CN107451519A - Moving object detection method - Google Patents
Moving object detection method Download PDFInfo
- Publication number
- CN107451519A CN107451519A CN201710103633.9A CN201710103633A CN107451519A CN 107451519 A CN107451519 A CN 107451519A CN 201710103633 A CN201710103633 A CN 201710103633A CN 107451519 A CN107451519 A CN 107451519A
- Authority
- CN
- China
- Prior art keywords
- detecting
- lattice
- region
- motive objects
- wide
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 claims abstract description 37
- 230000008859 change Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000006073 displacement reaction Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002045 lasting effect Effects 0.000 description 2
- PCTMTFRHKVHKIS-BMFZQQSSSA-N (1s,3r,4e,6e,8e,10e,12e,14e,16e,18s,19r,20r,21s,25r,27r,30r,31r,33s,35r,37s,38r)-3-[(2r,3s,4s,5s,6r)-4-amino-3,5-dihydroxy-6-methyloxan-2-yl]oxy-19,25,27,30,31,33,35,37-octahydroxy-18,20,21-trimethyl-23-oxo-22,39-dioxabicyclo[33.3.1]nonatriaconta-4,6,8,10 Chemical compound C1C=C2C[C@@H](OS(O)(=O)=O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2.O[C@H]1[C@@H](N)[C@H](O)[C@@H](C)O[C@H]1O[C@H]1/C=C/C=C/C=C/C=C/C=C/C=C/C=C/[C@H](C)[C@@H](O)[C@@H](C)[C@H](C)OC(=O)C[C@H](O)C[C@H](O)CC[C@@H](O)[C@H](O)C[C@H](O)C[C@](O)(C[C@H](O)[C@H]2C(O)=O)O[C@H]2C1 PCTMTFRHKVHKIS-BMFZQQSSSA-N 0.000 description 1
- 240000001439 Opuntia Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- VEMKTZHHVJILDY-UHFFFAOYSA-N resmethrin Chemical compound CC1(C)C(C=C(C)C)C1C(=O)OCC1=COC(CC=2C=CC=CC=2)=C1 VEMKTZHHVJILDY-UHFFFAOYSA-N 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The present disclosure provides a moving object detecting method, including the steps of: acquiring a first visual grid according to the detection range, and performing full-area detection on the first visual grid; defining a detection range including a detection area and a non-detection area according to the full-area detection result of the first view grid; and acquiring a second visual grid according to the detection range, and performing partial region detection in a detection region of the second visual grid. The moving object detection method can adjust the detection range according to the detection result, and further can improve the detection efficiency.
Description
Technical field
A kind of this disclosure relates to motive objects method for detecting;Specifically, the disclosure is one kind for drive assist system
Motive objects method for detecting.
Background technology
Drive safety is always one of important topic of transportation industry.With the progress of electronic technology, there are many actives
Formula safe driving scheme is imported in transportation industry.For example, the detecting of lane departure warning, blind spot, objects in front detecting, driving condition
Monitoring etc..By taking objects in front detecting scheme as an example, it receives and detects the contextual data in front of driver, when having detected thing
Body can send warning when close to driver.
However, the detecting mode of existing objects in front detecting scheme will receive all positions and the area of all sizes in image
Domain compares, and this practice will expend more calculation resources, cause operation efficiency bad.Therefore, existing objects in front detecting
The detecting mode of scheme still has much room for improvement.
The content of the invention
One purpose of the disclosure is to provide a kind of motive objects method for detecting, can adjust reconnaissance range according to detecting result.
One purpose of the disclosure is to provide a kind of motive objects method for detecting, can improve and detect side efficiency.
Motive objects method for detecting is used for drive assist system, and drive assist system includes video camera, is detectd to lasting acquirement
Survey the multiple of scope and regard lattice, multiple lattice that regard regard lattice including at least first regarding lattice and second, and motive objects method for detecting includes following step
Suddenly:First is obtained according to reconnaissance range and regards lattice, and is regarded lattice in first and performed region-wide detecting;Detectd according to first depending on the region-wide of lattice
Survey result defines reconnaissance range and includes detection region and non-detection region;Second is obtained according to reconnaissance range and regards lattice, and lattice are regarded in second
Detection region executable portion area detecting.
Brief description of the drawings
Fig. 1 is an embodiment flow chart of disclosure motive objects method for detecting;
Fig. 2 is an embodiment block diagram of disclosure drive assist system;
Fig. 3 is the embodiment flow chart that disclosure motive objects method for detecting performs different piece area detecting;
Fig. 4 is the top view of executable portion area detecting when not detecting motive objects;
Fig. 5 A and Fig. 5 B are the top view of executable portion area detecting when detecting motive objects;
Fig. 6 is the schematic diagram of fringe region composition;
Fig. 7 is the embodiment flow chart that disclosure motive objects method for detecting has detecting cycle set;
Fig. 8 is the embodiment flow chart that disclosure motive objects method for detecting judges region-wide detecting process;
Fig. 9 A are to use top view of the motive objects rear for baffle area;
Fig. 9 B to 9D are the schematic diagram for illustrating Fig. 9 A setting means.
Embodiment
The disclosure provides a kind of motive objects method for detecting, can be in the reconnaissance range of setting according to the detecting knot to motive objects
Fruit adjusts Subsequent detection mode, to improve system operations efficiency.Motive objects are, for example, pedestrian, vehicle, wildlife etc..The disclosure
Motive objects method for detecting can be used for vehicle drive assist system.
Generally speaking, the motive objects method for detecting of the disclosure includes two stages:(1) region-wide detecting;And (2) part
Area detecting.It refer to Fig. 1.Fig. 1 is an embodiment flow chart of disclosure motive objects method for detecting.As shown in figure 1, in step
S100:Perform region-wide detecting.For example, with 30 meters of shooting front, open the scope that 100 degree of horizontal view angle is surrounded and be used as detecting
Scope.Video camera obtains the multiple of reconnaissance range and regards lattice, and these cover reconnaissance range depending on the content of lattice.It is above-mentioned to form shadow depending on lattice
As crossfire, such as 20 per second regard lattice (20f/s).It is multiple to regard lattice regarding lattice and second comprising at least first depending on lattice.According to detecing
Survey scope acquirement first and regard lattice, and regard lattice first and perform region-wide detecting.For example, reconnaissance range is divided into multiple regions, with
The positive direction of video camera is front, is adopted from left to right, by closely being detected one by one to each position in reconnaissance range to remote mode.
After region-wide detecting terminates, region-wide detecting result is obtained.
After region-wide detecting result is obtained, receive second and regard lattice.In step S200:Define reconnaissance range and regarded in second
Lattice executable portion area detecting.Reconnaissance range is defined according to region-wide detecting result and includes detection region and non-detection region, and
Two regard the detection region executable portion area detecting of lattice.For example, first depending on the region-wide detecting of lattice after the completion of detect motive objects,
Ensuing second depending on lattice in motive objects position is defined as detection region, and the position beyond motive objects is then non-detecting
Area.That is, second depending on lattice in only detected with motive objects position, thus lift operation efficiency.
Fig. 2 is an embodiment block diagram of disclosure drive assist system.As shown in Fig. 2 drive assist system 100 includes
CPU110, image acquiring module 120, processing module 130, motive objects detecting module 140, speed sensing module 150, locating module
160th, cycle set module 170.In addition, drive assist system 100 is connected with camera module 200 and display module 300.
For example, camera module 200 includes video camera and lens set, with photographed scene data.Image acquiring module 120
Can be cmos sensor or ccd sensor, matching camera is carried out regarding lattice acquisition, and lattice are regarded so that lasting acquirement is multiple.Processing module
130 can be digital signal processing circuit, to carry out the differentiation of foregoing detection region/non-detection region.Motive objects detecting module 140 can be
Digital image processing unit, and coordinate ultrasonic radar or infrared radar.Using digital image processing unit in lattice
Hold and carry out feature identification, using radar to being detected depending on each position in lattice, and measure and the relative distance of motive objects, motive objects
The data such as speed.Speed sensing module 150 can be acceleration transducer or wheel speed sensor, and CPU110 passes through speed sensitive
The drive speed that module 150 can use currently.Locating module 160 can be GPS or rotary angle transmitter, and CPU110 passes through locating module
160 would know that steering direction.Cycle set module 170 can be frequency cells, and CPU110 can change week according to regarding lattice receiving velocity
The setting value of phase setting module 170, in a manner of adjusting the detecting of motive objects detecting module 140.Display module 300 can be entity
Display or HUD.Drive assist system 100 can be presented acquirement depending on lattice in display module 300, be detectd in addition, working as
When measuring motive objects, drive assist system 100 also can warn driver by display module 300.
Fig. 3 is the embodiment flow chart that disclosure motive objects method for detecting performs different piece area detecting.In figure 3,
Subregion reconnaissance phase is to provide difference for the appearance whether region-wide detecting result has motive objects depending on lattice to second and detect
Survey mode.As shown in figure 3, in step S100:Perform region-wide detecting.For example, after the completion of first regards the region-wide detecting of lattice, obtain
To region-wide detecting result.Then receive and second regard lattice, whether there are motive objects depending on lattice step S202 confirmations are previous.Hold above-mentioned
Embodiment, if first does not detect motive objects depending on the region-wide detecting results of lattice, for step S220:Detect fringe region.Change
Yan Zhi, the fringe region in reconnaissance range is chosen as detection region, to the second fringe region executable portion area detecting for regarding lattice.
It refer to Fig. 4.Fig. 4 is the top view of executable portion area detecting when not detecting motive objects.As shown in figure 4, car
400 are set with reconnaissance range R in frontal scene.When performing region-wide detecting, i.e., entered with all positions in reconnaissance range R
Row detecting.When not detecting motive objects after the completion of region-wide detecting, fringe region P is chosen as detection region.Fringe region P bags
Include close to the position (near-end) of car 400, the marginal belt extended along visual angle from both sides and long-range horizontal edge strip.In view of not
When detecting motive objects, subsequent movement thing enters reconnaissance range from sight edge, therefore chooses fringe region P as detection region.
Now fringe region P is the scope of subregion detecting, and middle section Q is then non-detection region.Thus the side locally detected
Formula can save the time of system operations.
Conversely, if first detects motive objects depending on the region-wide detecting results of lattice, as shown in figure 3, being then step S210:Production
Raw target area.When detecting motive objects, motive objects are defined in the position of reconnaissance range, and target is produced around motive objects
Region.In step S212:Detect fringe region and target area.Choose the fringe region in reconnaissance range and target area conduct
Detection region, in the fringe region and target area executable portion area detecting that second regards lattice.
It refer to Fig. 5 A and Fig. 5 B.Fig. 5 A and Fig. 5 B are the top view of executable portion area detecting when detecting motive objects.
As shown in Figure 5A, except fringe region P can be set in reconnaissance range R, the position of motive objects can also be directed in motive objects 500
Surrounding produces target area M.When detecting motive objects after the completion of region-wide detecting, choose fringe region P and target area M and make
For detection region.The position that now fringe region P and target area M are covered is the scope that subregion detecting performs, and central
Region Q (deducting the part after fringe region P and target area M) is then non-detection region.Followed the trail of using the setting of target area
The motive objects detected, and the motive objects for setting tracking and being likely to occur using fringe region.Thus the mode locally detected
The time of system operations can be saved.
In one embodiment, target area is according to produced by motive objects speed, drive speed or steering direction.Before such as
The CPU stated obtains motive objects distance and speed by motive objects detecting module, and is produced by processing module in motive objects surrounding
Target area is as detection region.
In addition, the range size of target area can adjust according to motive objects speed, depending on lattice speed.It is depending on lattice speed herein
Refer to the quantity per second regarding lattice.As shown in Figure 5 B, sensor 600 by eyeglass 602 in detecting motive objects 500 in reconnaissance range R.
Wherein sensor 600 is, for example, foregoing image acquiring module, and eyeglass 602 is, for example, foregoing camera module.In motive objects 500
Surrounding is set with target area M.There is target area M length of side m to be more than the width w of motive objects 500, and cover the place of motive objects 500
Position.
Specifically, such as motive objects speed is 10m/s, for 10f/s for lattice speed, each regards compartment and moves
The displacement of thing is then 1m.In one embodiment, 3 times (that is, targets of the length of side of target area no more than motive objects width
The length of side in region is not more than 3 times of motive objects speed and the ratio regarding lattice speed).Can sets target area according to above-mentioned calculation
Domain has the scope of length of side 3m sizes.Thus the size of target area can be estimated.
It need to supplement, the data of above-mentioned motive objects speed also can be default, such as detecting the situation of pedestrian, can
Basis of the walking speed higher limit of default pedestrian as sets target region.In other embodiments, can be directed to different
Identification feature establishes the corresponding table of different motive objects and translational speed.The number of corresponding motive objects speed is found out by feature identification
Basis as sets target region according to this.
It should be understood that the length of side of the target area refers to the average side length after each side totalling.In addition, the shape of target area
It is not limited with the positive triangle frame shown in Fig. 5 B.According to follow-up depending on can be further to the detecting result of motive objects moving direction in lattice
Shape and the position of target area are adjusted along the moving direction of motive objects.For example, for movement after terminating first depending on lattice detecting
Thing produces target area, and then after second terminates depending on lattice detecting, the moving direction of motive objects is judged in contrast first depending on lattice,
The shape of target area is adjusted according to the moving direction of motive objects.For being set as circular or approximate circle target area and
Speech, setting range then refer to the average value (such as major axis and minor axis length be averaged) of radical length.
Fig. 6 is the schematic diagram of fringe region composition.As shown in fig. 6, fringe region includes the first lateral margin P1, the second lateral margin P2
And remote edge P3.First lateral margin is positioned at an angle with the second lateral margin and extends the both ends of connection remote edge.In other words, marginal zone
Domain is the outer rim of horizontal view angle both sides, and both sides extend to the banded regions remotely surrounded towards horizontal plane.
In one embodiment, the selection mode of above-mentioned fringe region can be long-range in being adjusted in reconnaissance range according to drive speed
The size at edge.Such as in figure 6, when speed increase, increase remote edge P3 size in reconnaissance range R.Another
In embodiment, the first lateral margin P1, the second lateral margin P2 and remote edge P3 scope can be adjusted simultaneously.Specifically, such as detect
Ranging is 30m from (depth) r1, and remote horizontal distance r2 is 40m.It is 10m/s that detecting, which obtains the speed of motive objects 500, for 10f/
S regard lattice speed for, each regard the displacement of compartment motive objects 500 then as 1m.Can set middle section Q depth q1 as
28m (both ends reduce 1m compared with r1), middle section Q remote horizontal distances q2 are 38m (both ends reduce 1m compared with r2).Thus side can be estimated
The size in edge region.
Motive objects method for detecting can also include in addition to the both of the aforesaid stage:(3) cycle set.It refer to Fig. 7.Fig. 7 is
Disclosure motive objects method for detecting has the embodiment flow chart of detecting cycle set.As shown in fig. 7, enter step S100 and
Before its follow-up detecting step, step S300 is carried out:The setting detecting cycle.For example, the setting detecting cycle three is opened regarding lattice, then first
After performing region-wide detecting depending on lattice, lattice executable portion area detecting then is regarded regarding lattice and the 3rd second, can be again depending on lattice the 4th
It is secondary to perform region-wide detecting.
Confirm whether the cycle terminates in step S302.If it is not, it is (described above to implement then to repeat subregion detecting
Example, when second regard lattice subregion detecting terminate after because the cycle not yet terminates, therefore in the 3rd regard lattice progress subregion
Detecting), i.e. repeat step S202, S210, S212;Or repeat step S202, S220.It should be understood that in the above-described embodiment,
Second depending on lattice is to determine detection region and non-detection region according to region-wide detecting result;3rd depending on lattice is according to the second detecing depending on lattice
Result is surveyed to determine detection region and non-detection region.
Conversely, when step S302 judgement detecting end cycles, then region-wide detecting is performed.For the above embodiments,
The 4th is received depending on performing region-wide detecting during lattice.Similarly, lattice are regarded the 5th, is then according to the 4th region-wide detecting knot for regarding lattice
Fruit defines detection region and non-detection region.In other words, lattice are regarded after lattice for first, the detecting cycle is with performing region-wide detecting
With following relation:N=mx+1, wherein, n be regarding lattice ordinal number (2,3,4 ...), m be detect the cycle (such as 3), x be cycle sequence
Number (1,2,3 ...).That is, one obtained after lattice is opened per m and regards the region-wide detecting of lattice progress.If first is included depending on lattice
Above formula considers in the lump, then is x=0 situation.Detecting cycle (m values) is the integer more than or equal to 2.Thus using one
There are emergency situations in the non-detection region for performing region-wide detecting in the section time to ensure originally to set.
Fig. 8 is the embodiment flow chart that disclosure motive objects method for detecting judges region-wide detecting process.In fig. 8, entirely
The area detecting stage can come across first regarding the different detecting modes of lattice offer for motive objects.As shown in figure 8, in step
S300:The setting detecting cycle.Subsequently enter region-wide reconnaissance phase.In step S100:Perform region-wide detecting.In step S102
It is confirmed whether there are motive objects during the region-wide detecting of middle execution.If not detecting motive objects, for step S103:Persistently complete the whole district
Domain is detected, and judges whether region-wide detecting is completed in step S108, then carries out follow-up subregion detecting (step S202
~S220).As a further example, when setting the detecting cycle as every two regarding lattice execution once region-wide detecting, lattice is regarded first and are performed
Region-wide detecting, and persistently determine whether motive objects during region-wide detecting is carried out.If region-wide detecting is completed, detecting
Each position in scope was all detected and was not detected motive objects yet, produced region-wide detecting result, then obtains second and regards
Lattice carry out subsequent step (subregion detecting).
If conversely, judge to detect motive objects in step S102, for step S104:Define baffle area.Example is held, if
Motive objects are detected during the first region-wide detecting progress depending on lattice, the subregion for defining motive objects rear is baffle area.Lift
For example, when nearby detecting motive objects at a distance of video camera, the scope of motive objects dead astern () is determined at a distance of video camera remotely
Justice is baffle area.
Then in step S106:Ignore baffle area and continue executing with the region-wide detecting of other parts.It is region-wide when judging
Detecting is completed, and obtains region-wide detecting result, is then obtained second and is regarded lattice progress subsequent step.In other words, region-wide detecting can
The region skipped over is set with the appearance for detecting motive objects, thus promotes the efficiency of region-wide detecting.
Confirm whether the cycle terminates in step S302.According to the above embodiments, regarded due to setting the detecting cycle as every two
Lattice perform once region-wide detecting, and the subregion detecting that lattice are regarded when second terminates, and the 3rd is regarded then according to reconnaissance range acquirement
Lattice, regard lattice the 3rd and perform region-wide detecting.Similarly, the region-wide detecting result redefinable for lattice being regarded according to the 3rd is detected
Area and non-detection region, and obtain the 4th according to reconnaissance range and regard lattice.Then detectd in the 4th depending on the detection region executable portion regions of lattice
Survey.In short, according to foregoing setting, obtain regard the relation of lattice and detecting mode as:First regards lattice (portion regarding lattice (region-wide), second
Subregion), the 3rd regard lattice (region-wide), the 4th regard lattice (subregion), can save system operations using the mode locally detected
Time.Meanwhile in upper example, first depending on lattice and the 3rd depending on during the detecting of lattice all summary can be defined with motive objects are detected
The region crossed, further save the system operations time.
In one embodiment, when judging there are motive objects when performing region-wide detecting, the model positioned at motive objects rear is chosen
Enclose for baffle area.It refer to Fig. 9 A to Fig. 9 D.Fig. 9 A are to use top view of the motive objects rear for baffle area.As shown in Figure 9 A,
Motive objects 500 are detected in reconnaissance range R, and the scope for choosing the rear of motive objects 500 (it is long-range to extend to reconnaissance range R) is
Baffle area N.The visual angle that baffle area N both sides can be opened according to the width of motive objects 500 remotely extends towards reconnaissance range R, makes barrier
Area N is from the overall somewhat trapezoidal region of upward angle of visibility degree.
Fig. 9 B to 9D are the schematic diagram for illustrating Fig. 9 A setting means.By taking Fig. 9 B front views as an example, front reconnaissance range is driven
Inside there are different motive objects, be shown among dotted line frame 500A and dotted line frame 500B.It is closer to driver's when detecting to be located at
Motive objects 500, place shown in (long-range) the dotted line frame 500B of rear then ignore and without detecting.That is, dotted line frame is covered in baffle area
500B positions.
Specifically, as shown in Fig. 9 C and Fig. 9 D, in reconnaissance range R, in position, T detects motive objects 500.Self-inductance measurement end
(eyeglass 602) remotely extends composition one towards reconnaissance range R according to the visual angle that the width of motive objects 500 is opened and regards entirety slightly in three from upper
Angular scope SCD.Wherein, in scope SVD can according to the distance ST of motive objects 500, the half width ET of motive objects 500 and detecting distance
SV proportionate relationship calculates DV length.The horizontal range AU at the neighbouring rear of motive objects 500 can be calculated according to aforesaid way.
Similarly, CV and BU value can be calculated in scope SVC.It is baffle area according to above-mentioned result of calculation setting range ABCD.
Thus can it is region-wide detect side when clipped region do not perform detecting, further to lift operation efficiency.
In summary, the motive objects method for detecting of the disclosure can adjust reconnaissance range according to detecting result.In addition, it can also examine
Whether the process for considering region-wide detecting there are motive objects and decides whether that part is ignored and do not detect.Thus it can improve and detect side efficiency.
The disclosure is described by above-mentioned related embodiment, but above-described embodiment is only the example for implementing the disclosure.
It must be noted that, it has been disclosed that embodiment be not limiting as the scope of the present disclosure.On the contrary, be contained in claim spirit and
The modification of scope and impartial setting are both contained in the scope of the present disclosure.
Claims (11)
1. a kind of motive objects method for detecting, for drive assist system, the drive assist system includes video camera, to continue
Obtain the multiple of reconnaissance range and regard lattice, the multiple lattice that regard regard lattice including at least first regarding lattice and second, it is characterised in that described
Method comprises the following steps:
Described first is obtained according to the reconnaissance range and regards lattice, and is regarded lattice in described first and performed region-wide detecting;And
Define the reconnaissance range depending on the region-wide detecting results of lattice according to described first and include detection region and non-detection region and root
Described second is obtained according to the reconnaissance range and regards lattice, in the detection region executable portion area detecting that described second regards lattice.
2. motive objects method for detecting according to claim 1, it is characterised in that when the region-wide detecting that described first regards lattice
When as a result not detecting motive objects, the fringe region in the reconnaissance range is chosen as the detection region.
3. motive objects method for detecting according to claim 1, it is characterised in that when the region-wide detecting that described first regards lattice
When as a result detecting motive objects, the motive objects are defined in the position of the reconnaissance range, and produced around the motive objects
Target area, fringe region in the reconnaissance range and target area are chosen as the detection region.
4. motive objects method for detecting according to claim 3, it is characterised in that the target area, which produces step, also to be included
The target area is produced according to the motive objects speed, drive speed or steering direction.
5. motive objects method for detecting according to claim 3, it is characterised in that also include the side for judging the motive objects
To, the position of the target area in the moving direction of the motive objects change reconnaissance range, the target area
Domain obtains 3 times that the length of side is not more than the motive objects width.
6. motive objects method for detecting according to claim 3, it is characterised in that also include the side for setting the target area
3 times of the speed in the motive objects of failing to grow up and the ratio regarding lattice speed.
7. motive objects method for detecting according to claim 1, it is characterised in that also comprise the following steps:
Setting the detecting cycle, to be that m is individual regard lattice;
Obtain n-th and regard lattice, when judging n values for m+1, then regard lattice in described n-th and perform region-wide detecting;And
Define the reconnaissance range depending on the region-wide detecting results of lattice according to described n-th and include the detection region and the non-detecting
Area simultaneously regards lattice according to reconnaissance range acquirement described (n+1)th, in the detection region executable portion region that described (n+1)th regards lattice
Detecting.
8. motive objects method for detecting according to claim 7, it is characterised in that the value of the m is whole more than or equal to 2
Number.
9. motive objects method for detecting according to claim 1, it is characterised in that the described first region-wide detecting for regarding lattice walks
When detecting motive objects suddenly, also comprise the following steps:
The subregion for defining the rear of the motive objects is baffle area;
Ignore the baffle area, and continue executing with the described first region-wide detecting for regarding lattice other parts;And
Complete described first depending on lattice region-wide detecting and produce region-wide detecting result.
10. motive objects method for detecting according to claim 9, it is characterised in that described to regard the complete of lattice according to described first
In the step of area detecting result defines the reconnaissance range, it is the non-detection region to choose the baffle area.
11. motive objects method for detecting according to claim 1, it is characterised in that the reconnaissance range includes fringe region
As the detection region, the fringe region includes the first lateral margin, the second lateral margin and remote edge, first lateral margin with it is described
Second lateral margin is positioned at an angle and extended the both ends for connecting the remote edge, and methods described also includes according to drive speed in described
The size of the adjustment remote edge in reconnaissance range.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW105117072 | 2016-05-31 | ||
TW105117072A TWI571830B (en) | 2016-05-31 | 2016-05-31 | Moving object detecting method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107451519A true CN107451519A (en) | 2017-12-08 |
CN107451519B CN107451519B (en) | 2021-02-05 |
Family
ID=58608500
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710103633.9A Active CN107451519B (en) | 2016-05-31 | 2017-02-24 | Moving object detection method |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107451519B (en) |
TW (1) | TWI571830B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112288774A (en) * | 2020-10-22 | 2021-01-29 | 深圳市华宝电子科技有限公司 | Movement detection method and device, electronic equipment and storage medium |
TWI761047B (en) * | 2021-01-22 | 2022-04-11 | 明泰科技股份有限公司 | Method for verifying detection range of image detector |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI676152B (en) * | 2018-05-08 | 2019-11-01 | 中華電信股份有限公司 | A moving object detection method |
TWI783390B (en) * | 2021-02-26 | 2022-11-11 | 圓展科技股份有限公司 | Image processing system and method for generating dynamic image segmentation |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101080003A (en) * | 2006-05-24 | 2007-11-28 | 深圳市景阳数码技术有限公司 | Mobile detection alert of vidicon and digital amplification linkage method |
CN101161524A (en) * | 2006-10-12 | 2008-04-16 | 财团法人车辆研究测试中心 | Method and apparatus for detecting vehicle distance |
US20080100709A1 (en) * | 2006-10-27 | 2008-05-01 | Matsushita Electric Works, Ltd. | Target moving object tracking device |
CN101415103A (en) * | 2007-10-19 | 2009-04-22 | 英华达(南京)科技有限公司 | Method for regulating video signal picture |
CN101469987A (en) * | 2007-12-29 | 2009-07-01 | 财团法人工业技术研究院 | Movable object detecting apparatus and method |
CN101605209A (en) * | 2008-05-26 | 2009-12-16 | 三洋电机株式会社 | Camera head and image-reproducing apparatus |
CN101807131A (en) * | 2009-02-13 | 2010-08-18 | 华信光电科技股份有限公司 | Detection module and optical detection system containing same |
CN101894378A (en) * | 2010-06-13 | 2010-11-24 | 南京航空航天大学 | Moving target visual tracking method and system based on double ROI (Region of Interest) |
CN102131076A (en) * | 2011-01-19 | 2011-07-20 | 中兴通讯股份有限公司 | Video monitoring method and monitoring terminal |
CN102170558A (en) * | 2010-12-30 | 2011-08-31 | 财团法人车辆研究测试中心 | Obstacle detection alarm system and method |
US20110254955A1 (en) * | 2010-04-18 | 2011-10-20 | Peter Chi-Chen Shen | Detachable Universal Electronic Door Viewer |
CN102438122A (en) * | 2010-09-29 | 2012-05-02 | 鸿富锦精密工业(深圳)有限公司 | Camera device and method for dynamically detecting monitoring object by using same |
CN103043000A (en) * | 2011-10-13 | 2013-04-17 | 能晶科技股份有限公司 | Obstacle detection system and obstacle detection method thereof |
CN203005249U (en) * | 2012-10-29 | 2013-06-19 | 华创车电技术中心股份有限公司 | Vehicular omnidirectional warning system |
US20130156269A1 (en) * | 2011-12-20 | 2013-06-20 | Fujitsu Limited | Information processing apparatus and method |
CN204432515U (en) * | 2014-12-22 | 2015-07-01 | 合肥晟泰克汽车电子有限公司 | A kind of vehicle blind zone dynamic monitoring system |
CN105015408A (en) * | 2014-04-25 | 2015-11-04 | 帷享科技有限公司 | Obstacle waning system |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW200726217A (en) * | 2005-12-20 | 2007-07-01 | Sunvision Scient Inc | Object detection system and method |
TWI393074B (en) * | 2009-12-10 | 2013-04-11 | Ind Tech Res Inst | Apparatus and method for moving object detection |
TWI416069B (en) * | 2010-01-21 | 2013-11-21 | Tatung Co | Image detecting method |
-
2016
- 2016-05-31 TW TW105117072A patent/TWI571830B/en active
-
2017
- 2017-02-24 CN CN201710103633.9A patent/CN107451519B/en active Active
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101080003A (en) * | 2006-05-24 | 2007-11-28 | 深圳市景阳数码技术有限公司 | Mobile detection alert of vidicon and digital amplification linkage method |
CN101161524A (en) * | 2006-10-12 | 2008-04-16 | 财团法人车辆研究测试中心 | Method and apparatus for detecting vehicle distance |
US20080100709A1 (en) * | 2006-10-27 | 2008-05-01 | Matsushita Electric Works, Ltd. | Target moving object tracking device |
CN101415103A (en) * | 2007-10-19 | 2009-04-22 | 英华达(南京)科技有限公司 | Method for regulating video signal picture |
CN101469987A (en) * | 2007-12-29 | 2009-07-01 | 财团法人工业技术研究院 | Movable object detecting apparatus and method |
CN101605209A (en) * | 2008-05-26 | 2009-12-16 | 三洋电机株式会社 | Camera head and image-reproducing apparatus |
CN101807131A (en) * | 2009-02-13 | 2010-08-18 | 华信光电科技股份有限公司 | Detection module and optical detection system containing same |
US20110254955A1 (en) * | 2010-04-18 | 2011-10-20 | Peter Chi-Chen Shen | Detachable Universal Electronic Door Viewer |
CN101894378A (en) * | 2010-06-13 | 2010-11-24 | 南京航空航天大学 | Moving target visual tracking method and system based on double ROI (Region of Interest) |
CN102438122A (en) * | 2010-09-29 | 2012-05-02 | 鸿富锦精密工业(深圳)有限公司 | Camera device and method for dynamically detecting monitoring object by using same |
CN102170558A (en) * | 2010-12-30 | 2011-08-31 | 财团法人车辆研究测试中心 | Obstacle detection alarm system and method |
CN102131076A (en) * | 2011-01-19 | 2011-07-20 | 中兴通讯股份有限公司 | Video monitoring method and monitoring terminal |
CN103043000A (en) * | 2011-10-13 | 2013-04-17 | 能晶科技股份有限公司 | Obstacle detection system and obstacle detection method thereof |
US20130156269A1 (en) * | 2011-12-20 | 2013-06-20 | Fujitsu Limited | Information processing apparatus and method |
CN203005249U (en) * | 2012-10-29 | 2013-06-19 | 华创车电技术中心股份有限公司 | Vehicular omnidirectional warning system |
CN105015408A (en) * | 2014-04-25 | 2015-11-04 | 帷享科技有限公司 | Obstacle waning system |
CN204432515U (en) * | 2014-12-22 | 2015-07-01 | 合肥晟泰克汽车电子有限公司 | A kind of vehicle blind zone dynamic monitoring system |
Non-Patent Citations (2)
Title |
---|
SIDIB´E D等: "Using visual saliency for object tracking with particle filters", 《PROCEEDINGS OF THE 18TH EUROPEAN SIGNAL PROCESSING CONFERENCE》 * |
黎万义等: "引入视觉注意机制的目标跟踪方法综述", 《自动化学报》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112288774A (en) * | 2020-10-22 | 2021-01-29 | 深圳市华宝电子科技有限公司 | Movement detection method and device, electronic equipment and storage medium |
CN112288774B (en) * | 2020-10-22 | 2024-01-30 | 深圳市华宝电子科技有限公司 | Mobile detection method, mobile detection device, electronic equipment and storage medium |
TWI761047B (en) * | 2021-01-22 | 2022-04-11 | 明泰科技股份有限公司 | Method for verifying detection range of image detector |
Also Published As
Publication number | Publication date |
---|---|
TW201742002A (en) | 2017-12-01 |
TWI571830B (en) | 2017-02-21 |
CN107451519B (en) | 2021-02-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107451519A (en) | Moving object detection method | |
US20230072637A1 (en) | Vehicle Drivable Area Detection Method, System, and Autonomous Vehicle Using the System | |
EP3208635B1 (en) | Vision algorithm performance using low level sensor fusion | |
CN107272021B (en) | Object detection using radar and visually defined image detection areas | |
JP5939357B2 (en) | Moving track prediction apparatus and moving track prediction method | |
JP4830604B2 (en) | Object detection method and object detection apparatus | |
EP2919197B1 (en) | Object detection device and object detection method | |
US20210270957A1 (en) | Ranging method, ranging device and ranging system | |
JP5310745B2 (en) | Driving support device | |
JP5761349B2 (en) | Three-dimensional object detection apparatus and three-dimensional object detection method | |
CN110531376A (en) | Detection of obstacles and tracking for harbour automatic driving vehicle | |
JP4953498B2 (en) | Outside vehicle monitoring device with fail-safe function | |
EP2682896A2 (en) | In-vehicle apparatus | |
EP2541465A2 (en) | Vehicle periphery monitoring system | |
EP1615191A1 (en) | Image processing system and method for front-view image sensor in a vehicle | |
CN108596081A (en) | A kind of traffic detection method merged based on radar and video camera | |
JP2001092970A (en) | Lane recognizing device | |
JP2002099906A (en) | Object-recognizing device | |
JP2002099907A (en) | Object recognizing apparatus | |
CN101777261B (en) | Method for measuring vehicle speed based on CMOS digital camera with roll-type shutter | |
JP2006072495A (en) | Three-dimensional object monitoring device | |
JP4721278B2 (en) | Lane departure determination device, lane departure prevention device, and lane tracking support device | |
JP2003077099A (en) | Preceding vehicle recognition system | |
CN113734176A (en) | Environment sensing system and method for intelligent driving vehicle, vehicle and storage medium | |
JP2002098509A (en) | Vehicle detecting 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |