CN109509345A - Vehicle detection apparatus and method - Google Patents
Vehicle detection apparatus and method Download PDFInfo
- Publication number
- CN109509345A CN109509345A CN201710833413.1A CN201710833413A CN109509345A CN 109509345 A CN109509345 A CN 109509345A CN 201710833413 A CN201710833413 A CN 201710833413A CN 109509345 A CN109509345 A CN 109509345A
- Authority
- CN
- China
- Prior art keywords
- described image
- sliding window
- scene
- detection apparatus
- width
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the present invention provides a kind of vehicle detection apparatus and method.The vehicle checking method comprises determining that the image comprising test object belongs to complex scene or normal scene；Belong to complex scene or normal scene according to described image, the whole region or partial region to described image carry out the object detection based on sliding window.It can not only guarantee the accuracy of object detection as a result, and prevent missing inspection, but also the calculation amount of object detection can be greatly reduced, to meet the demand of the real-time detection in traffic monitoring field.
Description
Technical field
The present embodiments relate to the monitoring technology fields more particularly to one intelligent transportation (Intelligent Traffic)
Kind vehicle detection apparatus and method.
Background technique
At present in traffic monitoring field, digital camera has been widely used in urban road.With artificial intelligence
The development of (AI, Artificial Intelligence) technology, the video frame images obtained from traffic monitoring camera can be by
It imports intelligent transportation system (ITS, Intelligence Transportation System), it can be automatic by intelligent algorithm
Analyze the traffic condition of road.
There are many applications, such as traffic condition analysis, traffic flux measurement, automatic accident detection for Intelligent traffic video monitoring
Etc..In such applications, object (object, or be referred to as target) detection is very important on one side.It is logical
Object detection is crossed, can detecte out interested object.It, can be to occurring in video such as in vehicle detection at the parting of the ways
Vehicle carry out real-time object detection, to analyze real-time traffic condition.
Method for checking object can extract characteristics of image, such as histograms of oriented gradients (HOG, Histogram of
Oriented Gradient) or Haar feature, and can be classified by sorting algorithm to the feature extracted；This
A little sorting algorithms are for example including support vector machines (SVM, Support Vector Machines) or AdaBoost etc..In addition,
Sliding window (sliding-window) searches for the positioning that can also be used for object.
It should be noted that the above description of the technical background be intended merely to it is convenient to technical solution of the present invention carry out it is clear,
Complete explanation, and facilitate the understanding of those skilled in the art and illustrate.Cannot merely because these schemes of the invention
Background technology part is expounded and thinks that above-mentioned technical proposal is known to those skilled in the art.
Summary of the invention
But inventor has found: the calculation amount that current object detection scheme needs is still very big, leads to object detection
Speed it is slower, be not able to satisfy intelligent traffic monitoring field real-time detection demand.How the calculating of object detection is reduced
Amount, is still the technical problem for needing to solve at present.
The embodiment of the invention provides a kind of vehicle detection apparatus and methods.Expect to reduce the calculation amount of object detection and add
The speed of fast object detection.
According to the present embodiment in a first aspect, providing a kind of vehicle detection apparatus, comprising:
Scene determination unit determines that the image comprising test object belongs to complex scene or normal scene；
Subject detecting unit belongs to complex scene or normal scene according to described image, to the complete of described image
Portion region or partial region carry out the object detection based on sliding window.
According to the second aspect of the present embodiment, a kind of vehicle checking method is provided, comprising:
Determine that the image comprising test object belongs to complex scene or normal scene；
Belong to complex scene or normal scene according to described image, whole region or part area to described image
Domain carries out the object detection based on sliding window.
According to the third aspect of the present embodiment, a kind of electronic equipment is provided, the electronic equipment includes such as first aspect
The vehicle detection apparatus.
The beneficial effect of the embodiment of the present invention is: in the case where image belongs to complex scene, to the complete of described image
Portion region carries out the object detection based on sliding window；In the case where image belongs to normal scene, to the part area of described image
Domain carries out the object detection based on sliding window.It can not only guarantee the accuracy of object detection as a result, and prevent missing inspection, Er Qieke
To greatly reduce the calculation amount of object detection, to meet the demand of the real-time detection in traffic monitoring field.
Referring to following description and accompanying drawings, the particular implementation of the embodiment of the present invention is disclosed in detail, specifies this hair
The principle of bright embodiment can be in a manner of adopted.It should be understood that embodiments of the present invention in range not thus by
Limitation.In the range of the spirit and terms of appended claims, embodiments of the present invention include many changes, modifications and wait
Together.
The feature for describing and/or showing for a kind of embodiment can be in a manner of same or similar one or more
It uses in a other embodiment, is combined with the feature in other embodiment, or the feature in substitution other embodiment.
It should be emphasized that term "comprises/comprising" refers to the presence of feature, one integral piece, step or component when using herein, but simultaneously
It is not excluded for the presence or additional of one or more other features, one integral piece, step or component.
Detailed description of the invention
Included attached drawing is used to provide to be further understood from the embodiment of the present invention, and which constitute one of specification
Point, for illustrating embodiments of the present invention, and come together to illustrate the principle of the present invention with verbal description.Under it should be evident that
Attached drawing in the description of face is only some embodiments of the present invention, for those of ordinary skill in the art, is not paying wound
Under the premise of the property made is laborious, it is also possible to obtain other drawings based on these drawings.In the accompanying drawings:
Fig. 1 is a schematic diagram of the vehicle checking method of the embodiment of the present invention；
Fig. 2 is an exemplary diagram of the image of the embodiment of the present invention；
Fig. 3 is the exemplary diagram carried out the image of Fig. 2 after binary conversion treatment；
Fig. 4 is another exemplary diagram of the image of the embodiment of the present invention；
Fig. 5 is the exemplary diagram carried out the image of Fig. 4 after binary conversion treatment；
Fig. 6 is another schematic diagram of the vehicle checking method of the embodiment of the present invention；
Fig. 7 is an exemplary diagram of the image for being determined as normal field scape of the embodiment of the present invention；
Fig. 8 is the exemplary diagram carried out after foreground detection to Fig. 7；
Fig. 9 is the embodiment of the present invention since the difference of geometric angle leads to the exemplary diagram of different sizes of test object；
Figure 10 is a schematic diagram of the vehicle detection apparatus of the embodiment of the present invention；
Figure 11 is a schematic diagram of the electronic equipment of the embodiment of the present invention.
Specific embodiment
Referring to attached drawing, by following specification, the aforementioned and other feature of the embodiment of the present invention be will be apparent.?
In the description and the appended drawings, only certain exemplary embodiments of this invention is specifically disclosed, which show can wherein implement using the present invention
The some embodiments of the principle of example, it will thus be appreciated that the present invention is not limited to described embodiments, on the contrary, the present invention is real
Applying example includes whole modifications, modification and the equivalent fallen within the scope of the appended claims.With reference to the accompanying drawing to this hair
Bright various embodiments are illustrated.These embodiments are only exemplary, and are not limitations of the present invention.
In embodiments of the present invention, term " first ", " second " etc. are used to distinguish different elements from appellation, but
It is not offered as space arrangement or the time sequencing etc. of these elements, these elements should not be limited by these terms.Term " and/
Or " include the associated term listed one kind or any one of multiple and all combinations.Term "comprising", " comprising ",
" having " etc. refers to the presence of stated feature, element, element or component, but presence or addition one or more is not precluded
Other features, element, element or component.
In embodiments of the present invention, singular " one ", "the" etc. may include plural form, should be broadly interpreted as
"an" or " one kind " and the meaning for not being defined as "one"；Furthermore term " described " is interpreted as both including singular
It also include plural form, unless the context clearly indicates otherwise.Furthermore term " according to " is interpreted as " at least partly root
According to ... ", term "based" is interpreted as " being at least partially based on ... ", unless the context clearly indicates otherwise.
Embodiment 1
The embodiment of the present invention provides a kind of vehicle checking method.Fig. 1 is the one of the vehicle checking method of the embodiment of the present invention
Schematic diagram, as shown in Figure 1, the vehicle checking method includes:
Step 101, determine that the image comprising test object belongs to complex scene or normal scene；
Step 102, complex scene or normal scene are belonged to according to described image, whole region to described image or
Person partial region carries out the object detection based on sliding window.
In the present embodiment, the video information including multiple frame images can be obtained by camera.The camera can be with
It is the camera for carrying out traffic image monitoring, monitoring area is shot incessantly；However, the present invention is not limited thereto, also
It can be other picture control scenes.
In the present embodiment, the rgb value, gray value, connected domain (CC, Connected of pixel in described image can be passed through
Component), one of prospect (foreground) or many indexes, determine whether described image belongs to including congestion
(congestion), one of light flash (flickering), dim (darkness) or the complex scene of several scenes.
For example, one of These parameters or it is a variety of be more than preset threshold in the case where, can determine that described image belongs to complicated field
Otherwise scape belongs to normal scene.
Fig. 2 is an exemplary diagram of the image of the embodiment of the present invention, and Fig. 3 is after the image of Fig. 2 is carried out binary conversion treatment
Exemplary diagram.As shown in Figures 2 and 3, it such as can determine that Fig. 2 is congestion scene by the counting of the foreground pixel of Fig. 3, that is, belong to
Complex scene.
Fig. 4 is another exemplary diagram of the image of the embodiment of the present invention, and Fig. 5 is after the image of Fig. 4 is carried out binary conversion treatment
Exemplary diagram.As shown in Figures 4 and 5, such as it can determine that Fig. 4 is dim field by the morphological feature of the prospect connected domain of Fig. 5
Scape belongs to complex scene.
It is worth noting that, the merely exemplary determination for illustrating how to carry out complex scene and normal scene of Fig. 2 to Fig. 5,
However, the present invention is not limited thereto, such as can also directly according to fig. 2 or the rgb value of Fig. 4 determines whether to belong to complex scene.In addition,
These parameters and/or scene are also not necessarily limited to this, can also specific index and/or scene determine according to actual needs.
As a result, in the case where image belongs to complex scene, can the whole region to described image carry out based on sliding
The object detection of window；It can guarantee the accuracy of object detection and prevent missing inspection.In the case where image belongs to normal scene, only
Object detection based on sliding window is carried out to the partial region of described image；The calculation amount of object detection can be greatly reduced,
To meet the demand that the real-time in traffic monitoring field detects.
In the present embodiment, in the case where described image belongs to normal scene, prospect inspection can be carried out to described image
It surveys to obtain foreground area；And the object detection based on sliding window is carried out to the foreground area.
Fig. 6 is another schematic diagram of the vehicle checking method of the embodiment of the present invention, as shown in fig. 6, the vehicle detection side
Method includes:
Step 601, input includes the image of test object and carries out scene detection；
Step 602, determine whether described image belongs to complex scene；Step is executed in the case where belonging to complex scene
603, step 604 is executed in the case where being not belonging to complex scene (belonging to normal scene).
Step 603, the object detection based on sliding window is carried out to the whole region of described image.
Step 604, foreground detection is carried out to obtain foreground area to described image；
Step 605, the object detection based on sliding window is carried out to the foreground area.
Step 606, the multiple candidate targets that will test are post-processed and export the object information detected.
In the present embodiment, foreground detection can be carried out to the image of normal scene, obtains foreground area and only to before this
Scene area carries out object detection.Under normal circumstances, the calculation amount of foreground detection is far smaller than the calculation amount of object detection, and normal
The general more and foreground area of image under scene is only the partial region of image, therefore can greatly reduce object detection
Calculation amount.
About the concrete scheme of foreground detection, frame difference method (Frame differencing), mean value can be used for example
Filtration method (Mean filter) and background mixed model method (Background Mixture Model), etc..But the present invention
It is without being limited thereto, any correlation technique in the prior art can be used.
Fig. 7 is an exemplary diagram of the image for being determined as normal field scape of the embodiment of the present invention, and Fig. 8 is to carry out prospect to Fig. 7
An exemplary diagram after detection.As shown in figure 8, foreground area 801 can be obtained after carrying out foreground detection to described image.
It is worth noting that, figure 6 above only schematically illustrates the embodiment of the present invention, but the embodiment of the present invention is not
It is limited to this.Such as the sequence that executes between each step can be suitably adjusted, it can additionally increase other some steps,
Or reduce certain steps therein.Those skilled in the art can carry out suitably modification according to above content, and not only
It is limited to the record of above-mentioned attached drawing 6.
It is illustrated below for the sliding window of the embodiment of the present invention, about the particular content of object detection, can refer to
The relevant technologies.It is adjusted by the size to sliding window, the calculation amount of object detection can be further decreased.
In the present embodiment, can according to the test object relative to shooting described image camera geometry visual angle
Difference, and change the size of the sliding window.For example, can be according to area-of-interest preset in described image
The constant precondition of the ratio between the width of lane width and the test object in (ROI, Region of Interest), limit
The width size of the fixed sliding window.
Fig. 9 is the embodiment of the present invention since the difference of geometric angle leads to the exemplary diagram of different sizes of test object,
As shown in figure 9, the width from the closer vehicle of camera is (following to use due to the perspective effect of cameraIndicate) it is big
It is (following to use in the width from the farther away vehicle of cameraIt indicates)；It is wide from the lane in the closer ROI region of camera
Degree is (following to useIndicate) it is greater than from lane width (the following use in the farther away ROI region of cameraTable
Show).
But the lane width of actually road should be roughly equal, and no matter apart from camera how far, vehicle
Developed width it is (following to useIndicate) it is (following to use with the developed width in laneIndicate) it should be substantially not
Become.
It is assumed that being m from the closer magnifying power of cameranear, it is m from the farther away magnifying power of camerafar, then can have as follows
Formula:
Therefore, the relationship of vehicle width and lane width can be expressed as follows:
Wherein,WithIndicate no matter apart from camera how far the vehicle width of in the case where and
Lane width；R indicates the ratio of the developed width of vehicle and the developed width in lane.The ratio r can determine based on experience value
In a certain range, it can have following restrictive condition: r ∈ [rmin,rmax]；Wherein rmaxAnd rminIt can be based on experience value
It predefines.
In step 603 or step 605, when carrying out the object detection, can to described image line by line or every
It is detected capablely, and the sliding window is adjusted to of different size on different rows.For example, the width of the sliding window
In a linear relationship or linear approximate relationship between target value is sat with the column of described image.
For example, the width of the sliding window can satisfy following condition:
Swindow∈[rmin·widthy lane,rmax·widthy lane]；
widthy lane=ky+b；
Wherein, SwindowFor the width of the sliding window；rminAnd rmaxThe respectively described lane width and the test object
The ratio between width minimum value and maximum value；Y is the column coordinate of described image, and k and b are preset value.
In step 603, the object detection based on sliding window can be carried out using the method being described in table 1 below.Wherein,
The height of height expression described image.
Table 1
As a result, in the case where image belongs to complex scene, can the whole region to described image carry out based on sliding
The object detection of window；It can guarantee the accuracy of object detection and prevent missing inspection.
In step 605, the object detection based on sliding window can be carried out using the method being described in table 2 below.Wherein,
ymin iAnd ymax i* the minimum value and maximum value of the column coordinate of the foreground area, x are indicatedmin iAnd xmax i* the foreground zone is indicated
The minimum value and maximum value of the row coordinate in domain.
Table 2
As a result, in the case where image belongs to normal scene, only the foreground area of described image is carried out based on sliding window
Object detection；The calculation amount of object detection can be greatly reduced, thus meet the real-time detection in traffic monitoring field
Demand.
It is worth noting that, the above Tables 1 and 2 is merely exemplary to illustrate how to adjust sliding window in the embodiment of the present invention
Size, however, the present invention is not limited thereto.About the content of adjustment sliding window, can also be determined according to actual scene and specifically, this hair
It is bright to be limited not to this.
In step 606, the multiple candidate targets detected can also be post-processed, such as removes invalid candidate
Object merges duplicate candidate target etc.；It is possible thereby to obtain the information such as more accurately object's position and/or size.
As can be seen from the above embodiments, in the case where image belongs to complex scene, the whole region of described image is carried out
Object detection based on sliding window；In the case where image belongs to normal scene, the partial region of described image is based on
The object detection of sliding window.It can not only guarantee the accuracy of object detection as a result, and prevent missing inspection, but also can greatly drop
The calculation amount of low object detection, to meet the demand of the real-time detection in traffic monitoring field.
Embodiment 2
The embodiment of the present invention provides a kind of vehicle detection apparatus, which can be only fitted in electronic equipment,
It is also possible to some or the certain components or component of the electronic equipment.The embodiment of the present invention corresponds to the vehicle detection of embodiment 1
Method, identical content repeat no more.
Figure 10 is a schematic diagram of the vehicle detection apparatus of the embodiment of the present invention, as shown in Figure 10, vehicle detection apparatus
1000 include:
Scene determination unit 1001 determines that the image comprising test object belongs to complex scene or normal scene；
Subject detecting unit 1002 belongs to complex scene or normal scene according to described image, to described image
Whole region or partial region carry out the object detection based on sliding window.
In one embodiment, the subject detecting unit 1002 is in the case where described image belongs to complex scene,
Object detection based on sliding window is carried out to the whole region of described image.
In another embodiment, as shown in Figure 10, vehicle detection apparatus 1000 can also include:
Foreground detection unit 1003 carries out prospect to described image in the case where described image belongs to normal scene
Detection is to obtain foreground area；
And the subject detecting unit 1002 is also used to carry out the object detection based on sliding window to the foreground area.
In the present embodiment, the scene determination unit 1001 can pass through the rgb value of pixel, gray scale in described image
One of value, connected domain, prospect are a variety of, determine described image whether belong to including congestion, light flash, it is dim in one
The complex scene of kind or several scenes.
As shown in Figure 10, vehicle detection apparatus 1000 can also include:
Sliding window adjustment unit 1004, the geometry according to the test object relative to the camera of shooting described image
The difference at visual angle and the size for changing the sliding window.
For example, the sliding window adjustment unit 1004 can be according in area-of-interest preset in described image
The constant precondition of the ratio between lane width and the width of the test object, limits the width size of the sliding window.
In the present embodiment, the subject detecting unit 1002, can be to described image when carrying out the object detection
Line by line or interlacing detected, and the sliding window adjustment unit 1004 can be on different rows by the sliding window
It is adjusted to of different size.It wherein, can be in a linear relationship between the width of the sliding window and the column of described image seat target value
Or linear approximate relationship.
For example, the width of the sliding window meets following condition:
Swindow∈[rmin·widthy lane,rmax·widthy lane]；
widthy lane=ky+b；
Wherein, SwindowFor the width of the sliding window；rminAnd rmaxThe respectively described lane width and the test object
The ratio between width minimum value and maximum value；Y is the column coordinate of described image, and k and b are preset value.
It is worth noting that, only each component relevant to the embodiment of the present invention or module are illustrated above, but this
Inventive embodiments are without being limited thereto.For the other component or module of vehicle detection apparatus, such as camera or image procossing mould
Block etc. can also refer to the relevant technologies.
As can be seen from the above embodiments, in the case where image belongs to complex scene, the whole region of described image is carried out
Object detection based on sliding window；In the case where image belongs to normal scene, the partial region of described image is based on
The object detection of sliding window.It can not only guarantee the accuracy of object detection as a result, and prevent missing inspection, but also can greatly drop
The calculation amount of low object detection, to meet the demand of the real-time detection in traffic monitoring field.
Embodiment 3
The embodiment of the present invention also provides a kind of electronic equipment, includes vehicle detection apparatus as described in Example 2, in
Appearance is incorporated in this.The electronic equipment for example can be computer, server, work station, laptop computer, smart phone,
Etc.；But the embodiment of the present invention is without being limited thereto.
Figure 11 is a schematic diagram of the electronic equipment of the embodiment of the present invention.As shown in figure 11, electronic equipment 1100 can wrap
It includes: processor (such as central processor CPU) 1110 and memory 1120；Memory 1120 is coupled to central processing unit 1110.
Wherein the memory 1120 can store various data；The program 1121 of information processing is additionally stored, and in processor 1110
Control under execute the program 1121.
In one embodiment, the function of vehicle detection apparatus 1000 can be integrated into processor 1110.Wherein,
Processor 1110, which can be configured as, realizes vehicle checking method as described in Example 1.
In another embodiment, vehicle detection apparatus 1000 can be with 1110 separate configuration of processor, such as can be with
It configures vehicle detection apparatus 1000 to the chip connecting with processor 1110, vehicle is realized by the control of processor 1110
The function of detection device 1000.
For example, processor 1110, which can be configured as, carries out following control: determining that the image comprising test object is to belong to
In complex scene or normal scene；Belong to complex scene or normal scene according to described image, to the complete of described image
Portion region or partial region carry out the object detection based on sliding window.
In one embodiment, processor 1110 can be additionally configured to carry out following control: in described image category
In the case where complex scene, the object detection based on sliding window is carried out to the whole region of described image.
In one embodiment, processor 1110 can be additionally configured to carry out following control: in described image category
In the case where normal scene, foreground detection is carried out to obtain foreground area to described image；And to the foreground area into
Object detection of the row based on sliding window.
It in one embodiment, can be by the rgb value, gray value of pixel in described image, connected domain, prospect
It is one or more, determine whether described image belongs to the complexity including one of congestion, light flash, dim or several scenes
Scene.
In one embodiment, processor 1110 can be additionally configured to carry out following control: according to the detection
Object relative to the geometry visual angle of the camera of shooting described image difference and change the size of the sliding window.
In one embodiment, can according in area-of-interest preset in described image lane width with
The constant precondition of the ratio between the width of the test object limits the width size of the sliding window.
In one embodiment, processor 1110 can be additionally configured to carry out following control: described right in progress
When as detection to described image line by line or interlacing detect, and the sliding window is adjusted to wide on different rows
Degree is different.
In one embodiment, the width of the sliding window and the column of described image are sat in a linear relationship between target value
Or linear approximate relationship.
In one embodiment, the width of the sliding window meets following condition:
Swindow∈[rmin·widthy lane,rmax·widthy lane]；
widthy lane=ky+b；
Wherein, SwindowFor the width of the sliding window；rminAnd rmaxThe respectively described lane width and the test object
The ratio between width minimum value and maximum value；Y is the column coordinate of described image, and k and b are preset value.
In addition, as shown in figure 11, electronic equipment 1100 can also include: input and output (I/O) equipment 1130 and display
1140 etc.；Wherein, similarly to the prior art, details are not described herein again for the function of above-mentioned component.It is worth noting that, electronic equipment
1100 are also not necessary to include all components shown in Figure 11；In addition, electronic equipment 1100 can also include in Figure 11
The component being not shown can refer to the prior art.
The embodiment of the present invention also provides a kind of computer-readable program, wherein when executing described program in the electronic device
When, described program makes computer execute vehicle checking method described in embodiment 1 in the electronic equipment.
The embodiment of the present invention also provides a kind of storage medium for being stored with computer-readable program, wherein the computer can
Reader makes computer execute vehicle checking method described in embodiment 1 in the electronic device.
The device and method more than present invention can be by hardware realization, can also be by combination of hardware software realization.The present invention
It is related to such computer-readable program, when the program is performed by logical block, the logical block can be made to realize above
The device or component parts, or the logical block is made to realize various method or steps described above.The invention further relates to
For storing the storage medium of procedure above, such as hard disk, disk, CD, DVD, flash memory.
The software mould that hardware can be embodied directly in conjunction with the method, device that the embodiment of the present invention describes, executed by processor
Block or both combination.For example, the one or more of one or more of functional block diagram and/or functional block diagram shown in Figure 10
It combines (for example, scene determination unit 1001 and subject detecting unit 1002), both can correspond to each of computer program process
A software module can also correspond to each hardware module.These software modules can correspond respectively to shown in FIG. 1 each
Step.These software modules are for example solidified using field programmable gate array (FPGA) and are realized by these hardware modules.
Software module can be located at RAM memory, flash memory, ROM memory, eprom memory, eeprom memory, post
Storage, hard disk, mobile disk, CD-ROM or any other form known in the art storage medium.One kind can be deposited
Storage media is coupled to processor, to enable a processor to from the read information, and can be written to the storage medium
Information；Or the storage medium can be the component part of processor.Pocessor and storage media can be located in ASIC.This is soft
Part module can store in a memory in the mobile terminal, also can store in the storage card that can be inserted into mobile terminal.For example,
If equipment (such as mobile terminal) is using the MEGA-SIM card of larger capacity or the flash memory device of large capacity, the software mould
Block is storable in the flash memory device of the MEGA-SIM card or large capacity.
It is combined for one or more of function box described in attached drawing and/or the one or more of function box,
It can be implemented as general processor, digital signal processor (DSP), the dedicated integrated electricity for executing function described herein
Road (ASIC), field programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor logic device
Part, discrete hardware components or it is any appropriately combined.One or more of function box for attached drawing description and/or function
Can box one or more combinations, be also implemented as calculating the combination of equipment, for example, the combination of DSP and microprocessor, more
A microprocessor communicates the one or more microprocessors or any other this configuration combined with DSP.
Combining specific embodiment above, invention has been described, it will be appreciated by those skilled in the art that this
A little descriptions are all exemplary, and are not limiting the scope of the invention.Those skilled in the art can be according to the present invention
Spirit and principle various variants and modifications are made to the present invention, these variants and modifications are also within the scope of the invention.
Claims (10)
1. a kind of vehicle detection apparatus, which is characterized in that the vehicle detection apparatus includes:
Scene determination unit determines that the image comprising test object belongs to complex scene or normal scene；
Subject detecting unit belongs to complex scene or normal scene according to described image, to the whole region of described image
Or partial region carries out the object detection based on sliding window.
2. vehicle detection apparatus according to claim 1, wherein the subject detecting unit belongs to complexity in described image
In the case where scene, the object detection based on sliding window is carried out to the whole region of described image.
3. vehicle detection apparatus according to claim 1, wherein the vehicle detection apparatus further include:
Foreground detection unit carries out foreground detection to described image in the case where described image belongs to normal scene to obtain
Obtain foreground area；
And the subject detecting unit carries out the object detection based on sliding window to the foreground area.
4. vehicle detection apparatus according to claim 1, wherein the scene determination unit passes through pixel in described image
Rgb value, gray value, connected domain, one of prospect or a variety of, determine whether described image belongs to including congestion, light sudden strain of a muscle
The complex scene of one of bright, dim or several scenes.
5. vehicle detection apparatus according to claim 1, wherein the vehicle detection apparatus further include:
Sliding window adjustment unit, according to the test object relative to shooting described image camera geometry visual angle not
Size that is same and changing the sliding window.
6. vehicle detection apparatus according to claim 5, wherein the sliding window adjustment unit is according to pre- in described image
The constant precondition of the ratio between the width of the lane width in area-of-interest and the test object that first set, described in restriction
The width size of sliding window.
7. vehicle detection apparatus according to claim 5, wherein the subject detecting unit is carrying out the object detection
When to described image line by line or interlacing detect, and the sliding window is adjusted to by the sliding window adjustment unit
It is of different size on different rows.
8. vehicle detection apparatus according to claim 7, wherein the width of the sliding window and the column coordinate of described image
Value between in a linear relationship or linear approximate relationship.
9. vehicle detection apparatus according to claim 8, wherein the width of the sliding window meets following condition:
Wherein, SwindowFor the width of the sliding window；rminAnd rmaxThe width of respectively described lane width and the test object
The minimum value and maximum value of the ratio between degree；Y is the column coordinate of described image, and k and b are preset value.
10. a kind of vehicle checking method, which is characterized in that the vehicle checking method includes:
Determine that the image comprising test object belongs to complex scene or normal scene；And
Belong to complex scene or normal scene according to described image, the whole region or partial region to described image into
Object detection of the row based on sliding window.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710833413.1A CN109509345A (en) | 2017-09-15 | 2017-09-15 | Vehicle detection apparatus and method |
| JP2018117652A JP2019053719A (en) | 2017-09-15 | 2018-06-21 | Vehicle detection device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710833413.1A CN109509345A (en) | 2017-09-15 | 2017-09-15 | Vehicle detection apparatus and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109509345A true CN109509345A (en) | 2019-03-22 |
Family
ID=65744886
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710833413.1A Pending CN109509345A (en) | 2017-09-15 | 2017-09-15 | Vehicle detection apparatus and method |
Country Status (2)
| Country | Link |
|---|---|
| JP (1) | JP2019053719A (en) |
| CN (1) | CN109509345A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112309134A (en) * | 2019-07-29 | 2021-02-02 | 富士通株式会社 | Vehicle speed detection method and device |
| CN112349087A (en) * | 2019-08-07 | 2021-02-09 | 北京博研智通科技有限公司 | Visual data input method based on holographic perception of intersection information |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102043953A (en) * | 2011-01-27 | 2011-05-04 | 北京邮电大学 | Real-time-robust pedestrian detection method aiming at specific scene |
| CN102385690A (en) * | 2010-09-01 | 2012-03-21 | 汉王科技股份有限公司 | Target tracking method and system based on video image |
| CN102982539A (en) * | 2012-11-09 | 2013-03-20 | 电子科技大学 | Characteristic self-adaption image common segmentation method based on image complexity |
| CN103605953A (en) * | 2013-10-31 | 2014-02-26 | 电子科技大学 | Vehicle interest target detection method based on sliding window search |
| CN104657727A (en) * | 2015-03-18 | 2015-05-27 | 厦门麦克玛视电子信息技术有限公司 | Lane line detection method |
| US20150235092A1 (en) * | 2014-02-14 | 2015-08-20 | Toyota Motor Engineering & Manufacturing North America, Inc. | Parts based object tracking method and apparatus |
| CN105447880A (en) * | 2015-12-15 | 2016-03-30 | 北京文安科技发展有限公司 | Box-office attendance verification method, device and system |
| CN105469088A (en) * | 2015-11-17 | 2016-04-06 | 西北工业大学 | Object prediction area optimization method applicable to target identification |
| CN105654067A (en) * | 2016-02-02 | 2016-06-08 | 北京格灵深瞳信息技术有限公司 | Vehicle detection method and device |
| CN106096531A (en) * | 2016-05-31 | 2016-11-09 | 安徽省云力信息技术有限公司 | A kind of traffic image polymorphic type vehicle checking method based on degree of depth study |
| CN106128121A (en) * | 2016-07-05 | 2016-11-16 | 中国石油大学(华东) | Vehicle queue length fast algorithm of detecting based on Local Features Analysis |
| WO2017095543A1 (en) * | 2015-12-01 | 2017-06-08 | Intel Corporation | Object detection with adaptive channel features |
| CN107145820A (en) * | 2017-03-16 | 2017-09-08 | 杭州岱石科技有限公司 | Eyes localization method based on HOG features and FAST algorithms |
-
2017
- 2017-09-15 CN CN201710833413.1A patent/CN109509345A/en active Pending
-
2018
- 2018-06-21 JP JP2018117652A patent/JP2019053719A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102385690A (en) * | 2010-09-01 | 2012-03-21 | 汉王科技股份有限公司 | Target tracking method and system based on video image |
| CN102043953A (en) * | 2011-01-27 | 2011-05-04 | 北京邮电大学 | Real-time-robust pedestrian detection method aiming at specific scene |
| CN102982539A (en) * | 2012-11-09 | 2013-03-20 | 电子科技大学 | Characteristic self-adaption image common segmentation method based on image complexity |
| CN103605953A (en) * | 2013-10-31 | 2014-02-26 | 电子科技大学 | Vehicle interest target detection method based on sliding window search |
| US20150235092A1 (en) * | 2014-02-14 | 2015-08-20 | Toyota Motor Engineering & Manufacturing North America, Inc. | Parts based object tracking method and apparatus |
| CN104657727A (en) * | 2015-03-18 | 2015-05-27 | 厦门麦克玛视电子信息技术有限公司 | Lane line detection method |
| CN105469088A (en) * | 2015-11-17 | 2016-04-06 | 西北工业大学 | Object prediction area optimization method applicable to target identification |
| WO2017095543A1 (en) * | 2015-12-01 | 2017-06-08 | Intel Corporation | Object detection with adaptive channel features |
| CN105447880A (en) * | 2015-12-15 | 2016-03-30 | 北京文安科技发展有限公司 | Box-office attendance verification method, device and system |
| CN105654067A (en) * | 2016-02-02 | 2016-06-08 | 北京格灵深瞳信息技术有限公司 | Vehicle detection method and device |
| CN106096531A (en) * | 2016-05-31 | 2016-11-09 | 安徽省云力信息技术有限公司 | A kind of traffic image polymorphic type vehicle checking method based on degree of depth study |
| CN106128121A (en) * | 2016-07-05 | 2016-11-16 | 中国石油大学(华东) | Vehicle queue length fast algorithm of detecting based on Local Features Analysis |
| CN107145820A (en) * | 2017-03-16 | 2017-09-08 | 杭州岱石科技有限公司 | Eyes localization method based on HOG features and FAST algorithms |
Non-Patent Citations (3)
| Title |
|---|
| 常庆龙 夏洪山: "基于自适应滑动窗的模糊场景行人快速检测", 《电视技术》 * |
| 常庆龙: "航站楼集群安全识别与预警关键技术研究", 《中国博士学位论文全文数据库工程科技Ⅱ辑》 * |
| 黄成都 等: "基于Codebook背景建模的视频行人检测", 《传感器与微***》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112309134A (en) * | 2019-07-29 | 2021-02-02 | 富士通株式会社 | Vehicle speed detection method and device |
| CN112349087A (en) * | 2019-08-07 | 2021-02-09 | 北京博研智通科技有限公司 | Visual data input method based on holographic perception of intersection information |
| CN112349087B (en) * | 2019-08-07 | 2021-10-15 | 北京博研智通科技有限公司 | Visual data input method based on holographic perception of intersection information |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2019053719A (en) | 2019-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8509526B2 (en) | Detection of objects in digital images | |
| Kim et al. | Spatiotemporal saliency detection and its applications in static and dynamic scenes | |
| CN103207898B (en) | A kind of similar face method for quickly retrieving based on local sensitivity Hash | |
| CN105809146B (en) | A kind of image scene recognition methods and device | |
| CN111104898A (en) | Image scene classification method and device based on target semantics and attention mechanism | |
| CN105512683A (en) | Target positioning method and device based on convolution neural network | |
| US20190294863A9 (en) | Method and apparatus for face classification | |
| CN109948616A (en) | Image detecting method, device, electronic equipment and computer readable storage medium | |
| CN104036284A (en) | Adaboost algorithm based multi-scale pedestrian detection method | |
| CN104615986A (en) | Method for utilizing multiple detectors to conduct pedestrian detection on video images of scene change | |
| Wang et al. | When pedestrian detection meets nighttime surveillance: A new benchmark | |
| US9323989B2 (en) | Tracking device | |
| CN103345631A (en) | Image characteristic extraction, training, detection method, module, device and system | |
| Prasad et al. | HOG, LBP and SVM based traffic density estimation at intersection | |
| CN109509345A (en) | Vehicle detection apparatus and method | |
| Xing et al. | Fast pedestrian detection based on haar pre-detection | |
| CN112686122B (en) | Human body and shadow detection method and device, electronic equipment and storage medium | |
| CN110969101A (en) | Face detection and tracking method based on HOG and feature descriptor | |
| CN109726621B (en) | Pedestrian detection method, device and equipment | |
| CN102013101A (en) | Blind detection method of permuted and tampered images subjected to fuzzy postprocessing | |
| CN104966064A (en) | Pedestrian ahead distance measurement method based on visual sense | |
| Dong et al. | Nighttime pedestrian detection with near infrared using cascaded classifiers | |
| Dong et al. | Crowd Density Estimation Using Sparse Texture Features. | |
| JP3962517B2 (en) | Face detection method and apparatus, and computer-readable medium | |
| CN102314592B (en) | A kind of recognition methods of smiling face's image and recognition device |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190322 |
|
| WD01 | Invention patent application deemed withdrawn after publication |