82c and an image determining module 82 d.
The pixel point determining module 82a is configured to determine whether each pixel point in the current frame image conforms to the gaussian mixture model. And the background pixel point determining module 82b is configured to determine a certain pixel point as a background pixel point if the certain pixel point conforms to the gaussian mixture model. And a moving target pixel point determining module 82c, configured to determine a certain pixel point as a moving target pixel point if the certain pixel point does not conform to the gaussian mixture model. And the image determining module 82d is configured to determine the first moving target binary image and the current frame background image according to the background pixel points and the moving target pixel points.
Further, the image determining module 82d is specifically configured to: converting background pixel points into zero pixel points, converting moving target pixel points into non-zero pixel points, and determining a binary image formed by the zero pixel points and the non-zero pixel points as a first moving target binary image; and replacing the moving target pixel points with initial background pixel points, and determining an image formed by the background pixel points and the initial background pixel points as a current frame background image.
Further, the improved five-frame difference algorithm detection unit 83 specifically includes: a difference operation module 83a, a logic operation module 83b, and a morphology processing module 83 c.
The difference operation module 83a is configured to perform difference operation on the current frame image and the current frame background image, and perform binarization processing on the other four frames of images except the current frame image, so as to obtain a corresponding difference binary image. The logical operation module 83b is configured to perform logical operation on the difference binary image corresponding to the other four frames of images except the current frame of image and the difference binary image of the current frame of background image to obtain a logical operation binary image. And a morphology processing module 83c, configured to perform morphology processing on the logical operation binary image to obtain a second moving object binary image.
Further, the logic operation module 83b specifically includes: a first or operator sub-module 83b1, and operator sub-module 83b2, a second or operator sub-module 83b 3.
The first or operation sub-module 83b1 is configured to perform or operation between every two difference binary images corresponding to the other four frames of images except the current frame of image to obtain a first or operation binary image and a second or operation binary image. The and sub-module 83b2 is configured to perform and operation on the difference binary image corresponding to the current frame background image and the first or operation binary image and the second or operation binary image respectively to obtain a first and operation binary image and a second and operation binary image. The second or operation sub-module 83b3 is configured to perform an or operation on the first and operation binary image and the second and operation binary image to obtain a third or operation binary image. Wherein, the third OR operation binary image is a logic operation binary image.
Further, the first or operation sub-module 83b1 is specifically configured to perform an or operation on the difference binary image corresponding to the first frame image and the fifth frame image to obtain a first or operation binary image, and perform an or operation on the difference binary image corresponding to the second frame image and the fourth frame image to obtain a second or operation binary image.
In the moving object detection apparatus provided in this embodiment, when the improved five-frame difference algorithm detection unit performs moving object detection according to the current frame background image and the five frame image corresponding to the current frame image by using the improved five-frame difference algorithm to obtain the second moving object binary image, the difference operation module performs difference operation on the current frame image and the current frame background image, and performs binarization processing on the other four frame images except the current frame image, respectively, to obtain corresponding difference binary images, the first or operation sub-module performs or operation between every two difference binary images except the other four frame images of the current frame image, to obtain the first or operation binary image and the second or operation binary image, the and operation sub-module performs and operation on the difference binary image corresponding to the current frame background image, respectively, with the first or operation binary image and the second or operation binary image, to obtain a first and operation binary image and a second and operation binary image, the second OR operation sub-module performs OR operation on the first and operation binary image and the second and operation binary image, to obtain a third OR operation binary image, the morphology processing module performs morphology processing on the third OR operation binary image to obtain a second moving target binary image, because the moving target obtained by the background image of the current frame is more accurate, the moving target is used for carrying out AND operation with the first OR operation binary image and the second OR operation binary image, the smear problem in the first OR operation binary image and the second OR operation binary image is filtered, meanwhile, ghost and illumination sensitive part pixels existing in the existing five-frame difference algorithm are removed, and finally, the result of the AND operation is subjected to OR operation and morphological processing to obtain a second moving target binary image, so that the moving target detected by the improved frame-free difference algorithm is more accurate.
The detection apparatus for a moving object provided in this embodiment may perform the technical solutions of the method embodiments shown in the second embodiment, and the implementation principles thereof are similar and will not be described herein again.
EXAMPLE five
Fig. 10 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention, and as shown in fig. 10, the electronic device according to the present embodiment includes: a memory 1001, a processor 1002, and computer programs.
The computer program is stored in the memory 1001 and configured to be executed by the processor 1002 to implement the method for detecting a moving object according to the first embodiment of the present invention or the method for detecting a moving object according to the second embodiment of the present invention.
The related descriptions may be referred to in the related descriptions of the first embodiment to the second embodiment.
The electronic device provided by the embodiment comprises a memory, a processor and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method for detecting a moving object as provided in the first embodiment or the method for detecting a moving object as provided in the second embodiment of the present invention. The method comprises the steps of using a background image of a current frame of a Gaussian mixture model as a background frame of an improved five-frame difference algorithm to identify a moving target, improving the accuracy of detecting the moving target of the improved five-frame difference algorithm, basically eliminating the problem of smear, carrying out OR operation on the moving target detected by the Gaussian mixture model and the moving target detected by the improved five-frame difference algorithm to obtain all the moving targets detected by the two algorithms, and enabling the detected moving targets to be richer and have more complete outlines.
EXAMPLE six
A sixth embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method for detecting a moving object provided in the first embodiment of the present invention or the method for detecting a moving object provided in the second embodiment of the present invention.
In the computer-readable storage medium provided by this embodiment, a computer program is stored thereon, and the computer program is executed by a processor to implement the method for detecting a moving object provided by the first embodiment of the present invention or the method for detecting a moving object provided by the second embodiment of the present invention, because a current frame background image of a gaussian mixture model is used as a background frame of an improved five-frame difference algorithm to identify a moving object, accuracy of detecting a moving object by the improved five-frame difference algorithm is improved, an existing smear problem is substantially eliminated, and all moving objects detected by two algorithms are obtained by performing or operation on the moving object detected by the gaussian mixture model and the moving object detected by the improved five-frame difference algorithm, so that the detected moving objects are richer and have a more complete contour.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of modules is merely a division of logical functions, and an actual implementation may have another division, for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
Modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware form, and can also be realized in a form of hardware and a software functional module.
Program code for implementing the methods of the present invention may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Further, while operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims (11)
1. A method for detecting a moving object, comprising:
acquiring a video sequence frame image;
adopting a Gaussian mixture model to detect a moving target of the current frame image so as to obtain a first moving target binary image and a current frame background image;
detecting a moving target by adopting an improved five-frame difference algorithm according to the current frame background image and the five frame image corresponding to the current frame image to obtain a second moving target binary image;
carrying out OR operation on the first moving target binary image and the second moving target binary image to obtain a total moving target binary image;
and carrying out morphological processing on the total moving target binary image to obtain a moving target.
2. The method of claim 1, further comprising:
carrying out difference operation on the first moving target binary image and the second moving target binary image;
and updating the Gaussian mixture model according to the binary image after the difference operation.
3. The method according to claim 2, wherein the updating of the gaussian mixture model according to the binary image after the difference operation is specifically:
and updating the Gaussian mixture model according to the nonzero pixel point in the binary image after the difference operation.
4. The method according to claim 1, wherein the performing moving object detection on the current frame image by using the gaussian mixture model to obtain the first moving object binary image and the current frame background image specifically comprises:
judging whether each pixel point in the current frame image accords with the Gaussian mixture model;
if a certain pixel point accords with the Gaussian mixture model, determining the certain pixel point as a background pixel point;
if a certain pixel point does not conform to the Gaussian mixture model, determining the certain pixel point as a moving target pixel point;
and determining a first moving target binary image and a current frame background image according to the background pixel points and the moving target pixel points.
5. The method according to claim 4, wherein the determining a first moving object binary image and a current frame background image according to the background pixel points and the moving object pixel points specifically comprises:
converting the background pixel points into zero pixel points, converting the moving target pixel points into non-zero pixel points, and determining a binary image formed by the zero pixel points and the non-zero pixel points as a first moving target binary image;
and replacing the moving target pixel points with initial background pixel points, and determining an image formed by the background pixel points and the initial background pixel points as a current frame background image.
6. The method according to claim 1, wherein the performing moving object detection according to the current frame background image and the five frame images corresponding to the current frame image by using an improved five-frame difference algorithm to obtain a second moving object binary image specifically comprises:
respectively carrying out differential operation on the current frame image and the current frame background image except the other four frame images of the current frame image and carrying out binarization processing to obtain a corresponding differential binary image;
performing logical operation on the differential binary image corresponding to the other four frames of images except the current frame of image and the differential binary image of the current frame of background image to obtain a logical operation binary image;
and performing morphological processing on the logic operation binary image to obtain a second moving target binary image.
7. The method according to claim 6, wherein the performing a logical operation on the difference binary image corresponding to the other four frames of images except the current frame of image and the difference binary image of the current frame of background image to obtain a logical operation binary image specifically comprises:
performing OR operation between every two difference binary images corresponding to the other four frames except the current frame image to obtain a first OR operation binary image and a second OR operation binary image;
respectively performing AND operation on the differential binary image corresponding to the current frame background image and the first OR operation binary image and the second OR operation binary image to obtain a first AND operation binary image and a second AND operation binary image;
performing an OR operation on the first AND operation binary image and the second AND operation binary image to obtain a third OR operation binary image;
wherein the third or operation binary image is the logic operation binary image.
8. The method according to claim 7, wherein the or operation is performed between every two of the difference binary images corresponding to the other four frames of images except the current frame of image to obtain a first or operation binary image and a second or operation binary image, specifically:
and performing OR operation on the differential binary image corresponding to the first frame image and the fifth frame image to obtain a first OR operation binary image, and performing OR operation on the differential binary image corresponding to the second frame image and the fourth frame image to obtain a second OR operation binary image.
9. A moving object detection apparatus, comprising:
the image acquisition unit is used for acquiring a video sequence frame image;
the Gaussian mixture model detection unit is used for detecting a moving target of the current frame image by adopting a Gaussian mixture model so as to obtain a first moving target binary image and a current frame background image;
the improved five-frame difference algorithm detection unit is used for detecting a moving object by adopting an improved five-frame difference algorithm according to the current frame background image and the five frame image corresponding to the current frame image so as to obtain a second moving object binary image;
an or operation unit, configured to perform or operation on the first moving target binary image and the second moving target binary image to obtain a total moving target binary image;
and the morphology processing unit is used for carrying out morphology processing on the total moving target binary image so as to obtain a moving target.
10. An electronic device, comprising:
a memory, a processor, and a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1-8.
11. A readable storage medium, having stored thereon a computer program for execution by a processor to perform the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811539983.0A CN111325773A (en) | 2018-12-17 | 2018-12-17 | Method, device and equipment for detecting moving target and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811539983.0A CN111325773A (en) | 2018-12-17 | 2018-12-17 | Method, device and equipment for detecting moving target and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111325773A true CN111325773A (en) | 2020-06-23 |
Family
ID=71165047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811539983.0A Pending CN111325773A (en) | 2018-12-17 | 2018-12-17 | Method, device and equipment for detecting moving target and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111325773A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102365A (en) * | 2020-09-23 | 2020-12-18 | 烟台艾睿光电科技有限公司 | Target tracking method based on unmanned aerial vehicle pod and related device |
| CN112270657A (en) * | 2020-11-04 | 2021-01-26 | 成都寰蓉光电科技有限公司 | Sky background-based target detection and tracking algorithm |
| CN112509012A (en) * | 2020-12-14 | 2021-03-16 | 青岛聚好联科技有限公司 | Detection method of high-altitude object throwing |
| CN113052158A (en) * | 2021-03-30 | 2021-06-29 | 济南博观智能科技有限公司 | Night infrared scene target identification method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106846359A (en) * | 2017-01-17 | 2017-06-13 | 湖南优象科技有限公司 | Moving target method for quick based on video sequence |
| CN107507221A (en) * | 2017-07-28 | 2017-12-22 | 天津大学 | With reference to frame difference method and the moving object detection and tracking method of mixed Gauss model |
| WO2018133101A1 (en) * | 2017-01-23 | 2018-07-26 | 富士通株式会社 | Image foreground detection apparatus and method, and electronic device |
-
2018
- 2018-12-17 CN CN201811539983.0A patent/CN111325773A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106846359A (en) * | 2017-01-17 | 2017-06-13 | 湖南优象科技有限公司 | Moving target method for quick based on video sequence |
| WO2018133101A1 (en) * | 2017-01-23 | 2018-07-26 | 富士通株式会社 | Image foreground detection apparatus and method, and electronic device |
| CN107507221A (en) * | 2017-07-28 | 2017-12-22 | 天津大学 | With reference to frame difference method and the moving object detection and tracking method of mixed Gauss model |
Non-Patent Citations (2)
| Title |
|---|
| 刘波 等: "基于五帧帧差和混合高斯模型的运动目标检测", 嘉应学院学报（自然科学）, vol. 35, no. 8, pages 37 - 40 * |
| 潘峥嵘;钟珍珍;张宁;: "改进的背景减法与五帧差分法相结合的运动目标检测", 自动化与仪表, no. 07, pages 22 - 25 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102365A (en) * | 2020-09-23 | 2020-12-18 | 烟台艾睿光电科技有限公司 | Target tracking method based on unmanned aerial vehicle pod and related device |
| CN112270657A (en) * | 2020-11-04 | 2021-01-26 | 成都寰蓉光电科技有限公司 | Sky background-based target detection and tracking algorithm |
| CN112509012A (en) * | 2020-12-14 | 2021-03-16 | 青岛聚好联科技有限公司 | Detection method of high-altitude object throwing |
| CN112509012B (en) * | 2020-12-14 | 2022-12-09 | 青岛聚好联科技有限公司 | Detection method of high-altitude object throwing |
| CN113052158A (en) * | 2021-03-30 | 2021-06-29 | 济南博观智能科技有限公司 | Night infrared scene target identification method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101640998B1 (en) | Image processing apparatus and image processing method | |
| CN111325773A (en) | Method, device and equipment for detecting moving target and readable storage medium | |
| US7742650B2 (en) | Object detection in images | |
| St-Charles et al. | A self-adjusting approach to change detection based on background word consensus | |
| CN110443210B (en) | Pedestrian tracking method and device and terminal | |
| CN106296725B (en) | Moving target real-time detection and tracking method and target detection device | |
| CN107404628B (en) | Image processing apparatus and method, and monitoring system | |
| CN108229475B (en) | Vehicle tracking method, system, computer device and readable storage medium | |
| CN109685045B (en) | Moving target video tracking method and system | |
| CN108229300B (en) | Video classification method and device, computer-readable storage medium and electronic equipment | |
| CN109344864B (en) | Image processing method and device for dense object | |
| CN112364740B (en) | Unmanned aerial vehicle room monitoring method and system based on computer vision | |
| CN111144337B (en) | Fire detection method and device and terminal equipment | |
| CN112417955B (en) | Method and device for processing tour inspection video stream | |
| WO2019197021A1 (en) | Device and method for instance-level segmentation of an image | |
| CN104537622A (en) | Method and system for removing raindrop influence in single image | |
| CN111028266B (en) | Livestock and poultry inventory method and device, electronic equipment and storage medium | |
| CN113705380B (en) | Target detection method and device for foggy days, electronic equipment and storage medium | |
| KR101690050B1 (en) | Intelligent video security system | |
| CN107871315B (en) | Video image motion detection method and device | |
| CN111667419A (en) | Moving target ghost eliminating method and system based on Vibe algorithm | |
| CN116309590A (en) | Visual computing method, system, electronic equipment and medium based on artificial intelligence | |
| CN113221603A (en) | Method and device for detecting shielding of monitoring equipment by foreign matters | |
| CN114445898B (en) | Face living body detection method, device, equipment, storage medium and program product | |
| CN106446764B (en) | Video object detection method based on improved fuzzy color aggregated vector |
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 |