CN109919126A - A kind of mobile object detection method, device and storage medium - Google Patents
A kind of mobile object detection method, device and storage medium Download PDFInfo
- Publication number
- CN109919126A CN109919126A CN201910209887.8A CN201910209887A CN109919126A CN 109919126 A CN109919126 A CN 109919126A CN 201910209887 A CN201910209887 A CN 201910209887A CN 109919126 A CN109919126 A CN 109919126A
- Authority
- CN
- China
- Prior art keywords
- velocity vector
- vector
- pixel
- characteristic point
- image 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.)
- Granted
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
Present disclose provides a kind of mobile object detection method, device and storage mediums.Wherein, this method comprises: obtaining the picture frame of target vehicle surrounding scenes；According to the pixel value of adjacent described image frame, the corresponding velocity vector of at least one characteristic point of described image frame is determined；The sequencing queue that velocity vector is determined according to the velocity vector determines the mobile object around the target vehicle according to the comparison of head and the tail vector in the sequencing queue.Using the embodiment of the present disclosure, the mobile object around target vehicle can easy, be accurately detected.
Description
Technical field
This disclosure relates to information technology field more particularly to a kind of mobile object detection method, device and storage medium.
Background technique
With the development of economy, people's lives level is continuously improved, and the diversified vehicles are that the trip of people mentions
For convenience.In a variety of vehicles, since its is convenient and efficient, the average volume of holding increases automobile year by year, is increasingly becoming people's
Main means of transport.
While automobile quantity increases, Frequent Accidents on road seriously affect daily life and out line efficiency,
Even endanger the life security of people.Therefore, Exploration on Train Operation Safety gradually becomes focus concerned by people.How to motor vehicle environment
Mobile object carry out detection become the current technical issues that need to address.
Summary of the invention
In view of this, the present disclosure proposes a kind of mobile object detection method, device and storage medium, with easy, accurate
Ground detects the mobile object around target vehicle.
According to the one side of the disclosure, a kind of mobile object detection method is provided, comprising:
Obtain the picture frame of target vehicle surrounding scenes；
According to the pixel value of adjacent described image frame, determine the corresponding speed of at least one characteristic point of described image frame to
Amount；
The sequencing queue that velocity vector is determined according to the velocity vector, according to the ratio of head and the tail vector in the sequencing queue
Relatively determine the mobile object around the target vehicle.
In one possible implementation, the picture frame for obtaining target vehicle surrounding scenes, comprising:
Obtain the first picture frame that photographic device is acquired with the first projection pattern；
If first projection pattern is different from default projection pattern, by the first image frame according to default projection pattern
Transformation, obtains the second picture frame.
In one possible implementation, the pixel value according to adjacent described image frame, determines described image frame
The corresponding velocity vector of at least one characteristic point, comprising:
According to the pixel value of the pixel of adjacent described image frame, at least one characteristic point is determined in the pixel；
According to the pixel coordinate of the characteristic point of adjacent described image frame, determine the corresponding speed of the characteristic point to
Amount.
In one possible implementation, the pixel coordinate of the characteristic point according to adjacent described image frame,
Determine the corresponding velocity vector of the characteristic point, comprising:
Obtain pixel coordinate and the brightness of corresponding first pixel of characteristic point in adjacent described image frame；
According to the pixel coordinate of first pixel, obtains the first pixel described in distance in adjacent image frame and preset picture
Second pixel of vegetarian refreshments distance；
According to the brightness of first pixel and the brightness of the second pixel determine the corresponding speed of the characteristic point to
Amount.
In one possible implementation, the sequencing queue of velocity vector is determined according to the velocity vector, comprising:
Described image frame is divided at least one image-region；
The velocity vector for obtaining characteristic point in each image-region, according at least one corresponding vector of the velocity vector
Parameter is ranked up the velocity vector, obtains ranking results；
According to the ranking results, the sequencing queue of the velocity vector corresponding to each image-region is determined.
In one possible implementation, the velocity vector for obtaining characteristic point in each image-region, according to institute
It states at least one corresponding vector parameter of velocity vector to be ranked up the velocity vector, obtains ranking results, comprising:
The parameter value of vector parameter is obtained according to the velocity vector of the fisrt feature point in each image-region；
According to the parameter value of the vector parameter, the speed of the fisrt feature point is determined in velocity vector sorted lists
The insertion position of vector, wherein the velocity vector sorted lists are stored with before the velocity vector of the fisrt feature point
The velocity vector of the second feature point of insertion；
The velocity vector of the fisrt feature point is inserted into the insertion position in the velocity vector sorted lists, is obtained
To ranking results.
In one possible implementation, the vector parameter includes: mould length, deflection.
In one possible implementation, the target carriage is determined according to the comparison of head and the tail vector in the sequencing queue
Mobile object around, comprising:
Determine the first vector sum tail vector in the sequencing queue of velocity vector corresponding to each image-region；
The case where difference of the parameter value of vector parameter between the tail vector described in the first vector sum is greater than parameter threshold
Under, determine that there are mobile objects around the target vehicle.
According to another aspect of the present disclosure, a kind of mobile object detection device is provided, comprising:
Module is obtained, for obtaining the picture frame of target vehicle surrounding scenes；
First determining module determines at least one of described image frame for the pixel value according to adjacent described image frame
The corresponding velocity vector of characteristic point；
Second determining module, for determining the sequencing queue of velocity vector according to the velocity vector, according to the sequence
The comparison of head and the tail vector determines the mobile object around the target vehicle in queue.
In one possible implementation, the acquisition module includes:
First acquisition submodule, the first picture frame acquired for obtaining photographic device with the first projection pattern；
Transformation submodule, if different from default projection pattern for first projection pattern, by the first image frame
It is converted according to default projection pattern, obtains the second picture frame.
In one possible implementation, first determining module includes:
First determines submodule, for the pixel value according to the pixel of adjacent described image frame, in the pixel
Determine at least one characteristic point；
Second determines submodule, for the pixel coordinate according to the characteristic point of adjacent described image frame, determine described in
The corresponding velocity vector of characteristic point.
In one possible implementation, described second determine that submodule includes:
First acquisition unit, for obtain corresponding first pixel of characteristic point in adjacent described image frame pixel coordinate and
Brightness；
Second acquisition unit obtains distance institute in adjacent image frame for the pixel coordinate according to first pixel
State the second pixel of the first pixel presetted pixel point distance；
Determination unit, for determining the characteristic point according to the brightness of first pixel and the brightness of the second pixel
Corresponding velocity vector.
In one possible implementation, second determining module includes:
Submodule is divided, for described image frame to be divided at least one image-region；
Sorting sub-module, for obtaining the velocity vector of characteristic point in each image-region, according to the velocity vector pair
At least one vector parameter answered is ranked up the velocity vector, obtains ranking results；
Third determines submodule, for determining the speed corresponding to each image-region according to the ranking results
The sequencing queue of vector.
In one possible implementation, the sorting sub-module includes:
Parameter value acquiring unit, for obtaining vector ginseng according to the velocity vector of the fisrt feature point in each image-region
Several parameter values；
Position determination unit determines institute for the parameter value according to the vector parameter in velocity vector sorted lists
State the insertion position of the velocity vector of fisrt feature point, wherein the velocity vector sorted lists are stored with special described first
Levy the velocity vector for the second feature point being inserted into before the velocity vector of point；
It is inserted into unit, the institute for being inserted into the velocity vector of the fisrt feature point in the velocity vector sorted lists
Insertion position is stated, ranking results are obtained.
In one possible implementation, the vector parameter includes: mould length, deflection.
In one possible implementation, second determining module of the second determining module further include:
Vector determination unit, the first vector sum in sequencing queue for determining velocity vector corresponding to each image-region
Tail vector；
Mobile object determination unit, for the vector parameter between the tail vector described in the first vector sum parameter value it
In the case that difference is greater than parameter threshold, determine that there are mobile objects around the target vehicle.
According to another aspect of the present disclosure, a kind of mobile object detection device is provided, comprising: processor；For storing
The memory of processor-executable instruction；Wherein, the processor is configured to executing the above method.
According to another aspect of the present disclosure, a kind of non-volatile computer readable storage medium storing program for executing is provided, is stored thereon with
Computer program instructions, wherein the computer program instructions realize the above method when being executed by processor.
The embodiment of the present disclosure, can be according to the picture of adjacent picture frame by the picture frame of acquisition target vehicle surrounding scenes
Element value, determines the corresponding velocity vector of at least one characteristic point of picture frame, the sequence of velocity vector is determined according to velocity vector
Queue, so as to determine the mobile object around target vehicle according to the comparison of head and the tail vector in sequencing queue.The disclosure is real
Apply example offer mobile object detecting strategy can it is easy, accurately detect existing mobile object around target vehicle, for example,
The mobile object within the scope of user blind area can be detected, driving convenience is provided to drive the user of target vehicle, reduces traffic thing
Therefore generation.
According to below with reference to the accompanying drawings to detailed description of illustrative embodiments, the other feature and aspect of the disclosure will become
It is clear.
Detailed description of the invention
Comprising in the description and constituting the attached drawing of part of specification and specification together illustrates the disclosure
Exemplary embodiment, feature and aspect, and for explaining the principles of this disclosure.
Fig. 1 shows a kind of flow chart of mobile object detection method according to one embodiment of the disclosure.
Fig. 2 shows the flow charts according to the determination characteristic point corresponding velocity vector process of one embodiment of the disclosure.
Fig. 3 shows the block diagram of the gaussian pyramid according to one embodiment of the disclosure.
Fig. 4 shows the flow chart of the sequencing queue process of the determination velocity vector according to one embodiment of the disclosure.
Fig. 5 shows a kind of block diagram of mobile object detection device according to one embodiment of the disclosure.
Fig. 6 shows a kind of structure chart of mobile object detection device according to one embodiment of the disclosure.
Specific embodiment
Various exemplary embodiments, feature and the aspect of the disclosure are described in detail below with reference to attached drawing.It is identical in attached drawing
Appended drawing reference indicate element functionally identical or similar.Although the various aspects of embodiment are shown in the attached drawings, remove
It non-specifically points out, it is not necessary to attached drawing drawn to scale.
Dedicated word " exemplary " means " being used as example, embodiment or illustrative " herein.Here as " exemplary "
Illustrated any embodiment should not necessarily be construed as preferred or advantageous over other embodiments.
In addition, giving numerous details in specific embodiment below to better illustrate the disclosure.
It will be appreciated by those skilled in the art that without certain details, the disclosure equally be can be implemented.In some instances, for
Method, means, element and circuit well known to those skilled in the art are not described in detail, in order to highlight the purport of the disclosure.
The mobile object detecting strategy that the embodiment of the present disclosure provides, the picture frame of available target vehicle surrounding scenes,
And according to the pixel value of adjacent picture frame, determines at least one characteristic point of picture frame and determine speed corresponding to characteristic point
Spend vector.By the pixel value of picture frame, can quickly recognize the characteristic point in picture frame, reduce picture frame processing when
Between.It is then possible to which the velocity vector according to corresponding to determining characteristic point determines the sequencing queue of velocity vector, and according to sequence
The comparison of head and the tail vector determines the mobile object around target vehicle in queue, in this way, can be to the movement around target vehicle
Object, which is made, quickly and accurately to be judged, implementation is simple, is provided effective reference for the safe driving of user, is reduced traffic thing
Therefore generation.
The mobile object detecting strategy that the embodiment of the present disclosure provides can be applied to any need and visit to mobile object
The scene of survey, for example, being applied to mobile object detection device, safety driving system of vehicle etc..The disclosure is not to answering specifically
It is limited with scene, the specific example that any mobile object detecting strategy provided using the disclosure is realized, in the disclosure
Protection scope in.
In the following, the mobile object detecting strategy provided in conjunction with specific embodiments the disclosure is described in detail.
Fig. 1 shows the flow chart of the mobile object detection method according to one embodiment of the disclosure.This method can be applied to
Terminal device, for example, can be applied to car-mounted terminal, mobile object detection (MOD, Moving Object Detection) set
It is standby, also can be applied to the network equipment, such as can be applied to safe driving platform etc..As shown in Figure 1, the mobile object detects
Method includes:
Step 11, the picture frame of target vehicle surrounding scenes is obtained.
In the present embodiment, Image Acquisition can be carried out to target vehicle surrounding scenes by photographic device, and then obtained
The picture frame of target vehicle surrounding scenes.For example, multiple photographic devices can be set on the vehicle body of target vehicle, photographic device can
To be shot in real time to target vehicle surrounding scenes.Car-mounted terminal can be set in target vehicle, obtain camera shooting dress in real time
Set the picture frame of the target vehicle surrounding scenes of transmitting.
In one possible implementation, the picture frame of target vehicle surrounding scenes may include the first picture frame and
Two picture frames.For car-mounted terminal when obtaining the picture frame of target vehicle surrounding scenes, available photographic device is with the first projection
The first picture frame that mode acquires can be by the first picture frame according to pre- if the first projection pattern is different from default projection pattern
If projection pattern converts, the second picture frame is obtained.For example, photographic device can be acquired by the first projection pattern of fish eye images
First picture frame, the first picture frame of acquisition are fish eye images frames.If car-mounted terminal judges the first projection pattern of photographic device
It is different from default projection pattern, when obtaining the first picture frame, the first picture frame can be converted to the of default projection pattern
Two picture frames.Here default projection pattern can be linear projection mode.
Here, when the first picture frame for acquiring the first projection pattern is transformed to two picture frame of default projection pattern,
Due to projection pattern difference, some objects in the first picture frame may be distorted after transformation, thus these objects
It can also be identified.For example, fish eye images are by after projective transformation, the higher buildings body possibility such as tree therein, railing
It can be distorted, and then can identify higher object in image.
Step 12, according to the pixel value of adjacent described image frame, at least one characteristic point pair of described image frame is determined
The velocity vector answered.
It in the present embodiment, can be according to adjacent image frame after the picture frame for obtaining target vehicle surrounding scenes
The pixel value of pixel determines at least one characteristic point, then according to the pixel of the characteristic point of adjacent image frame in pixel
Coordinate determines the corresponding velocity vector of characteristic point.Here, each characteristic point can have a velocity vector.
In one possible implementation, in the pixel value according to the pixel of adjacent image frame, in pixel really
When at least one fixed characteristic point, pixel value and detection a little then can will test using any pixel point as test point
The pixel value of point surrounding pixel point compares, and obtains comparing result.Then whether test point can be determined according to comparing result
It is characterized a little.For example, if the pixel value of test point is all larger than than the pixel value of the surrounding pixel point of continuous number or respectively less than picture
Plain threshold value can then determine that test point is characteristic point.Otherwise, test point is not characteristic point.
In one possible implementation, in the pixel coordinate according to the characteristic point of adjacent picture frame, feature is determined
It, can be according to the same characteristic point pixel coordinate in adjacent picture frame respectively, Yi Jixiang when the corresponding velocity vector of point
Acquisition time between adjacent picture frame determines the corresponding velocity vector of characteristic point.For example, if characteristic point A is in t image frame
Pixel coordinate be (x1, y1), be (x2, y2) in the pixel coordinate of t+1 picture frame, then characteristic point A velocity vector (u,
V)=(x2, y2)-(x1, y1).
Step 13, the sequencing queue that velocity vector is determined according to the velocity vector, according to head and the tail in the sequencing queue
The comparison of vector determines the mobile object around the target vehicle.
It in the present embodiment, can be according to picture frame after the velocity vector corresponding to the characteristic point for determining picture frame
Characteristic point velocity vector vector parameter, velocity vector is ranked up, sequencing queue is obtained, then will be in sequencing queue
First vector sum tail vector be compared, and the mobile object around target vehicle is determined according to the comparison result after comparison.
In one possible implementation, it when determining the sequencing queue of velocity vector according to velocity vector, can incite somebody to action
Picture frame is divided at least one image-region, the velocity vector of characteristic point in each image-region is then obtained, according to speed
At least one corresponding vector parameter of vector is ranked up velocity vector, obtains ranking results, further according to ranking results, determines
The sequencing queue of velocity vector corresponding to each image-region.Here, picture frame is being divided at least one image-region
When, each picture frame can be divided into multiple images region according to preset image graph area size.In this way, each image
Region can have the sequencing queue of corresponding velocity vector, may thereby determine that the image-region there are mobile object.Image
Area size can be rationally arranged according to application scenarios, if too small, each image of image area size setting
The characteristic point for including in region is very few, unfavorable to be compared with the velocity vector of characteristic point, if image area size setting
It is excessive, then being difficult to judge the picture position where mobile object.Therefore, the suitable setting of image area size, can be improved
The efficiency of mobile object detection.
In one possible implementation, it is determined around target vehicle according to the comparison of head and the tail vector in sequencing queue
Mobile object when, can first determine first vector sum tail in the sequencing queue of velocity vector corresponding to each image-region to
Amount, then can compare first vector and tail vector, the parameter value of the vector parameter between first vector sum tail vector it
It in the case that difference is greater than parameter threshold, can determine that there are mobile objects in image-region, i.e., there is movement around target vehicle
Object.If the case where difference of the parameter value of the vector parameter between first vector sum tail vector is less than or equal to parameter threshold
Under, it can determine that there is no mobile objects in image-region.
Here, the vector parameter of velocity vector may include mould length and deflection.Corresponding at least according to velocity vector
When one vector parameter is ranked up velocity vector, it can choose mould length or deflection be ranked up velocity vector, also
Velocity vector can be ranked up with deflection according to mould is long respectively.If respectively according to mould length and deflection to velocity vector
It is ranked up, then each image-region can be corresponded to the long sequencing queue being ranked up of mould and is ranked up with deflection
Sequencing queue, then can be according to first in the comparison of head and the tail vector in the long sequencing queue of mould and the sequencing queue of deflection
The comparison of tail vector, the common mobile object determined in image-region.For example, first in the long sequencing queue being ranked up of mould
The long difference of tail vector field homoemorphism is greater than the long threshold value of mould, also, the head and the tail vector field homoemorphism in the sequencing queue being ranked up with deflection
Long difference is greater than deflection threshold value, can determine that there are mobile objects in image-region.This mode can reduce image-region
In mobile object misjudgment, improve mobile object detection accuracy.
By above-mentioned mobile object detection method, at least one characteristic point of the picture frame of acquisition can be determined, and according to
Velocity vector corresponding to characteristic point determines the sequencing queue of velocity vector, is determined according to the comparison of head and the tail vector in sequencing queue
Mobile object around target vehicle quickly and accurately judges in this way, can make to the mobile object around target vehicle,
Implementation is simple, provides effective reference for the safe driving of user, reduces traffic accident.
In above-mentioned steps 12, at least one characteristic point of picture frame can be determined according to the pixel value of adjacent image frame
Corresponding velocity vector, so as to determine the mobile object in picture frame according to velocity vector.In the following, combining a kind of possible
Implementation is illustrated the corresponding velocity vector of at least one characteristic point for determining picture frame.
Fig. 2 shows according to the corresponding velocity vector process of the determination picture frame of one embodiment of the disclosure at least one characteristic point
Flow chart, comprising:
Step 121, according to the pixel value of the pixel of adjacent described image frame, at least one is determined in the pixel
Characteristic point.
Here, car-mounted terminal can judge whether test point p is special using any pixel point in picture frame as test point p
Sign point.For test point p, the pixel apart from test point p presetted pixel point distance can be first determined, then obtain pixel
Pixel value can determine a circle for example, radius is 3 pixel distances using test point p as the center of circle, then determine on circle
16 pixels.Then the pixel value img [p] and the pixel value img [i] of the pixel determined that point p can be will test are compared
Compared with judging that the difference of the pixel value in determining pixel with the presence or absence of continuous N number of pixel i and test point p is all larger than or small
In pixel threshold threshold, i.e., whether meet following pixel condition:
Img [i]<img [ p ] -threshold,or,img [ i ]>img [p]+threshold.Wherein, img [i] is picture
The pixel value of vegetarian refreshments i, i are the positive integer less than or equal to N, and N is positive integer.
For example, whether there is 10 pixel x of arbitrary continuation in above-mentioned 16 pixels, meet the Rule of judgment.
If it exists, then test point p is characteristic point.Otherwise, test point p is not characteristic point.
In one possible implementation, at least one characteristic point for determining picture frame, judging that test point p is full
After sufficient pixel condition, it can also further judge whether test point p meets rejection condition, if test point p, which also meets, inhibits item
Part can then determine that test point p is characteristic point, and otherwise, test point p is not characteristic point.Here it is possible to which pixel condition will be met
Test point is known as candidate feature point, and correspondingly, rejection condition can be candidate special in the presetted pixel surface area of picture frame
The maximum score for levying point is maximum, wherein maximum score can be according to the picture apart from candidate feature point presetted pixel point distance
The difference of the pixel value of vegetarian refreshments and candidate feature point is calculated.For example, can be determined in 3 × 3 presetted pixel surface area
Meet the candidate feature point of pixel condition, then can be directed to any candidate feature point, determine apart from 3 pixels of candidate feature point
16 pixels of point distance, then calculate separately the difference of the pixel value of candidate feature point and 16 pixels, then will obtain
16 pixel values difference seek absolute value after sum, obtain the maximum score of candidate feature point, and maximum score is maximum
Characteristic point of the candidate feature point as picture frame.
Step 122, according to the pixel coordinate of the characteristic point of adjacent described image frame, determine that the characteristic point is corresponding
Velocity vector.
In one possible implementation, when determining the corresponding velocity vector of characteristic point, available adjacent image
The pixel coordinate of corresponding first pixel of characteristic point and brightness, then can obtain according to the pixel coordinate of the first pixel in frame
The second pixel for taking the first pixel of distance presetted pixel point distance in adjacent image frame, further according to the brightness of the first pixel
The corresponding velocity vector of characteristic point is determined with the brightness of the second pixel.
For example, the pixel coordinate of corresponding first pixel of characteristic point in picture frame is (x, y), if expanding to three
Dimension space, the pixel coordinate of the first pixel are (x, y, z).If the brightness of the first pixel in the t image frame that the time is t
For I (x, y, z, t), the brightness of the first pixel is I (x+ δ x, y+ δ y, z+ δ z, t+ in the t+1 picture frame that the time is t+ δ t
δ t), wherein I (x+ δ x, y+ δ y, z+ δ z, t+ δ t) meets following formula:
Wherein, H.O.T. is partial derivative of higher order, can be ignored in the case where the movement of the first picture frame is sufficiently small.Due to
Brightness of first pixel in adjacent image frame may be considered it is constant, then it is considered that: I (x, y, z, t)=I (x+ δ
X, y+ δ y, z+ δ z, t+ δ t).And then it can wait to obtain:
It is available by above-mentioned equation transform:
Wherein, Vx,Vy,VzX, y, z in I (x, y, z, t) can be respectively indicated
Optical flow components.
Assuming that light stream (Vx, Vy, Vz) is a constant in the pixel window that size is m*m*m (m > 1), then according to pixel
Point 1 to pixel n, available following one group of equation:
Wherein, n=m*m*m, IxnIn the x direction for pixel n
Luminance component, IynFor the luminance component of pixel n in y-direction, IznFor the luminance component of pixel n in a z-direction.
Above-mentioned equation group can indicate are as follows:
It can be denoted as:According to least square method:And then it can obtain
To the velocity vector of characteristic point
In addition, if characteristic point is in the biggish situation of relative displacement of the first picture frame and the second picture frame, Ke Yijian
Vertical gaussian pyramid.Gaussian pyramid may include multilayer, and top layer can indicate that the first picture frame, bottom can indicate the second figure
As frame.Then, since the location of pixels the top layer of gaussian pyramid in estimation next image frame where characteristic point, and will be each
Initial pixel locations of the location of pixels of characteristic point as next layer of characteristic point, downward along each layer of gaussian pyramid in layer
Search, until reaching pyramidal bottom.Fig. 3 shows a kind of block diagram of gaussian pyramid, and gaussian pyramid may include 3
Layer, h1 can indicate the velocity vector of characteristic point in first layer and second layer corresponding image frame, h2 can indicate the second layer with
The velocity vector of characteristic point in third layer corresponding image frame.
In above-mentioned steps 13, the sequencing queue of velocity vector can be determined, according to velocity vector so as to according to row
The comparison of head and the tail vector determines the mobile object in picture frame in sequence queue.In the following, in conjunction with a kind of possible implementation to true
The process for determining the sequencing queue of velocity vector is illustrated.
Fig. 4 shows the flow chart of the sequencing queue process of the determination velocity vector according to one embodiment of the disclosure, comprising:
Step 131, described image frame is divided at least one image-region.
It here, can be according to preset image graph region when determining the sequencing queue of velocity vector according to velocity vector
Each picture frame is divided into multiple images region by size.In this way, each image-region can have corresponding velocity vector
Sequencing queue may thereby determine that the image-region there are mobile object.
Step 132, vector parameter is obtained according to the velocity vector of the fisrt feature point in each image-region.
In one possible implementation, in any vector parameter according to velocity vector to the velocity vector of characteristic point
When being ranked up, can be realized by way of the velocity vector insertion speed vector order list by each characteristic point speed to
The sequence of amount.It may include fisrt feature point and second feature point in image-region, wherein the velocity vector of fisrt feature point can
Think the velocity vector being currently ranked up, the velocity vector of second feature point can be in velocity vector sequence class table according to
The velocity vector that sequence is arranged.It, can be first according to the first spy when the velocity vector for fisrt feature point is ranked up
The velocity vector of sign point obtains the parameter value of vector parameter.Here, the vector parameter of velocity vector may include mould length and direction
Angle.
Step 133, according to the parameter value of the vector parameter, the fisrt feature is determined in velocity vector sorted lists
The insertion position of the velocity vector of point, wherein the velocity vector sorted lists are stored with the speed in the fisrt feature point
The velocity vector for the second feature point being inserted into before vector.
Here, after obtaining the parameter value of velocity vector of fisrt feature point, can according to the parameter value of velocity vector,
In the velocity vector sorted lists being ranked up with corresponding vector parameter, the insertion of the velocity vector of fisrt feature point is determined
Position.It can store the second feature point being inserted into before the velocity vector of fisrt feature point in velocity vector sorted lists
The velocity vector of velocity vector, second feature point can carry out from large to small or from small to large according to the parameter value of vector parameter
Arrangement.For example, the velocity vector of second feature point can be according to mould is long or the size relation of deflection is ranked up.In determination
When the insertion position of the velocity vector of fisrt feature point, the velocity vector of fisrt feature point can be determined by the sortord that reduces by half
Insertion position.For example, if the ascending progress of parameter value of the velocity vector in velocity vector sorted lists with vector parameter
Sequence, the first vector sum tail vector of velocity vector sorted lists can be expressed as v [low] and v [high], then can be by the first spy
The parameter value for levying the reference vector v [m] in middle position in the parameter value and velocity vector sorted lists of the velocity vector of point carries out
Comparison, if the velocity vector of fisrt feature point is smaller than the parameter value of reference vector v [m], it is determined that the speed of fisrt feature point to
The insertion position of amount arrives the position section of v [m-1] at velocity vector v [low], otherwise, it determines the velocity vector of fisrt feature point
Insertion position velocity vector v [m+1] arrive v [high] position section.
Then the first vector sum tail vector of the determining band of position can be expressed as v [low] and v [high], by position
The reference vector in the middle position in section is expressed as v [m], then can be by the parameter value of the velocity vector of fisrt feature point and speed
The parameter value of degree vector v [m] compares, and redefines the position section of fisrt feature point insertion position, is repeated with this, until
The parameter value of v [low] is greater than the parameter value of v [high], then the insertion position of the velocity vector of fisrt feature point is determined as speed
Spend the storage location where vector v [high+1].
Step 134, the velocity vector of the fisrt feature point is inserted into described slotting in the velocity vector sorted lists
Enter position, obtains ranking results.
It here, can be by the speed of fisrt feature point after determining the insertion position of velocity vector of fisrt feature point
The insertion position determined in vector insertion speed vector order list.And by the speed of insertion position in velocity vector sorted lists
Velocity vector after vector and insertion position moves backward a storage unit.Characteristic point in image-region is being inserted
After entering in velocity vector sorted lists, feature can be determined according to the arrangement position of velocity vector in velocity vector sorted lists
The ranking results of point.
By way of above-mentioned determining velocity vector sequencing queue, can rapidly the velocity vector to multiple characteristic points into
Row sequence is realized fast so as to improve the speed that the sequencing queue using vector determines the mobile object around target vehicle
Mobile object around speed detection target vehicle.
According to the above-mentioned explanation to mobile object detection method, Fig. 5 shows a kind of movement of embodiment of the present disclosure offer
The block diagram of object detection device 50.The device 50 of the present embodiment can be used for realizing the behaviour of each step in mobile object detection method
Make, various specific examples and its advantages can be found in the above-mentioned explanation to mobile object detection method, for simplicity here
It is not repeated to describe.
As shown in figure 5, the mobile object detection device 50 that the embodiment of the present disclosure provides includes: to obtain module 51, for obtaining
Take the picture frame of target vehicle surrounding scenes；First determining module 52 is determined for the pixel value according to adjacent described image frame
The corresponding velocity vector of at least one characteristic point of described image frame；Second determining module 53, for according to the velocity vector
The sequencing queue for determining velocity vector determines around the target vehicle according to the comparison of head and the tail vector in the sequencing queue
Mobile object.
In one example, the acquisition module 51 includes: the first acquisition submodule, for obtaining photographic device with first
First picture frame of projection pattern acquisition；Transformation submodule, if different from default projection pattern for first projection pattern,
The first image frame is converted according to default projection pattern, obtains the second picture frame.
In one example, first determining module 52 includes that first determines submodule, for according to the adjacent figure
As the pixel value of the pixel of frame, at least one characteristic point is determined in the pixel；Second determines submodule, is used for basis
The pixel coordinate of the characteristic point of adjacent described image frame determines the corresponding velocity vector of the characteristic point.
In one example, described second determine that submodule includes: first acquisition unit, for obtaining adjacent described image
The pixel coordinate of corresponding first pixel of characteristic point and brightness in frame；Second acquisition unit, for according to first pixel
Pixel coordinate, obtain the second pixel of the first pixel presetted pixel point distance described in distance in adjacent image frame；It determines
Unit, for according to the brightness of first pixel and the brightness of the second pixel determine the corresponding speed of the characteristic point to
Amount.
In one example, second determining module 53 includes: division submodule, for described image frame to be divided into
At least one image-region；Sorting sub-module, for obtaining the velocity vector of characteristic point in each image-region, according to the speed
At least one corresponding vector parameter of degree vector is ranked up the velocity vector, obtains ranking results；Third determines submodule
Block, for determining the sequencing queue of the velocity vector corresponding to each image-region according to the ranking results.
In one example, the sorting sub-module includes: parameter value acquiring unit, for according in each image-region
The velocity vector of fisrt feature point obtain the parameter value of vector parameter；Position determination unit, for according to the vector parameter
Parameter value, the insertion position of the velocity vector of the fisrt feature point is determined in velocity vector sorted lists, wherein described
Velocity vector sorted lists be stored with the speed of the second feature point being inserted into before the velocity vector of the fisrt feature point to
Amount；It is inserted into unit, it is described slotting in the velocity vector sorted lists for the velocity vector of the fisrt feature point to be inserted into
Enter position, obtains ranking results.
In one example, the vector parameter includes: mould length, deflection.
In one example, second determining module 53 further include: vector determination unit, for determining each image district
First vector sum tail vector in the sequencing queue of velocity vector corresponding to domain；Mobile object determination unit, for it is described it is first to
In the case that the difference of the parameter value of vector parameter between amount and the tail vector is greater than parameter threshold, the target vehicle is determined
There are mobile objects for surrounding.
Above-mentioned mobile object detection device, can be by the picture frame of acquisition target vehicle surrounding scenes, can be according to phase
The pixel value of adjacent picture frame, determines the corresponding velocity vector of at least one characteristic point of picture frame, is determined according to velocity vector
The sequencing queue of velocity vector, so as to determine the movement around target vehicle according to the comparison of head and the tail vector in sequencing queue
Object provides driving convenience to drive the user of target vehicle, reduces traffic accident.
Fig. 6 is a kind of block diagram of device 600 for detecting mobile object shown according to an exemplary embodiment.Example
Such as, device 600 can be car-mounted terminal, mobile phone, computer, digital broadcasting terminal, messaging device, game control
Platform, tablet device, Medical Devices, body-building equipment, personal digital assistant etc..
Referring to Fig. 6, device 600 may include following one or more components: processing component 602, memory 604, power supply
Component 606, multimedia component 608, audio component 610, the interface 612 of input/output (I/O), sensor module 614, and
Communication component 616.
The integrated operation of the usual control device 600 of processing component 602, such as with display, telephone call, data communication, phase
Machine operation and record operate associated operation.Processing component 602 may include that one or more processors 620 refer to execute
It enables, to perform all or part of the steps of the methods described above.In addition, processing component 602 may include one or more modules, just
Interaction between processing component 602 and other assemblies.For example, processing component 602 may include multi-media module, it is more to facilitate
Interaction between media component 608 and processing component 602.
Memory 604 is configured as storing various types of data to support the operation in device 600.These data are shown
Example includes the instruction of any application or method for operating on device 600, contact data, and telephone book data disappears
Breath, picture, video etc..Memory 604 can be by any kind of volatibility or non-volatile memory device or their group
It closes and realizes, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable to compile
Journey read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash
Device, disk or CD.
Power supply module 606 provides electric power for the various assemblies of device 600.Power supply module 606 may include power management system
System, one or more power supplys and other with for device 600 generate, manage, and distribute the associated component of electric power.
Multimedia component 608 includes the screen of one output interface of offer between described device 600 and user.One
In a little embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen
Curtain may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touch sensings
Device is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding action
Boundary, but also detect duration and pressure associated with the touch or slide operation.In some embodiments, more matchmakers
Body component 608 includes a front camera and/or rear camera.When device 600 is in operation mode, such as screening-mode or
When video mode, front camera and/or rear camera can receive external multi-medium data.Each front camera and
Rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 610 is configured as output and/or input audio signal.For example, audio component 610 includes a Mike
Wind (MIC), when device 600 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone is matched
It is set to reception external audio signal.The received audio signal can be further stored in memory 604 or via communication set
Part 616 is sent.In some embodiments, audio component 610 further includes a loudspeaker, is used for output audio signal.
I/O interface 612 provides interface between processing component 602 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock
Determine button.
Sensor module 614 includes one or more sensors, and the state for providing various aspects for device 600 is commented
Estimate.For example, sensor module 614 can detecte the state that opens/closes of device 600, and the relative positioning of component, for example, it is described
Component is the display and keypad of device 600, and sensor module 614 can be with detection device 600 or a group of device 600
The position change of part, the existence or non-existence that user contacts with device 600,600 orientation of device or acceleration/deceleration and device 600
Temperature change.Sensor module 614 may include proximity sensor, be configured to examine without any physical contact
Survey presence of nearby objects.Sensor module 614 can also include that optical sensor is used for such as CMOS or ccd image sensor
It is used in imaging applications.In some embodiments, which can also include acceleration transducer, and gyroscope passes
Sensor, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 616 is configured to facilitate the communication of wired or wireless way between device 600 and other equipment.Device
600 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.In an exemplary implementation
In example, communication component 616 receives broadcast singal or broadcast related information from external broadcasting management system via broadcast channel.
In one exemplary embodiment, the communication component 616 further includes near-field communication (NFC) module, to promote short range communication.Example
Such as, NFC module can be based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology,
Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 600 can be believed by one or more application specific integrated circuit (ASIC), number
Number processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In a kind of possible embodiment, above procedure can be the program code for including computer operation instruction.The journey
Sequence, which is particularly used in, realizes above-mentioned mobile object detection method.
The disclosure can be system, method and/or computer program product.Computer program product may include computer
Readable storage medium storing program for executing, containing for making processor realize the computer-readable program instructions of various aspects of the disclosure.Institute
It states and realizes above-mentioned mobile object detection method when computer program instructions are executed by processor.
Computer readable storage medium, which can be, can keep and store the tangible of the instruction used by instruction execution equipment
Equipment.Computer readable storage medium for example can be-- but it is not limited to-- storage device electric, magnetic storage apparatus, optical storage
Equipment, electric magnetic storage apparatus, semiconductor memory apparatus or above-mentioned any appropriate combination.Computer readable storage medium
More specific example (non exhaustive list) includes: portable computer diskette, hard disk, random access memory (RAM), read-only deposits
It is reservoir (ROM), erasable programmable read only memory (EPROM or flash memory), static random access memory (SRAM), portable
Compact disk read-only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, for example thereon
It is stored with punch card or groove internal projection structure and the above-mentioned any appropriate combination of instruction.Calculating used herein above
Machine readable storage medium storing program for executing is not interpreted that instantaneous signal itself, the electromagnetic wave of such as radio wave or other Free propagations lead to
It crosses the electromagnetic wave (for example, the light pulse for passing through fiber optic cables) of waveguide or the propagation of other transmission mediums or is transmitted by electric wire
Electric signal.
Computer-readable program instructions as described herein can be downloaded to from computer readable storage medium it is each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, local area network, wide area network and/or wireless network
Portion stores equipment.Network may include copper transmission cable, optical fiber transmission, wireless transmission, router, firewall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
Computer program instructions for executing disclosure operation can be assembly instruction, instruction set architecture (ISA) instructs,
Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming languages
The source code or object code that any combination is write, the programming language include the programming language-of object-oriented such as
Smalltalk, C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer
Readable program instructions can be executed fully on the user computer, partly execute on the user computer, be only as one
Vertical software package executes, part executes on the remote computer or completely in remote computer on the user computer for part
Or it is executed on server.In situations involving remote computers, remote computer can pass through network-packet of any kind
It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit
It is connected with ISP by internet).In some embodiments, by utilizing computer-readable program instructions
Status information carry out personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or can
Programmed logic array (PLA) (PLA), the electronic circuit can execute computer-readable program instructions, to realize each side of the disclosure
Face.
Referring herein to according to the flow chart of the method, apparatus (system) of the embodiment of the present disclosure and computer program product and/
Or block diagram describes various aspects of the disclosure.It should be appreciated that flowchart and or block diagram each box and flow chart and/
Or in block diagram each box combination, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to general purpose computer, special purpose computer or other programmable datas
The processor of processing unit, so that a kind of machine is produced, so that these instructions are passing through computer or other programmable datas
When the processor of processing unit executes, function specified in one or more boxes in implementation flow chart and/or block diagram is produced
The device of energy/movement.These computer-readable program instructions can also be stored in a computer-readable storage medium, these refer to
It enables so that computer, programmable data processing unit and/or other equipment work in a specific way, thus, it is stored with instruction
Computer-readable medium then includes a manufacture comprising in one or more boxes in implementation flow chart and/or block diagram
The instruction of the various aspects of defined function action.
Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other
In equipment, so that series of operation steps are executed in computer, other programmable data processing units or other equipment, to produce
Raw computer implemented process, so that executed in computer, other programmable data processing units or other equipment
Instruct function action specified in one or more boxes in implementation flow chart and/or block diagram.
The flow chart and block diagram in the drawings show system, method and the computer journeys according to multiple embodiments of the disclosure
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
One module of table, program segment or a part of instruction, the module, program segment or a part of instruction include one or more use
The executable instruction of the logic function as defined in realizing.In some implementations as replacements, function marked in the box
It can occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually be held substantially in parallel
Row, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that block diagram and/or
The combination of each box in flow chart and the box in block diagram and or flow chart, can the function as defined in executing or dynamic
The dedicated hardware based system made is realized, or can be realized using a combination of dedicated hardware and computer instructions.
The presently disclosed embodiments is described above, above description is exemplary, and non-exclusive, and
It is not limited to disclosed each embodiment.Without departing from the scope and spirit of illustrated each embodiment, for this skill
Many modifications and changes are obvious for the those of ordinary skill in art field.The selection of term used herein, purport
In the principle, practical application or technological improvement to technology in market for best explaining each embodiment, or make the art
Other those of ordinary skill can understand each embodiment disclosed herein.
Claims (11)
1. a kind of mobile object detection method characterized by comprising
Obtain the picture frame of target vehicle surrounding scenes；
According to the pixel value of adjacent described image frame, the corresponding velocity vector of at least one characteristic point of described image frame is determined；
The sequencing queue that velocity vector is determined according to the velocity vector, the comparison according to head and the tail vector in the sequencing queue are true
Mobile object around the fixed target vehicle.
2. the method according to claim 1, wherein the picture frame for obtaining target vehicle surrounding scenes, packet
It includes:
Obtain the first picture frame that photographic device is acquired with the first projection pattern；
If first projection pattern is different from default projection pattern, the first image frame is become according to default projection pattern
It changes, obtains the second picture frame.
3. the method according to claim 1, wherein the pixel value according to adjacent described image frame, determines
The corresponding velocity vector of at least one characteristic point of described image frame, comprising:
According to the pixel value of the pixel of adjacent described image frame, at least one characteristic point is determined in the pixel；
According to the pixel coordinate of the characteristic point of adjacent described image frame, the corresponding velocity vector of the characteristic point is determined.
4. according to the method described in claim 3, it is characterized in that, the characteristic point according to adjacent described image frame
Pixel coordinate determines the corresponding velocity vector of the characteristic point, comprising:
Obtain pixel coordinate and the brightness of corresponding first pixel of characteristic point in adjacent described image frame；
According to the pixel coordinate of first pixel, the first pixel presetted pixel point described in distance in adjacent image frame is obtained
Second pixel of distance；
The corresponding velocity vector of the characteristic point is determined according to the brightness of first pixel and the brightness of the second pixel.
5. the method according to claim 1, wherein determining the sequence team of velocity vector according to the velocity vector
Column, comprising:
Described image frame is divided at least one image-region；
The velocity vector for obtaining characteristic point in each image-region, according at least one corresponding vector parameter of the velocity vector
The velocity vector is ranked up, ranking results are obtained；
According to the ranking results, the sequencing queue of the velocity vector corresponding to each image-region is determined.
6. according to the method described in claim 5, it is characterized in that, the speed for obtaining characteristic point in each image-region to
Amount, is ranked up the velocity vector according at least one corresponding vector parameter of the velocity vector, obtains ranking results,
Include:
The parameter value of vector parameter is obtained according to the velocity vector of the fisrt feature point in each image-region；
According to the parameter value of the vector parameter, the velocity vector of the fisrt feature point is determined in velocity vector sorted lists
Insertion position, wherein the velocity vector sorted lists are stored with to be inserted into before the velocity vector of the fisrt feature point
Second feature point velocity vector；
The velocity vector of the fisrt feature point is inserted into the insertion position in the velocity vector sorted lists, is arranged
Sequence result.
7. according to the method described in claim 5, it is characterized in that, the vector parameter includes: mould length, deflection.
8. according to the method described in claim 5, it is characterized in that, being determined according to the comparison of head and the tail vector in the sequencing queue
Mobile object around the target vehicle, comprising:
Determine the first vector sum tail vector in the sequencing queue of velocity vector corresponding to each image-region；
In the case that the difference of the parameter value of vector parameter between the tail vector described in the first vector sum is greater than parameter threshold, really
There are mobile objects around the fixed target vehicle.
9. a kind of mobile object detection device characterized by comprising
Module is obtained, for obtaining the picture frame of target vehicle surrounding scenes；
First determining module determines at least one feature of described image frame for the pixel value according to adjacent described image frame
The corresponding velocity vector of point；
Second determining module, for determining the sequencing queue of velocity vector according to the velocity vector, according to the sequencing queue
The comparison of middle head and the tail vector determines the mobile object around the target vehicle.
10. a kind of mobile object detection device characterized by comprising
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to method described in any one of perform claim requirement 1 to 8.
11. a kind of non-volatile computer readable storage medium storing program for executing, is stored thereon with computer program instructions, which is characterized in that institute
It states and realizes method described in any one of claim 1 to 8 when computer program instructions are executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910209887.8A CN109919126B (en) | 2019-03-19 | 2019-03-19 | Method and device for detecting moving object and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910209887.8A CN109919126B (en) | 2019-03-19 | 2019-03-19 | Method and device for detecting moving object and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109919126A true CN109919126A (en) | 2019-06-21 |
| CN109919126B CN109919126B (en) | 2023-07-25 |
Family
ID=66965710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910209887.8A Active CN109919126B (en) | 2019-03-19 | 2019-03-19 | Method and device for detecting moving object and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109919126B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111068323A (en) * | 2019-12-20 | 2020-04-28 | 腾讯科技（深圳）有限公司 | Intelligent speed detection method and device, computer equipment and storage medium |
| CN114018589A (en) * | 2021-10-25 | 2022-02-08 | 中汽研汽车检验中心（天津）有限公司 | Method and device for determining air bag ejection speed, electronic equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2628864A1 (en) * | 1988-03-21 | 1989-09-22 | France Etat | Segmentation of point velocity vectors in image sequence - segmenting velocity data based on movement prediction to generate representative vector for processing |
| JPH0795592A (en) * | 1993-03-15 | 1995-04-07 | Massachusetts Inst Of Technol <Mit> | System for encoding of image data and for changing of said data into plurality of layers expressing coherent motion region and into motion parameter accompanying said layers |
| JP2013076615A (en) * | 2011-09-30 | 2013-04-25 | Mitsubishi Space Software Kk | Mobile object detection apparatus, mobile object detection program, mobile object detection method, and flying object |
| WO2014064690A1 (en) * | 2012-10-23 | 2014-05-01 | Sivan Ishay | Real time assessment of picture quality |
| CN107292266A (en) * | 2017-06-21 | 2017-10-24 | 吉林大学 | A kind of vehicle-mounted pedestrian area estimation method clustered based on light stream |
| CN107845104A (en) * | 2016-09-20 | 2018-03-27 | 意法半导体股份有限公司 | A kind of method, associated processing system, passing vehicle detecting system and vehicle for detecting passing vehicle |
-
2019
- 2019-03-19 CN CN201910209887.8A patent/CN109919126B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2628864A1 (en) * | 1988-03-21 | 1989-09-22 | France Etat | Segmentation of point velocity vectors in image sequence - segmenting velocity data based on movement prediction to generate representative vector for processing |
| JPH0795592A (en) * | 1993-03-15 | 1995-04-07 | Massachusetts Inst Of Technol <Mit> | System for encoding of image data and for changing of said data into plurality of layers expressing coherent motion region and into motion parameter accompanying said layers |
| JP2013076615A (en) * | 2011-09-30 | 2013-04-25 | Mitsubishi Space Software Kk | Mobile object detection apparatus, mobile object detection program, mobile object detection method, and flying object |
| WO2014064690A1 (en) * | 2012-10-23 | 2014-05-01 | Sivan Ishay | Real time assessment of picture quality |
| CN107845104A (en) * | 2016-09-20 | 2018-03-27 | 意法半导体股份有限公司 | A kind of method, associated processing system, passing vehicle detecting system and vehicle for detecting passing vehicle |
| CN107292266A (en) * | 2017-06-21 | 2017-10-24 | 吉林大学 | A kind of vehicle-mounted pedestrian area estimation method clustered based on light stream |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111068323A (en) * | 2019-12-20 | 2020-04-28 | 腾讯科技（深圳）有限公司 | Intelligent speed detection method and device, computer equipment and storage medium |
| CN111068323B (en) * | 2019-12-20 | 2023-08-22 | 腾讯科技（深圳）有限公司 | Intelligent speed detection method, intelligent speed detection device, computer equipment and storage medium |
| CN114018589A (en) * | 2021-10-25 | 2022-02-08 | 中汽研汽车检验中心（天津）有限公司 | Method and device for determining air bag ejection speed, electronic equipment and medium |
| CN114018589B (en) * | 2021-10-25 | 2024-03-15 | 中汽研汽车检验中心（天津）有限公司 | Method and device for determining airbag ejection speed, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109919126B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829501B (en) | Image processing method and device, electronic equipment and storage medium | |
| TWI724736B (en) | Image processing method and device, electronic equipment, storage medium and computer program | |
| WO2021164469A1 (en) | Target object detection method and apparatus, device, and storage medium | |
| CN108596116A (en) | Distance measuring method, intelligent control method and device, electronic equipment and storage medium | |
| CN108629354B (en) | Target detection method and device | |
| WO2021155632A1 (en) | Image processing method and apparatus, and electronic device and storage medium | |
| CN108010060B (en) | Target detection method and device | |
| CN105512685B (en) | Object identification method and device | |
| US11288531B2 (en) | Image processing method and apparatus, electronic device, and storage medium | |
| CN110503023A (en) | Biopsy method and device, electronic equipment and storage medium | |
| CN110458218B (en) | Image classification method and device and classification network training method and device | |
| CN108886582A (en) | Photographic device and focusing controlling method | |
| CN109522910A (en) | Critical point detection method and device, electronic equipment and storage medium | |
| CN106557759B (en) | Signpost information acquisition method and device | |
| CN109344832A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN110503689A (en) | Attitude prediction method, model training method and device | |
| CN107563994B (en) | Image significance detection method and device | |
| WO2021052008A1 (en) | Screen projection method and system | |
| CN109978891A (en) | Image processing method and device, electronic equipment and storage medium | |
| KR102367648B1 (en) | Method and apparatus for synthesizing omni-directional parallax view, and storage medium | |
| CN106875446B (en) | Camera method for relocating and device | |
| CN108154466A (en) | Image processing method and device | |
| CN109919126A (en) | A kind of mobile object detection method, device and storage medium | |
| KR20210148134A (en) | Object counting method, apparatus, electronic device, storage medium and program | |
| CN109344703A (en) | Method for checking object and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |