CN104349125A

CN104349125A - Area monitoring method and device

Info

Publication number: CN104349125A
Application number: CN201310336416.6A
Authority: CN
Inventors: 谢志明; 潘晖; 潘石柱; 张兴明; 傅利泉; 朱江明; 吴军; 吴坚
Original assignee: Zhejiang Dahua Technology Co Ltd
Current assignee: Zhejiang Dahua Technology Co Ltd
Priority date: 2013-08-05
Filing date: 2013-08-05
Publication date: 2015-02-11
Anticipated expiration: 2033-08-05
Also published as: CN104349125B

Abstract

The invention discloses an area monitoring method and device. Specific content is as follows: analyzing a plurality of video image frames which are included in an obtained video image frame sequence; and targeting at an identical specific area of the plurality of video image frames, determining a first number of video image frames, in which the gray level of the specific area and the gray level of a reference image are different, in a first number of video image frames and a second number of video image frames, in which moving targets exist in the target area, in a second number of video image frames so as to determine whether people enter a practical area corresponding to the specific area so that accurate judgment of whether people enter the specific area can be realized.

Description

A kind of area monitoring method and equipment

Technical field

The present invention relates to technical field of image processing, particularly relate to a kind of area monitoring method and equipment.

Background technology

In the scene of the indoor and outdoor isolation such as bank counter, Real-Time Monitoring is carried out in order to realize entering the situation of carrying out business handling in sales counter region to outdoor personnel, at present, prior art mainly adopts carries out distinguishing the method detected to background image and foreground target, enters sales counter monitor personnel.Specifically, background foreground detection method of the prior art can first be distinguished the background area (i.e. background image) in image and foreground target; Then, then to the motion conditions of foreground target monitor; Finally, whether move in appointed area according to foreground target, can judge whether foreground target enters appointed area.

Due in the method that prior art adopts, the detection accuracy of background image is easily subject to the impact of the factor that light etc. causes image background to change, thus is difficult to accurately background image be detected; And for the personnel at bank counter stay longer, adopt the method that these personnel also may be caused to be identified as a part for background image, thus obtain the judged result of mistake.

Based on the above-mentioned defect of prior art, prior art is difficult to realize whether that someone enters the accurate judgement in a certain region.

Summary of the invention

In view of this, the present invention proposes a kind of area monitoring method, accurately can judge someone enters a certain region.

According to one embodiment of the invention, provide a kind of area monitoring method, comprising:

Obtain video image frame sequence;

Whether be there are differences with the gray scale of the described specific region of reference picture by the gray scale detecting the same specific region of each video frame image in the video frame image of the first quantity that described video image frame sequence comprises respectively, determine the first number of the video frame image that the gray scale of the gray scale of described specific region and the described specific region of described reference picture there are differences;

Whether there is moving target by the described specific region of detecting each video frame image in the video frame image of the second quantity that described video image frame sequence comprises respectively, determine the second number of the video frame image that there is moving target in described specific region;

According to described first number and the second number, judge whether that someone enters the actual area corresponding to described specific region.

As can be seen from such scheme, due to the same specific region of multiple video frame images comprised for the video image frame sequence obtained, carry out gray difference detection and moving object detection respectively, and determine whether that someone enters the actual area corresponding to described specific region according to the combination of two kinds of testing results, achieve the information according to reflection specific region grey scale change situation, and the information of object of which movement situation in reflection specific region, complete the monitoring to the actual area corresponding to specific region.Compared with the scheme provided with prior art, the program provided due to the embodiment of the present invention is not easy to be subject to the impact of the factors such as light, therefore can realize accurately judging someone enters a certain region.

Particularly, adopt following manner, whether the gray scale detecting the same specific region of each video frame image in the video frame image of described first quantity respectively there are differences with the gray scale of the described specific region of reference picture:

The first assigned operation is performed respectively for each video frame image in the video frame image of described first quantity;

Wherein, described first assigned operation comprises:

Perform respectively for each pixel in the described specific region of this video frame image: the gray value comparing the pixel being in the same position of described specific region in the gray value of this pixel and reference picture with this pixel;

According to the comparative result for described each pixel, from the described specific region of this video frame image, determine that the difference of the gray value of the pixel that gray value is corresponding to reference picture is greater than all pixels of preset difference value threshold value;

When the number of described all pixels is greater than gray scale number threshold value, determine that the gray scale of the gray scale of the described specific region of this video frame image and the described specific region of described reference picture there are differences.

Like this, by comparing the gray value difference of its corresponding pixel one by one to the specific region of video frame image and the specific region of reference picture, can the grey scale change of the accurate specific region of reflecting video picture frame whether obvious, for determining whether that someone enters the actual area corresponding to the specific region of video frame image.

Particularly, adopt following manner, in the described specific region detecting each video frame image in the video frame image of described second quantity respectively, whether there is moving target:

The second assigned operation is performed respectively for each video frame image in the video frame image of described second quantity;

Wherein, described second assigned operation comprises:

Determine the modulus value of the motion vector of each pixel in the described specific region of this video frame image respectively;

According to the modulus value of the motion vector of each pixel described, determine that the modulus value of motion vector in all pixels of described specific region is greater than the number of the pixel of modulus value threshold value;

When the number that the modulus value of described motion vector is greater than the pixel of modulus value threshold value is greater than the first motion number threshold value, determine to there is moving target in described specific region.

Like this, by the modulus value of the motion vector of each pixel in the specific region of determining video frame image, the specific region of accurate reflecting video picture frame whether can there is moving target, for determining whether that someone enters the actual area corresponding to the specific region of video frame image.

Alternatively, can following manner be adopted, in the described specific region detecting each video frame image in the video frame image of described second quantity respectively, whether there is moving target:

The 3rd assigned operation is performed respectively for each video frame image in the video frame image of described second quantity;

Wherein, described 3rd assigned operation comprises:

Determine the absolute value of the motion vector of each pixel in the described specific region of this video frame image respectively; Wherein, the absolute value of described motion vector refers to the absolute value sum of each component in this motion vector;

According to the absolute value of the motion vector of each pixel described, determine that the absolute value of motion vector in all pixels of described specific region is greater than the number of the pixel of absolute value threshold value;

When the number that the absolute value of described motion vector is greater than the pixel of absolute value threshold value is greater than the second motion number threshold value, determine to there is moving target in described specific region.

Like this, by the absolute value of the motion vector of each pixel in the specific region of determining video frame image, the specific region of accurate reflecting video picture frame whether can there is moving target, for determining whether that someone enters the actual area corresponding to the specific region of video frame image.

Corresponding with above-mentioned zone method for supervising, embodiments of the invention also provide a kind of area monitoring equipment, and described equipment comprises:

Obtain module, for obtaining video image frame sequence;

First determination module, whether the gray scale for the same specific region by detecting each video frame image in the video frame image of the first quantity that described video image frame sequence comprises respectively there are differences with the gray scale of the described specific region of reference picture, determines the first number of the video frame image that the gray scale of the gray scale of described specific region and the described specific region of described reference picture there are differences;

Second determination module, for whether there is moving target in the described specific region by detecting each video frame image in the video frame image of the second quantity that described video image frame sequence comprises respectively, determine the second number of the video frame image that there is moving target in described specific region;

Judging module, for according to described first number and the second number, judges whether that someone enters the actual area corresponding to described specific region.

The same specific region of the multiple video frame images adopting this equipment can comprise the video image frame sequence obtained, carry out gray difference detection and moving object detection respectively, and determine whether that someone enters the actual area corresponding to described specific region according to the combination of two kinds of testing results, achieve the information according to reflection specific region color change situation, and the information of object of which movement situation in reflection specific region, complete the monitoring to the actual area corresponding to specific region.Compared with the scheme provided with prior art, the program provided due to the embodiment of the present invention is not easy to be subject to the impact of the factors such as light, therefore can realize accurately judging someone enters a certain region.

Particularly, described first determination module can be used for performing the first assigned operation respectively for each video frame image in the video frame image of described first quantity;

Wherein, described first assigned operation comprises: perform respectively for each pixel in the described specific region of this video frame image: the gray value comparing the pixel being in the same position of described specific region in the gray value of this pixel and reference picture with this pixel; According to the comparative result for described each pixel, from the described specific region of this video frame image, determine that the difference of the gray value of the pixel that gray value is corresponding to reference picture is greater than all pixels of preset difference value threshold value; When the number of described all pixels is greater than gray scale number threshold value, determine that the gray scale of the gray scale of the described specific region of this video frame image and the described specific region of described reference picture there are differences.

Particularly, described second determination module can be used for performing the second assigned operation respectively for each video frame image in the video frame image of described second quantity;

Wherein, described second assigned operation comprises: the modulus value determining the motion vector of each pixel in the described specific region of this video frame image respectively; According to the modulus value of the motion vector of each pixel described, determine that the modulus value of motion vector in all pixels of described specific region is greater than the number of the pixel of modulus value threshold value; When the number that the modulus value of described motion vector is greater than the pixel of modulus value threshold value is greater than the first motion number threshold value, determine to there is moving target in described specific region.

Alternatively, described second determination module can be used for performing the 3rd assigned operation respectively for each video frame image in the video frame image of described second quantity;

Wherein, described 3rd assigned operation comprises: the absolute value determining the motion vector of each pixel in the described specific region of this video frame image respectively; Wherein, the absolute value of described motion vector refers to the absolute value sum of each component in this motion vector; According to the absolute value of the motion vector of each pixel described, determine that the absolute value of motion vector in all pixels of described specific region is greater than the number of the pixel of absolute value threshold value; When the number that the absolute value of described motion vector is greater than the pixel of absolute value threshold value is greater than the second motion number threshold value, determine to there is moving target in described specific region.

Area monitoring method in above-described embodiment and equipment are applicable to the situation that obtained video frame image is gray level image, for the situation that obtained video frame image is coloured image, the embodiment of the present invention also provides another area monitoring method and equipment, accurately judges whether that someone enters the problem in a certain region in order to solve being difficult to of existing in prior art.

Therefore, according to another embodiment of the present invention, provide a kind of area monitoring method, comprising:

Obtain video image frame sequence;

Whether be there are differences with the color of the described specific region of reference picture by the color detecting the same specific region of each video frame image in the video frame image of the first quantity that described video image frame sequence comprises respectively, determine the first number of the video frame image that the color of the color of described specific region and the described specific region of described reference picture there are differences;

As can be seen from such scheme, due to the same specific region of multiple video frame images comprised for the video image frame sequence obtained, carry out heterochromia detection and moving object detection respectively, and determine whether that someone enters the actual area corresponding to described specific region according to the combination of two kinds of testing results, achieve the information according to reflection specific region color change situation, and the information of object of which movement situation in reflection specific region, complete the monitoring to the actual area corresponding to specific region.Compared with the scheme provided with prior art, the program provided due to the embodiment of the present invention is not easy to be subject to the impact of the factors such as light, therefore can realize accurately judging someone enters a certain region.

Particularly, adopt following manner, whether the color detecting the same specific region of each video frame image in the video frame image of described first quantity respectively there are differences with the color of the described specific region of reference picture:

Wherein, described first assigned operation comprises:

Perform respectively for each pixel in the described specific region of this video frame image: each color space component for this pixel performs respectively: compare the corresponding color space component being in the pixel of the same position of described specific region in this color space component of this pixel and reference picture to this pixel;

According to the comparative result for described each pixel, from the described specific region of this video frame image, be determined to a rare color space component and meet all pixels being greater than preset difference value threshold value to the difference of the corresponding color space component of the corresponding pixel of reference picture;

When the number of described all pixels is greater than color number threshold value, determine that the color of the color of the described specific region of this video frame image and the described specific region of described reference picture there are differences.

Like this, by comparing the difference of the corresponding color space component of its corresponding pixel one by one to the specific region of video frame image and the specific region of reference picture, can the color change of the accurate specific region of reflecting video picture frame whether obvious, for determining whether that someone enters the actual area corresponding to the specific region of video frame image.

Wherein, described second assigned operation comprises:

Alternatively, adopt following manner, in the described specific region detecting each video frame image in the video frame image of described second quantity respectively, whether there is moving target:

Wherein, described 3rd assigned operation comprises:

Obtain module, for obtaining video image frame sequence;

First determination module, whether the color for the same specific region by detecting each video frame image in the video frame image of the first quantity that described video image frame sequence comprises respectively there are differences with the color of the described specific region of reference picture, determines the first number of the video frame image that the color of the color of described specific region and the described specific region of described reference picture there are differences;

The same specific region of the multiple video frame images adopting this equipment can comprise the video image frame sequence obtained, carry out heterochromia detection and moving object detection respectively, and determine whether that someone enters the actual area corresponding to described specific region according to the combination of two kinds of testing results, achieve the information according to reflection specific region color change situation, and the information of object of which movement situation in reflection specific region, complete the monitoring to the actual area corresponding to specific region.Compared with the scheme provided with prior art, the program provided due to the embodiment of the present invention is not easy to be subject to the impact of the factors such as light, therefore can realize accurately judging someone enters a certain region.

Wherein, described first assigned operation comprises: perform respectively for each pixel in the described specific region of this video frame image: each color space component for this pixel performs respectively: compare the corresponding color space component being in the pixel of the same position of described specific region in this color space component of this pixel and reference picture to this pixel; According to the comparative result for described each pixel, from the described specific region of this video frame image, be determined to a rare color space component and meet all pixels being greater than preset difference value threshold value to the difference of the corresponding color space component of the corresponding pixel of reference picture; When the number of described all pixels is greater than color number threshold value, determine that the color of the color of the described specific region of this video frame image and the described specific region of described reference picture there are differences.

Accompanying drawing explanation

Fig. 1 is the method step schematic diagram in the embodiment of the present invention one;

Fig. 2 is the schematic diagram of the specific region in the embodiment of the present invention one in a video frame image;

Fig. 3 a is the schematic diagram of the pixel in the specific region of current video image frame in the embodiment of the present invention one;

Fig. 3 b is the schematic diagram of the pixel in the specific region of reference picture in the embodiment of the present invention one;

Method step schematic diagram in Fig. 4 embodiment of the present invention two;

Fig. 5 is the device structure schematic diagram in the embodiment of the present invention three, four.

Embodiment

The scheme of the embodiment of the present invention carries out static gray Difference test and dynamic motion target detection by the multiple video frame images comprised the video image frame sequence obtained, for multiple video frame images that video image frame sequence comprises, determine the number of the video frame image that the gray scale of the gray scale of specific region and the specific region of reference picture there are differences, and in this specific region, the number of the video frame image that there is moving target detected, and judge whether that someone enters the actual area corresponding to this specific region according to testing result, effectively can enter a certain region to personnel to monitor in real time.

Below for acquisition video frame image be gray level image, embodiments of the present invention is further illustrated, but the present invention is not limited to the following examples.

Embodiment one:

As shown in Figure 1, be the step schematic diagram of area monitoring method in the embodiment of the present invention one, described method mainly comprises the following steps:

Step 101: obtain video image frame sequence.

The specific implementation of this step 101 can be: obtain the video image frame sequence that in a certain setting-up time section, video camera photographs.Particularly, described video camera can captured in real-time to personnel's situation in a certain region, such as, a video camera is installed in bank counter inside, the situation of counter window external client transacting business can be photographed.As shown in Figure 2, for the schematic diagram including a frame video image frame of counter window and bank clerk region that described video camera photographs, dotted line frame institute's region in this video frame image and counter window region, it is the specific region in this video frame image.In the method that the embodiment of the present invention provides, only can carry out hereinafter described various detections for the specific region in video frame image.

It should be noted that, in a frame video image frame of the video image frame sequence that this step 101 obtains, a specific region (image-region at the counter window place namely photographed) may be comprised, also may comprise multiple specific region.The scheme of the embodiment of the present invention is described to comprise a specific region in video frame image, for the situation comprising multiple specific region in video frame image, each specific region in described multiple specific region all can adopt the scheme of the embodiment of the present invention to process.

Step 102: determine in the video frame image of the first quantity that this video image frame sequence comprises, the first number of the video frame image that the gray scale of the gray scale of specific region and the specific region of reference picture there are differences.

For convenience of description, in the embodiment of the present invention, the gray scale of the gray scale of specific region detected in video frame image and the specific region of reference picture be there are differences and detect referred to as gray difference.

Based on the video image frame sequence that step 101 obtains, the video frame image of this step 102 to the first quantity that obtained video image frame sequence comprises carries out gray difference detection, and the first number of video frame image that the gray scale of adding up the gray scale of specific region and the specific region of reference picture there are differences.

Particularly, this step 102 can carry out gray difference detection to each video frame image in obtained video image frame sequence, and the number of video frame image that statistic mixed-state there are differences to the gray scale of the specific region of the gray scale of specific region and reference picture, the first quantity namely mentioned above can be total number of the video frame image that this video image frame sequence comprises.Alternatively, be enough to the prerequisite of the grey scale change situation of the accurate reflecting video sequence of image frames of the first number energy ensureing finally to obtain in the number of the video frame image carrying out gray difference detection under, in order to reduce amount of calculation, gray difference detection can be carried out by interval N frame to the video frame image in obtained sequence of image frames, wherein, N be greater than 1 positive integer, alternatively, N is the positive integer between 2 ~ 5, and the first quantity namely mentioned above can be less than total number of the video frame image that this video image frame sequence comprises.

In order to realize carrying out gray difference detection to the video frame image of the first quantity that the video image frame sequence obtained comprises, the reference picture detecting gray difference first can be determined.Particularly, described reference picture can for the image taken when not having personnel to enter by video camera in the actual area corresponding to specific region, wherein, position in a reference image, the specific region of reference picture is identical with the position of specific region in video frame image of video frame image.

150 video frame images are comprised below with video image frame sequence, every 2 frames, gray difference detection is carried out to specific region, namely gray difference is carried out to 75 video frame images in the video image frame sequence obtained and is detected as example, following detailed description is carried out to the specific implementation of this step 102:

Carrying out in the process of gray difference detection to each video frame image in above-mentioned 75 video frame images respectively, for the current any video frame image (hereinafter current video image frame) carrying out gray difference detection, before whether the gray scale of the gray scale of specific region and the specific region of reference picture that judge current video image frame there are differences, first can be normalized preliminary treatment to the specific region of reference picture and the specific region of current video image frame.Wherein, described normalized specifically refers to, the gray average of the specific region of current video image frame and the specific region of reference picture and gray variance value are adjusted to the gray average preset and gray variance value corresponding consistent respectively.

After above-mentioned normalized is carried out to current video image frame, judge that the process whether gray scale of specific region of the current video image frame after normalization and the gray scale of the specific region of reference picture there are differences is as follows:

By the gray value of each pixel in the specific region of the current video image frame after normalization respectively with the specific region of reference picture in be in the pixel of same position with this pixel gray value compare.Such as, the gray value of the gray value of first pixel (as shown in Figure 3 a) in the specific region of the current video image frame after normalization and first pixel (as shown in Figure 3 b) in the specific region of reference picture is compared, judge whether the difference of its gray value is greater than preset difference value threshold value, if, then trigger the pixel counter execution pixel number pre-set and add 1, if not, then do not trigger this counter execution pixel number and add 1.For the operation performed by other pixels can the like.Each pixel in the specific region to the current video image frame after normalization all completes after above-mentioned gray value difference judges, in the specific region can determining the current video image frame after normalization, the difference of the gray value of the pixel that gray value is corresponding with in the specific region of reference picture is greater than the number of the pixel of preset difference value threshold value.

When the number that the difference of described gray value is greater than the pixel of preset difference value threshold value is greater than gray scale number threshold value, can determine that the gray scale of the gray scale of the specific region of this video frame image and the specific region of reference picture there are differences; Otherwise, then determine that the gray scale of the gray scale of the specific region of this video frame image and the specific region of reference picture not there are differences.

For each video frame image comprised in the video image frame sequence of 75 video frame images obtained, said method all can be adopted to judge, and whether the gray scale of specific region of current video image frame and the gray scale of the specific region of reference picture there are differences, if so, then trigger the number that the picture frame that a pre-sets counter performs the video frame image that the gray scale of the gray scale of specific region and the specific region of reference picture be there are differences and add 1; If not, then do not trigger this counter to carry out adding 1 operation.

Such as, after gray difference detection is carried out to the specific region of 75 video frame images, determine and wherein have the gray scale of the gray scale of the specific region of 55 video frame images and the specific region of reference picture there are differences, then 75 is the first quantity in the embodiment of the present invention one, and 55 is the first number in the embodiment of the present invention one.

Step 103: determine, in the video frame image of the second quantity that this video image frame sequence comprises, to there is the second number of the video frame image of moving target in specific region.

It should be noted that, this step 103 and step 102 are independently carried out, and its execution sequence in no particular order, can carry out simultaneously.

Based on the video image frame sequence that step 101 obtains, moving object detection is carried out in the specific region of this step 103 to multiple video frame images that obtained video image frame sequence comprises, and statistics detects the second number of the video frame image of moving target in specific region.

Similar with step 102, this step 103 can carry out moving object detection to the specific region of each video frame image in obtained video image frame sequence, and statistics detects the number that there is Moving Targets Based on Video Streams picture frame in specific region, the second quantity namely mentioned above can be total number of the video frame image that this video image frame sequence comprises.Alternatively, be enough to the prerequisite of the object of which movement situation in the accurate reflecting video sequence of image frames of the second number energy ensureing finally to obtain in the number of the video frame image carrying out moving object detection under, in order to reduce amount of calculation, moving object detection can be carried out by interval N frame to the specific region of the video frame image in obtained video image frame sequence, wherein, N be greater than 1 positive integer, alternatively, N is the positive integer between 2 ~ 5, and the second quantity namely mentioned above can be less than total number of the video frame image that this video image frame sequence comprises.

It should be noted that, first quantity of carrying out the video frame image of gray difference detection in the second quantity of the video frame image of moving object detection and step 102 is carried out in this step 103, can be identical, also can be different, if the video frame image carrying out gray difference detection in a step 102 has also carried out moving object detection in step 103, then testing result is more accurate.

150 video frame images are comprised below with video image frame sequence, every 2 frames, moving object detection is carried out to the specific region of video frame image, namely carrying out moving object detection to the specific region of 75 video frame images in the video image frame sequence obtained is example, is described in detail the specific implementation of this step 103.

The first step: the video image frame sequence obtained step 101 to carry out the Gaussian smoothing of specific region every 2 frames, obtain one comprise 75 frames level and smooth after the video image frame sequence of video frame image.

Second step: perform respectively for often pair that comprises in the video image frame sequence that obtains by performing the above-mentioned first step adjacent video frame image: calculate this global optical flow field to the specific region of video frame image respectively, and according to calculate this to the global optical flow field of the specific region of video frame image, determine this motion vector to each pixel in the specific region of the rear frame video image frame in video frame image.

Particularly, the reflection of described optical flow field be movable information between image, represent in a certain time interval due to the image change caused of moving.Be the pixel of (x, y) for the specific region internal coordinate of arbitrary video frame image, by the calculating of the global optical flow field of the specific region to this video frame image, the motion vector (v corresponding with this pixel can be determined _x, v _y).Particularly, existing LK optical flow method can be adopted to determine the global optical flow field of the specific region of this video frame image, thus the motion vector that in the specific region determining this video frame image, each pixel is corresponding.

For above-mentioned comprise 75 frames level and smooth after the video image frame sequence of video frame image, by performing this second step, the motion vector that in the specific region that can calculate other the 74 frame video image frames except the first frame in this video image frame sequence, each pixel is corresponding.

It should be noted that, the motion vector of each pixel in the specific region that this step 103 is not limited to utilize optical flow method to determine this video frame image.

3rd step: determined that each video frame image of motion vector that in specific region, each pixel is corresponding performs respectively for by performing above-mentioned second step: according to the motion vector of each pixel in the specific region of this video frame image, determine the modulus value of the motion vector of each pixel in this specific region, and according to the modulus value of described motion vector, in the specific region determining this video frame image, whether there is moving target.

Particularly, in the specific region determining this video frame image each pixel motion vector after, can determine the modulus value of the motion vector of each pixel, be the pixel of (x, y) for above-mentioned coordinate, based on the motion vector (v that this pixel is corresponding _x, v _y), the modulus value of the motion vector of this pixel can be determined

\sqrt{{v_{x}}^{2} + {v_{y}}^{2}} .

Further, in the specific region determining this video frame image the motion vector of each pixel modulus value after, can determine that the modulus value of motion vector in all pixels of the specific region of this video frame image is greater than the number of the pixel of modulus value threshold value.Now, by set a certain this video frame image of threshold decision specific region in whether there is moving target.Such as, when the number determining that the modulus value of described motion vector is greater than the pixel of modulus value threshold value is greater than the first motion number threshold value, in the specific region determining this video frame image, there is moving target; Otherwise, then there is not moving target in the specific region can determining this video frame image.

When there is moving target in the specific region determining this video frame image, the picture frame counter execution pre-set can be triggered the number of the video frame image that there is moving target in specific region is added 1.

Alternatively, by performing the second step that comprises of this step 103, in the specific region determining current video image frame each pixel motion vector after, no longer can perform the 3rd step, and perform the 4th following step.

4th step: determined that each video frame image of motion vector that in specific region, each pixel is corresponding performs respectively for by performing above-mentioned second step: according to the motion vector of each pixel in the specific region of this video frame image, the absolute value of the motion vector of each pixel in this specific region can be determined, and according to the absolute value of described motion vector, in the specific region determining this video frame image, whether there is moving target.

Particularly, in the specific region determining this video frame image each pixel motion vector after, the absolute value of the motion vector of each pixel can be determined, with above-mentioned coordinate for (x, y) pixel is example, based on the motion vector (v that this pixel is corresponding _x, v _y), can determine the motion vector of this pixel absolute value (| v _x|+| v _y|).

Further, in the specific region determining this video frame image the motion vector of each pixel absolute value after, can determine that the absolute value of motion vector in all pixels of the specific region of this video frame image is greater than the number of the pixel of absolute value threshold value.Now, by set a certain this video frame image of threshold decision specific region in whether there is moving target, such as, when the number determining that the absolute value of described motion vector is greater than the pixel of absolute value threshold value is greater than the second motion number threshold value, in the specific region determining video frame image, there is moving target; Otherwise, then there is not moving target in the specific region can determining this video frame image.

150 video frame images in obtained video image frame sequence execute second step and the 3rd step every 2 frames, or after second step and the 4th step, namely achieve in the video frame image determining the second quantity comprised at this video image frame sequence, in specific region, there is the second number of the video frame image of moving target.Such as, after moving object detection is carried out to the specific region of 75 video frame images, determine and wherein have the specific region of 55 video frame images to there is moving target, then 75 is the second quantity in the embodiment of the present invention one, and 55 is the second number in the embodiment of the present invention one.

Step 104: according to the first number of the video frame image that the gray scale by performing the gray scale of specific region determined of step 102 and the specific region of reference picture there are differences, and by performing the second number that there is the video frame image of moving target in the specific region determined of step 103, determine whether that someone enters the actual area corresponding to specific region.

Particularly, for multiple video frame images that video image frame sequence comprises, the number of the video frame image that there are differences when the gray scale of the gray scale of its specific region and the specific region of reference picture is greater than the first number threshold value, and the number that there is the video frame image of moving target in its specific region is when being greater than the second number threshold value, then define in actual area that people enters corresponding to this specific region.Such as, gray difference detection and moving object detection are carried out to the specific region of 75 video frame images in the video image frame sequence obtained, when the gray scale of the gray scale of specific region and the specific region of reference picture that define 55 video frame images there are differences, and in the specific region of 55 video frame images, detect to there is moving target, be then determined with in actual area that people enters corresponding to this specific region.

Alternatively, for multiple video frame images that video image frame sequence comprises, the number of the video frame image that there are differences when the gray scale of the gray scale of specific region and the specific region of reference picture is greater than the first number threshold value, but when there is the number of the video frame image of moving target in specific region and be not more than the second number threshold value, can by last video frame image in the video image frame sequence of the acquisition by execution step 101, as the reference picture adopted during this area monitoring method performed other video image frame sequences of follow-up acquisition in embodiment one, thus can continue to determine whether that someone enters the actual area corresponding to specific region according to the scheme of the embodiment of the present invention.

The situation of to be obtained video frame image the be gray level image that above-described embodiment one describes, below for acquisition video frame image be coloured image, embodiments of the present invention is further illustrated, but the present invention is not limited to the following examples.

Embodiment two:

As shown in Figure 4, be the step schematic diagram of area monitoring method in the embodiment of the present invention two, described method mainly comprises the following steps:

Step 201: obtain video image frame sequence.

The specific implementation of this step 201 can be: obtain the video image frame sequence that in a certain setting-up time section, video camera photographs.Particularly, described video camera can captured in real-time to personnel's situation in a certain region, such as, a video camera is installed in bank counter inside, the situation of counter window external client transacting business can be photographed.

It should be noted that, in a frame video image frame of the video image frame sequence that this step 201 obtains, a specific region (image-region at the counter window place namely photographed) may be comprised, also may comprise multiple specific region.The scheme of the embodiment of the present invention is described to comprise a specific region in video frame image, for the situation comprising multiple specific region in video frame image, each specific region in described multiple specific region all can adopt the scheme of the embodiment of the present invention to process.

Step 202: determine in the video frame image of the first quantity that this video image frame sequence comprises, the first number of the video frame image that the color of the color of specific region and the specific region of reference picture there are differences.

For convenience of description, in the embodiment of the present invention, the color of the color of specific region detected in video frame image and the specific region of reference picture be there are differences and detect referred to as heterochromia.

Based on the video image frame sequence that step 201 obtains, the video frame image of this step 202 to the first quantity that obtained video image frame sequence comprises carries out heterochromia detection, and the first number of video frame image that the color adding up the color of specific region and the specific region of reference picture there are differences.

Particularly, this step 202 can carry out heterochromia detection to each video frame image in obtained video image frame sequence, and the number of video frame image that statistic mixed-state there are differences to the color of the specific region of the color of specific region and reference picture, the first quantity namely described in the present embodiment two can be total number of the video frame image that this video image frame sequence comprises.Alternatively, be enough to the prerequisite of the color change situation of the accurate reflecting video sequence of image frames of the first number energy ensureing finally to obtain in the number of the video frame image carrying out heterochromia detection under, in order to reduce amount of calculation, heterochromia detection can be carried out by interval N frame to the video frame image in obtained sequence of image frames, wherein, N be greater than 1 positive integer, alternatively, N is the positive integer between 2 ~ 5, and the first quantity namely described in the present embodiment two can be less than total number of the video frame image that this video image frame sequence comprises.

In order to realize carrying out heterochromia detection to the video frame image of the first quantity that the video image frame sequence obtained comprises, the reference picture detecting heterochromia first can be determined.Particularly, described reference picture can for the image taken when not having personnel to enter by video camera in the actual area corresponding to specific region, wherein, position in a reference image, the specific region of reference picture is identical with the position of specific region in video frame image of video frame image.

150 video frame images are comprised below with video image frame sequence, every 2 frames, heterochromia detection is carried out to specific region, namely heterochromia is carried out to 75 video frame images in the video image frame sequence obtained and be detected as example, following detailed description is carried out to the specific implementation of this step 202.

Carrying out in the process of heterochromia detection to each video frame image in above-mentioned 75 video frame images respectively, for the current any video frame image (hereinafter current video image frame) carrying out heterochromia detection, judge that the process whether color of the color of the specific region of current video image frame and the specific region of reference picture there are differences is as follows:

Each color space component of each pixel in the specific region of current video image frame is compared to the corresponding color space component that this pixel is in the pixel of same position respectively with in the specific region of reference picture.With RGB (Red Green & Blue, RGB) color space is example, the R component of first pixel in the specific region of the R component of the pixel of first in the specific region of current video image frame and reference picture can be compared; The G component of first pixel in the G component of the pixel of first in the specific region of current video image frame and the specific region of reference picture is compared; The B component of first pixel in the B component of the pixel of first in the specific region of current video image frame and the specific region of reference picture is compared.When the difference that at least one color space component of this pixel meets the color space component corresponding to the corresponding pixel of reference picture is greater than preset difference value threshold value, then trigger the pixel counter execution pixel number pre-set and add 1, if not, then do not trigger this counter execution pixel number and add 1.For the operation performed by other pixels can the like.Each pixel in the specific region of current video image frame all completes after above-mentioned color space component difference judges, meets the number of the pixel of above-mentioned decision condition in the specific region can determining current video image frame.

When the number of the pixel meeting above-mentioned decision condition is greater than color number threshold value, can determine that the color of the color of the specific region of this video frame image and the specific region of reference picture there are differences; Otherwise, then determine that the color of the color of the specific region of this video frame image and the specific region of reference picture not there are differences.

For each video frame image comprised in the video image frame sequence of 75 video frame images obtained, said method all can be adopted to judge, and whether the color of specific region of current video image frame and the color of the specific region of reference picture there are differences, if so, then trigger the number that the picture frame that a pre-sets counter performs the video frame image that be there are differences by the color of the color of specific region and the specific region of reference picture and add 1; If not, then do not trigger this counter to carry out adding 1 operation.

Such as, after heterochromia detection is carried out to the specific region of 75 video frame images, determine and wherein have the color of the color of the specific region of 55 video frame images and the specific region of reference picture there are differences, then 75 is the first quantity in the embodiment of the present invention two, and 55 is the first number in the embodiment of the present invention two.

It should be noted that, color space component involved in this step 202 is not limited to R, G, B, also can be the color space component such as Y, U, V, or C, M, Y, K.

Step 203: determine, in the video frame image of the second quantity that this video image frame sequence comprises, to there is the second number of the video frame image of moving target in specific region.

It should be noted that, this step 203 and step 202 are independently carried out, and its execution sequence in no particular order, can carry out simultaneously.

Based on the video image frame sequence that step 201 obtains, moving object detection is carried out in the specific region of this step 203 to multiple video frame images that obtained video image frame sequence comprises, and statistics detects the second number of the video frame image of moving target in specific region.

Similar with step 202, this step 203 can carry out moving object detection to the specific region of each video frame image in obtained video image frame sequence, and statistics detects the number that there is Moving Targets Based on Video Streams picture frame in specific region, the second quantity namely described in the present embodiment two can be total number of the video frame image that this video image frame sequence comprises.Alternatively, be enough to the prerequisite of the object of which movement situation in the accurate reflecting video sequence of image frames of the second number energy ensureing finally to obtain in the number of the video frame image carrying out motion detection under, in order to reduce amount of calculation, moving object detection can be carried out by interval N frame to the specific region of the video frame image in obtained video image frame sequence, wherein, N be greater than 1 positive integer, alternatively, N is the positive integer between 2 ~ 5, and the second quantity namely described in the present embodiment two can be less than total number of the video frame image that this video image frame sequence comprises.

It should be noted that, first quantity of carrying out the video frame image of heterochromia detection in the second quantity of the video frame image of moving object detection and step 202 is carried out in this step 203, can be identical, also can be different, if the video frame image carrying out heterochromia detection in step 202. has also carried out moving object detection in step 203, then testing result is more accurate.

150 video frame images are comprised below with video image frame sequence, every 2 frames, moving object detection is carried out to the specific region of video frame image, namely carrying out moving object detection to the specific region of 75 video frame images in the video image frame sequence obtained is example, is described in detail the specific implementation of this step 203.

The first step: the video image frame sequence obtained step 201 to carry out the Gaussian smoothing of specific region every 2 frames, obtain one comprise 75 frames level and smooth after the video image frame sequence of video frame image.

It should be noted that, the motion vector of each pixel in the specific region that this step 203 is not limited to utilize optical flow method to determine this video frame image.

\sqrt{{v_{x}}^{2} + {v_{y}}^{2}} .

Alternatively, by performing the second step that comprises of this step 203, in the specific region determining current video image frame each pixel motion vector after, no longer can perform the 3rd step, and perform the 4th following step.

150 video frame images in obtained video image frame sequence execute second step and the 3rd step every 2 frames, or after second step and the 4th step, namely achieve in the video frame image determining the second quantity comprised at this video image frame sequence, in specific region, there is the second number of the video frame image of moving target.Such as, after moving object detection is carried out to the specific region of 75 video frame images, determine and wherein have the specific region of 55 video frame images to there is moving target, then 75 is the second quantity in the embodiment of the present invention two, and 55 is the second number in the embodiment of the present invention two.

Step 204: according to the first number of the video frame image that the color by performing the color of specific region determined of step 202 and the specific region of reference picture there are differences, and by performing the second number that there is the video frame image of moving target in the specific region determined of step 203, determine whether that someone enters the actual area corresponding to specific region.

Particularly, for multiple video frame images that video image frame sequence comprises, the number of the video frame image that there are differences when the color of the color of its specific region and the specific region of reference picture is greater than the first number threshold value, and the number that there is the video frame image of moving target in its specific region is when being greater than the second number threshold value, then define in actual area that people enters corresponding to this specific region.Such as, heterochromia detection and moving object detection are carried out to the specific region of 75 video frame images in the video image frame sequence obtained, when the color of the color of specific region and the specific region of reference picture that define 55 video frame images there are differences, and in the specific region of 55 video frame images, detect to there is moving target, be then determined with in actual area that people enters corresponding to this specific region.

Alternatively, for multiple video frame images that video image frame sequence comprises, the number of the video frame image that there are differences when the color of the color of specific region and the specific region of reference picture is greater than the first number threshold value, but when there is the number of the video frame image of moving target in specific region and be not more than the second number threshold value, can by by performing last video frame image in the video image frame sequence that obtains of step 201, as the reference picture adopted during this area monitoring method performed other video image frame sequences of follow-up acquisition in embodiment two, thus can continue to determine whether that someone enters the actual area corresponding to specific region according to the scheme of the embodiment of the present invention.

The scheme of the embodiment of the present invention carries out static color Difference test and dynamic motion target detection by the multiple video frame images comprised the video image frame sequence obtained, for multiple video frame images that video image frame sequence comprises, determine the number of the video frame image that the color of the color of specific region and the specific region of reference picture there are differences, and in this specific region, the number of the video frame image that there is moving target detected, and judge whether that someone enters the actual area corresponding to this specific region according to testing result, effectively can enter a certain region to personnel to monitor in real time.

Embodiment three:

The present embodiment three is the area monitoring equipment belonging to same inventive concept with embodiment one, and as shown in Figure 5, described equipment mainly comprises: obtain module 11, first determination module 12, second determination module 13 and judging module 14.

Wherein, module 11 is obtained for obtaining video image frame sequence.

Whether the first determination module 12 there are differences with the gray scale of the described specific region of reference picture for the gray scale of the same specific region by detecting each video frame image in the video frame image of the first quantity that described video image frame sequence comprises respectively, determines the first number of the video frame image that the gray scale of the gray scale of described specific region and the described specific region of described reference picture there are differences.

Second determination module 13, for whether there is moving target in the described specific region by detecting each video frame image in the video frame image of the second quantity that described video image frame sequence comprises respectively, determines the second number of the video frame image that there is moving target in described specific region.

Judging module 14, for according to described first number and the second number, judges whether that someone enters the actual area corresponding to described specific region.

Particularly, the first determination module 12 performs the first assigned operation respectively specifically for each video frame image in the video frame image for described first quantity.Wherein, described first assigned operation comprises: perform respectively for each pixel in the described specific region of this video frame image: the gray value comparing the pixel being in the same position of described specific region in the gray value of this pixel and reference picture with this pixel; According to the comparative result for described each pixel, from the described specific region of this video frame image, determine that the difference of the gray value of the pixel that gray value is corresponding to reference picture is greater than all pixels of preset difference value threshold value; When the number of described all pixels is greater than gray scale number threshold value, determine that the gray scale of the gray scale of the described specific region of this video frame image and the described specific region of described reference picture there are differences.

Particularly, the second determination module 13 performs the second assigned operation respectively specifically for each video frame image in the video frame image for described second quantity.Wherein, described second assigned operation comprises: the modulus value determining the motion vector of each pixel in the described specific region of this video frame image respectively; According to the modulus value of the motion vector of each pixel described, determine that the modulus value of motion vector in all pixels of described specific region is greater than the number of the pixel of modulus value threshold value; When the number that the modulus value of described motion vector is greater than the pixel of modulus value threshold value is greater than the first motion number threshold value, determine to there is moving target in described specific region.

Particularly, the second determination module 13 specifically also performs the 3rd assigned operation for each video frame image in the video frame image for described second quantity respectively.Wherein, described 3rd assigned operation comprises: the absolute value determining the motion vector of each pixel in the described specific region of this video frame image respectively; Wherein, the absolute value of described motion vector refers to the absolute value sum of each component in this motion vector; According to the absolute value of the motion vector of each pixel described, determine that the absolute value of motion vector in all pixels of described specific region is greater than the number of the pixel of absolute value threshold value; When the number that the absolute value of described motion vector is greater than the pixel of absolute value threshold value is greater than the second motion number threshold value, determine to there is moving target in described specific region.

It should be noted that, the description to each part major function to the description of each part of area monitoring equipment in the embodiment of the present invention three, in the embodiment of the present invention three, each part also possesses the function of the method step realized described in embodiment one, meanwhile, the area monitoring equipment in the embodiment of the present invention three also has the logic module performing each step of embodiment one.

Embodiment four:

The present embodiment four is the area monitoring equipment belonging to same inventive concept with embodiment two, and its concrete structure still with reference to shown in Fig. 5, mainly can comprise: obtain module 11, first determination module 12, second determination module 13 and judging module 14.

Wherein, module 11 is obtained for obtaining video image frame sequence.

Whether the first determination module 12 there are differences with the color of the described specific region of reference picture for the color of the same specific region by detecting each video frame image in the video frame image of the first quantity that described video image frame sequence comprises respectively, determines the first number of the video frame image that the color of the color of described specific region and the described specific region of described reference picture there are differences.

Particularly, the first determination module 12 performs the first assigned operation respectively specifically for each video frame image in the video frame image for described first quantity.Wherein, described first assigned operation comprises: perform respectively for each pixel in the described specific region of this video frame image: each color space component for this pixel performs respectively: compare the corresponding color space component being in the pixel of the same position of described specific region in this color space component of this pixel and reference picture to this pixel; According to the comparative result for described each pixel, from the described specific region of this video frame image, be determined to a rare color space component and meet all pixels being greater than preset difference value threshold value to the difference of the corresponding color space component of the corresponding pixel of reference picture; When the number of described all pixels is greater than color number threshold value, determine that the color of the color of the described specific region of this video frame image and the described specific region of described reference picture there are differences.

It should be noted that, the description to each part major function to the description of each part of area monitoring equipment in the embodiment of the present invention four, in the embodiment of the present invention four, each part also possesses the function of the method step realized described in embodiment two, meanwhile, the area monitoring equipment in the embodiment of the present invention four also has the logic module performing each step of embodiment two.

Those skilled in the art should understand, embodiments of the invention can be provided as method, system or computer program.Therefore, the present invention can adopt the form of complete hardware embodiment, completely software implementation or the embodiment in conjunction with software and hardware aspect.And the present invention can adopt in one or more form wherein including the upper computer program implemented of computer-usable storage medium (including but not limited to magnetic disc store, CD-ROM, optical memory etc.) of computer usable program code.

The present invention describes with reference to according to the flow chart of the method for the embodiment of the present invention, equipment (system) and computer program and/or block diagram.Should understand can by the combination of the flow process in each flow process in computer program instructions realization flow figure and/or block diagram and/or square frame and flow chart and/or block diagram and/or square frame.These computer program instructions can being provided to the processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device to produce a machine, making the instruction performed by the processor of computer or other programmable data processing device produce device for realizing the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.

These computer program instructions also can be stored in can in the computer-readable memory that works in a specific way of vectoring computer or other programmable data processing device, the instruction making to be stored in this computer-readable memory produces the manufacture comprising command device, and this command device realizes the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.

These computer program instructions also can be loaded in computer or other programmable data processing device, make on computer or other programmable devices, to perform sequence of operations step to produce computer implemented process, thus the instruction performed on computer or other programmable devices is provided for the step realizing the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.

Although describe the preferred embodiments of the present invention, those skilled in the art once obtain the basic creative concept of cicada, then can make other change and amendment to these embodiments.So claims are intended to be interpreted as comprising preferred embodiment and falling into all changes and the amendment of the scope of the invention.

Obviously, those skilled in the art can carry out various change and modification to the present invention and not depart from the spirit and scope of the present invention.Like this, if these amendments of the present invention and modification belong within the scope of the claims in the present invention and equivalent technologies thereof, then the present invention is also intended to comprise these change and modification.

Claims

1. an area monitoring method, is characterized in that, described method comprises:

Obtain video image frame sequence;

2. area monitoring method as claimed in claim 1, is characterized in that,

Adopt following manner, whether the gray scale detecting the same specific region of each video frame image in the video frame image of described first quantity respectively there are differences with the gray scale of the described specific region of reference picture:

Wherein, described first assigned operation comprises:

3. the area monitoring method as described in as arbitrary in claim 1 or 2, is characterized in that,

Adopt following manner, in the described specific region detecting each video frame image in the video frame image of described second quantity respectively, whether there is moving target:

Wherein, described second assigned operation comprises:

4. the area monitoring method as described in as arbitrary in claim 1 or 2, is characterized in that,

Wherein, described 3rd assigned operation comprises:

5. an area monitoring method, is characterized in that, described method comprises:

Obtain video image frame sequence;

6. area monitoring method as claimed in claim 5, is characterized in that,

Adopt following manner, whether the color detecting the same specific region of each video frame image in the video frame image of described first quantity respectively there are differences with the color of the described specific region of reference picture:

Wherein, described first assigned operation comprises:

7. the area monitoring method as described in as arbitrary in claim 5 or 6, is characterized in that,

Wherein, described second assigned operation comprises:

8. the area monitoring method as described in as arbitrary in claim 5 or 6, is characterized in that,

Wherein, described 3rd assigned operation comprises:

9. an area monitoring equipment, is characterized in that, described equipment comprises:

Obtain module, for obtaining video image frame sequence;

10. area monitoring equipment as claimed in claim 9, is characterized in that,

Described first determination module, performs the first assigned operation respectively specifically for each video frame image in the video frame image for described first quantity;

Wherein, described first assigned operation comprises:

11. as arbitrary in claim 9 or 10 as described in area monitoring equipment, it is characterized in that,

Described second determination module, performs the second assigned operation respectively specifically for each video frame image in the video frame image for described second quantity;

Wherein, described second assigned operation comprises:

12. as arbitrary in claim 9 or 10 as described in area monitoring equipment, it is characterized in that,

Described second determination module, performs the 3rd assigned operation respectively specifically for each video frame image in the video frame image for described second quantity;

Wherein, described 3rd assigned operation comprises:

13. 1 kinds of area monitoring equipment, is characterized in that, described equipment comprises:

Obtain module, for obtaining video image frame sequence;

14. area monitoring equipment as claimed in claim 13, is characterized in that,

Wherein, described first assigned operation comprises:

15. as arbitrary in claim 13 or 14 as described in area monitoring equipment, it is characterized in that,

Wherein, described second assigned operation comprises:

16. as arbitrary in claim 13 or 14 as described in area monitoring equipment, it is characterized in that,

Wherein, described 3rd assigned operation comprises: