CN105574511B - Have the adaptability object sorter and its method of parallel framework - Google Patents
Have the adaptability object sorter and its method of parallel framework Download PDFInfo
- Publication number
- CN105574511B CN105574511B CN201510960147.XA CN201510960147A CN105574511B CN 105574511 B CN105574511 B CN 105574511B CN 201510960147 A CN201510960147 A CN 201510960147A CN 105574511 B CN105574511 B CN 105574511B
- Authority
- CN
- China
- Prior art keywords
- barrier
- image
- data
- classification
- parallel framework
- 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.)
- Active
Links
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
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
Abstract
The invention discloses a kind of adaptability object sorter for having parallel framework and its methods, the step of adaptability object classification method for wherein having parallel framework includes more scenario parameters of storage and more classifier parameters, after first capturing an at least image data, frame selects multiple barrier images in image data, can select selection range appropriate according to each barrier image capturing range.Multiple image process units are recycled to respectively correspond more barrier characteristics for calculating multiple barrier images with one-to-one parallel processing, and corresponding scenario parameters and corresponding multiple classifier parameters are chosen according to multiple barrier characteristics and carry out operation, to obtain more classification data, if it is determined that classification data is default obstacle species, the position that institute's frame selects barrier image is then exported, so can reach the purpose of detecting real-time barrier.
Description
Technical field
The present invention relates to a kind of adaptability object sorter and its methods, particularly relate to a kind of adaptation for having parallel framework
Property object classification devices and methods therefor.
Background technique
Since traffic safety is increasingly taken seriously in recent years, as the cost of image documentation equipment is greatly reduced and image identification skill
Art is increasingly mature, and image recognition system is applied more and more extensive on vehicle safety, and in the security system, is distinguished using image
Knowledge is to reduce an important method of whole system cost.It is shown according to statistical data, as long as driver is colliding
Early warning was obtained before 0.5 second, it can avoids at least 60% car accident that knocks into the back, 30% head-on car accident and 50% road
Face related accidents, and if have 1 second pre-warning time, can avoid 90% accident.But in image recognition system, calculation amount
Huge is a main difficulty, and real-time operation is required more to need to be taken seriously in harsh Vehicle security system.
For anti-collision system, the pedestrian's detecting system used is usually all very expensive equipment, for example uses infrared ray
Detecting, laser radar detecting etc., have multiple pedestrians, vehicle and cat and dog due to the complexity of road scene, such as in Same Scene,
Therefore pedestrian and other background informations are separated with greater need for more strong characteristic parameter.In addition, pedestrian's detecting system is being detectd
During survey, it is subjected to the interference of the various environmental change factors of floor and the accuracy rate of detecting result is declined, such as
Cause pedestrian part excessive lightness or darkness in the environment of uneven illumination, or in the case where the drive body of pedestrian is partially obscured,
Usually whether can not accurately it judge in scene with the presence of pedestrian.The method of another pedestrian's detecting is to utilize background acquisition method
Foreground information is obtained using as image treatment method further, however obtains being more broken using the method pick-up image
Prospect, cause rear end recognize difficulty, and because need for a long time capture, to increase the burden of system.Therefore, how to mention
It rises the detecting efficiency of barrier and meets detecting real-time demand and be a problem to be solved.
In view of this, inventor satisfies in view of the above shortcomings of the prior art, a kind of adaptation for having parallel framework is proposed
Property object classification devices and methods therefor, it is above-mentioned effectively to overcome the problems, such as.
Summary of the invention
The main purpose of the present invention is to provide a kind of adaptability object sorter for having parallel framework and its methods, put down
Row handles multiple barrier images, so as to accelerate image processing efficiency, and then simplifies the complexity and reduction of image processing
It is time-consuming.
Another object of the present invention is to provide a kind of adaptability object sorter for having parallel framework and its method,
Corresponding scene can be judged according to the image captured, it can be according to various different scenes come elastic adjustment classifier parameters, energy
The higher barrier image of accuracy and its type are calculated, enough to solve the problems, such as existing detecting system erroneous judgement.
Another object of the present invention is to provide a kind of adaptability object sorter for having parallel framework and its method,
It can select barrier image capturing range appropriate according to the remote depth of the image captured and the size of barrier image, frame and carry out shadow again
As processing, it is able to ascend image processing efficiency.
A further object of the present invention is to provide a kind of adaptability object sorter for having parallel framework and its method,
It is embeddable in the anti-collision system of vehicle, to achieve the purpose that detecting real-time.
In order to achieve the above object, the present invention provides a kind of adaptability object classification method for having parallel framework, the party
The step of method includes more scenario parameters of storage and more classifier parameters, adaptability object classification method includes the following steps:
Capture an at least image data；Frame selects multiple barrier images in image data, and according to each barrier image capturing range
Select selection range appropriate.Multiple image process units are recycled to respectively correspond more barriers for calculating multiple barrier images
Hinder object characteristic, and chooses corresponding scenario parameters and corresponding multiple classifier parameters according to multiple barrier characteristics
And operation is carried out, to obtain more classification data.Wherein, multiple classifier parameters include more directions of different obstacle species
Gradient Features parameter, each classification data are multiplied by corresponding classifier parameters by each barrier characteristic, and add up and
It obtains.Whether match stop data are greater than a floating threshold, the corresponding obstacle species of floating threshold, if so, determining classification
The corresponding obstacle species of data, and export institute's frame and select the position of barrier image, appoint if it is not, then determining that classification data is not corresponding
What obstacle species.Since the present invention not only can effectively shorten operation time with the multiple barrier images of parallel processing, from
And achieve the purpose that detecting real-time, and corresponding scene can be judged according to image data, it can not only be suitable according to scenario parameters
Answering property adjusts classifier parameters, and barrier characteristic of arranging in pairs or groups carries out operation to obtain more reliable classification data, therefore can
Whole detecting accuracy, great market competition advantage is substantially improved.
Wherein, further comprising the steps of before frame selects multiple barrier image steps: from image data select one have it is emerging
Interesting region, then select from interesting region center multiple barrier images in image data.And in view of in image data
Multiple barrier images have remote depth and image size issue, therefore after frame selects multiple barrier image steps, it further include that adjustment is every
The step of selection range size of one barrier image.
Wherein, direction gradient algorithm is further comprising the steps of: first calculating the marginal value of each barrier image, direction gradient
Each barrier image is divided into multiple block of cells by algorithm (HOG), then calculates the direction of each pixel in each block of cells
And edge parameter value and add up, to obtain nine feature vectors, and nine feature vectors in each block of cells are counted, is hindered
Hinder the barrier characteristic of object image.
The present invention also provides a kind of adaptability object sorter for having parallel framework, which stores more scenes
Parameter and more classifier parameters, adaptability object sorter include an at least video capture device and an image processor.Shadow
As an acquisition device acquisition at least image data, and frame selects multiple barrier images in image data, and according to each obstacle
Object image capturing range selectes selection range appropriate.Image processor includes multiple image process units, multiple image process units
More barrier characteristics for calculating multiple barrier images are respectively corresponded, according to the selection pair of multiple barrier characteristics
The contextual data and corresponding multiple classifier parameters answered simultaneously carry out operation, to obtain more classification data, then by classification data
Compared with a floating threshold, the corresponding obstacle species of floating threshold, and the institute's frame for exporting corresponding floating threshold selects barrier
The position of image.
Below by specific embodiment elaborate, when be easier to understand the purpose of the present invention, technology contents, feature and its
The effect of reached.
Detailed description of the invention
Fig. 1 is block schematic diagram of the invention；
Fig. 2 is step flow chart of the invention；
Fig. 3 is that the multiple frame of parallelization in the present invention selects barrier image schematic diagram；
Fig. 4 A to Fig. 4 D is the flow diagram of barrier in detecting image data of the present invention.
Description of symbols: 10- reservoir；102- scenario parameters；104- classifier parameters；12- video capture device；122-
Image data；124,124a, 124b, 124c, 124d- barrier image；14- image processor；142,142a,142b,142c,
142d- image process unit；144- adjusts dimension cells；16- display.
Specific embodiment
To make anti-collision system (AEB) that can quickly judge braking time, the present invention provides one kind to have parallelization frame
The adaptability object sorter and its method of structure and pipelined operation technology, come solve the prior art can not detecting real-time lack
Point.
It is as shown in Figure 1 block schematic diagram of the invention.Adaptability object sorter is built into an anti-collision system, is fitted
Answering property object classification device includes a reservoir 10, at least a video capture device 12 and an image processor 14, image processor
14 are electrically connected reservoir 10 and video capture device 12.Wherein, reservoir 10 can be synchronous dynamic random-access reservoir
(Synchronous Dynamic Random Access Memory, SDRAM), internal reservoir has more scenario parameters 102
And more classifier parameters 104, image processor 14 include multiple image process units 142 and multiple adjustment dimension cells
(resize unit) 144, multiple image process unit 142 are electrically connected multiple adjustment dimension cells 144.Image capture
After device 12 captures an image data 122, frame selects multiple barrier images 124 in image data 122, and according to each barrier
124 range of object image is hindered to select selection range appropriate.Since video capture device 12 has far and near pick-up image ability, barrier
124 range of image is also different therewith, therefore each barrier image 124 for being selected institute's frame using multiple adjustment dimension cells 144
Range is adjusted to selection range appropriate, can so reduce the data volume of subsequent images processing.In order to accelerate image processing to imitate
Rate, center select several barrier images 124 and are just corresponding with the several progress of image process units 142 parallel processing, Yi Jiying
Picture processing unit 142 and barrier image 124 are one-to-one parallel processing, therefore multiple image process units 142 are corresponding
Calculate more barrier characteristics of multiple barrier images.Corresponding field is chosen further according to multiple barrier characteristics
Scape parameter 102 and corresponding multiple classifier parameters 104 simultaneously carry out operation, to obtain more classification data, then by classification data
Compared with a floating threshold, the corresponding obstacle species of floating threshold, and the institute's frame for exporting corresponding floating threshold selects barrier
The position of image 124 is in a display 16.Using several 124 methods of barrier image of parallel processing, can speed up at image
Efficiency is managed, and then simplifies the complexity of image processing and reduces time-consuming.
Reach detecting real-time effect to be further understood that the present invention such as how parallel shelf structure and pipelined operation mode,
As shown in Figure 1, Figure 2 and Figure 3, Fig. 2 is step flow chart of the invention, and Fig. 3 is that the multiple frame of parallelization of the invention selects barrier
Image schematic diagram.Firstly, capturing an at least image data 122 such as step S10, illustrating by taking an image data as an example herein.It can
According to dynamic interest section of driving a vehicle at present, dynamically adjust the region scanned, avoid scanning the imagery zone for not needing operation with
Operand is reduced, such as step S12, an interesting region (ROI) is selected from image data, then select from interesting region center
Multiple barrier images in image data 122, multiple barrier images are vehicle, pedestrian, animal, electric pole, Lu Shu, roadblock
Or above combination, as shown in figure 3, multiple barrier images include barrier image 124a, barrier image 124b, obstacle
Object image 124c and barrier image 124d is respectively corresponded every to adjust such as step S14 using multiple adjustment dimension cells 144
The selection range size of one barrier image 124a, 124b, 124c, 124d is chosen to be each 124 range of barrier image suitable
When selection range, due to the difference of obstacle species, length and the shadow presented in view of shooting focal length is far and near
As difference in size, selection range size is adjusted for different barrier images using adjustment dimension cells 144, is able to ascend shadow
As processing speed.Such as step S16, more barriers for calculating multiple barrier images are respectively corresponded using multiple image process units
Hinder object characteristic, as image process unit 142a calculates the barrier characteristic of barrier image 124a, image processing
Unit 142b calculates the barrier characteristic of barrier image 124b, and image process unit 142c calculates barrier image
The barrier characteristic of 124c, image process unit 142d calculate the barrier characteristic of barrier image 124d,
In, image process unit 142a, 142b, 142c, 142d be barrier image 124a, 124b, 124c corresponding to parallel processing,
124d, and corresponding scenario parameters 102 and corresponding multiple classifier parameters 104 are chosen simultaneously according to multiple barrier characteristics
Operation is carried out, to obtain more classification data.Wherein, scenario parameters 102 are overexposure scene, night scenes, on the sunny side scene or Huang
Confused scene, and elastic according to different scenes can adjust, classifier parameters 104 include more direction ladders of different obstacle species
Characteristic parameter is spent, and can be adjusted in time according to obstacle species.Whether last such as step S18, match stop data are greater than one
Floating threshold, the corresponding obstacle species of floating threshold determine the corresponding barrier of classification data if so, thening follow the steps S20
Type, and export the position that institute's frame selects barrier image；If it is not, thening follow the steps 22, then it is any to determine that classification data does not correspond to
One obstacle species, wherein obstacle species are car body, pedestrian or roadblock.Since the present invention can sentence according to the image captured
Disconnected corresponding scene out, it is higher can to calculate accuracy according to various different scenes come elastic adjustment classifier parameters 104
Barrier image 124 and its type, to solve the problems, such as the erroneous judgement of existing detecting system, and in multiple image process units 142
It is built in the anti-collision system of vehicle.
To further illustrate how image process unit 142 of the invention calculates the barrier characteristic of barrier image
According to, and how corresponding scenario parameters and corresponding classifier parameters to be chosen according to barrier characteristic and carry out operation,
To obtain classification data, illustrate by taking pedestrian's detecting image as an example in this barrier image.As shown in Fig. 1 and Fig. 4 A to Fig. 4 D, figure
4A to Fig. 4 D is the flow diagram of barrier in detecting image data of the present invention.Here, the present invention is that use direction gradient is calculated
Method (Histogram of Oriented Gradient, HOG) calculates barrier characteristic value, predominantly counts the ladder of whole image
The foundation of intensity and directional information as subsequent classification is spent, use direction gradient algorithm increases intensity for the edge of barrier
And there is higher tolerance to barrier deformability.In addition, the more classifier parameters that the present invention stores are from supporting vector
Machine classifier (Support Vector Machine, SVM), to be corresponded to the characteristic parameter of barrier using inner product of vectors
The separating degree of barrier characteristic value is maximum by one hyperplane.Specifically, support vector machine classifier is using hundreds of or counts
The pedestrian sample of a thousand sheets after calculating barrier characteristic value via direction gradient algorithm, then is inputted as pedestrian's image database
Trained off-line is carried out to support vector machine classifier, finally using more classifier parameters of training result as subsequent obstacle species
The classification foundation of class.
As shown in Figure 4 A, an image data 122 is captured, and frame selects multiple barrier images in image data 122
124a, barrier image 124b, barrier image 124c, then as shown in Figure 4 B, each 142 utilization orientation of image process unit ladder
Degree algorithm first calculates the marginal value of each barrier image, and each barrier image 124 after frame is selected is divided into multiple small
Block (block), then calculate the direction of each pixel in each block of cells and edge parameter value and add up, it is each to obtain
Nine feature vectors in block of cells.For example, detect barrier image 124 be pedestrian when, 124 size of barrier image
It is 64 (n) × 128 (m), each of barrier image 124 pixel is subjected to edge detection (Edge Detection), it can
The edge direction and edge strength of each pixel are obtained, it is 16 × 16 and portion that barrier image 124, which is next divided into size,
The operation for dividing the unit (cell) to overlap to carry out direction gradient algorithm, and 8 lattice of displacement every time, here, in order to reduce operation time,
Pipeline design method can be utilized, data flow is pre-stored in a fritter memory (SRAM), to reduce the data-moving time,
In the assisted instruction period, wherein memory is electrically connected image processor 14.Since edge direction difference 180 degree can be considered same side
To, therefore each unit is divided into nine feature vectors, that is, each 16 × 16 blocks in 0~180 degree according to edge direction
Nine directions can be corresponded to, as shown in Figure 4 C, the total amount of data in this stage is a barrier characteristic of 9 × (n/8) × (m/8)
According to.Wherein all pixels do ballot statistics to the direction character vector belonging to it respectively in each unit, and the poll thrown is picture
The information of the edge strength of element, this nine directions can be represented with the vector of nine dimensions, that is, nine feature vectors.By four phases
Adjacent unit is considered as a block, can mutually overlap between different blocks, and block describes obstacle with the feature vector of its interior 4 unit
The local edge information of 124 position of object image.Parallel calculation is utilized herein, four units are calculated with the time, and will
It is put into memory to be counted, to accelerate the whole instruction cycle.It is finally represented with 36 dimensional vectors, 36 dimensional vectors are through normalization
(Normalize) make vector length 1, by 36 dimensional vectors of all 7x15 blocks combine it is available 3780 dimension to
Amount, this vector contain the whole information with part of pedestrian, that is, the barrier characteristic of barrier image 124.
It connects, every barrier characteristic is multiplied by corresponding classifier parameters, such as barrier characteristic 9 ×
(n/8) × (m/8) is multiplied by classifier parameters 9 × (n/8) × (m/8), and adds up and obtain an end value, this end value frame thus
The score of favored area represents this frame favored area with detected barrier as soon as such score is greater than floating threshold, it is on the contrary then
Clear, as shown in Figure 4 D, herein for detecting pedestrian, therefore, the score of frame favored area is greater than one floating threshold, that is, table
Show that frame favored area has detected barrier for pedestrian, and pedestrian's image of display box favored area, such as shows barrier image
124b, barrier image 124c；Conversely, the score of frame favored area is less than a floating threshold, then frame favored area, which has, is detected
Barrier non-pedestrian, thus it is for example possible to be vehicle, roadblock or other barriers or without any barrier.Not due to obstacle species
Together, classifier parameters can also change therewith with floating threshold, therefore can adjust classifier parameters in real time, more accurately be detectd with reaching
Efficiency is surveyed, existing generate because scenario parameters and sorting parameter can not be adaptively adjusted is no longer limited to and detects asking for mistake
Topic.That is, image process unit 142 can choose corresponding scenario parameters and corresponding classification according to barrier characteristic
Device parameter simultaneously carries out operation, to obtain classification data, reinforces the identification precision of this device.In conclusion due to the prior art
Obstruction detection and sort out obstacle species must in image one by one search detect barrier, then sequentially detect operation at
Obstacle species are managed and sort out, this image operand is quite big and time-consuming, is not easy to reach the efficiency of real-time judge.And it is of the invention
In order to enable anti-collision system quickly accurately to judge brake opportunity, therefore devise the suitable of the parallel framework of tool and pipelined operation framework
Answering property object classification device can speed up statistical vector using the multiple barrier images of one-to-one image processing parallel calculation
Treatment effeciency, the higher barrier data of accuracy are provided and give anti-collision system, are avoided that traffic accident, and then simplify shadow
As the complexity and time-consuming problem of processing.
In addition, since current used classifier parameters are the good parameters of precondition, and be embedded in anti-collision system, when
When vehicle encounters different scenes in outdoor traveling, such as dusk, on the sunny side, night or overexposure scene, it is appropriate because that can not adjust
Scenario parameters also can not adjust classifier parameters because scene is different, erroneous judgement and the decline of detecting rate etc. is be easy to cause to lack
Point.And the present invention can judge corresponding scene according to the image captured, it can be according to various different scenes come elastic adjustment point
Class device parameter can calculate the higher barrier image of accuracy and its kind because having the scene judgement of adaptability
Class, to solve the problems, such as existing detecting system erroneous judgement.Still further, the present invention can according to the remote deep of the image captured and
The size of barrier image, frame select barrier image capturing range appropriate and carry out image processing again, are able to ascend image processing effect
Rate, so solve the problems, such as that current image capturing range is big and caused by operand it is huge.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not used to limit the scope of implementation of the present invention.Therefore i.e.
Equivalent change or modification carried out by all features according to the scope of claims of the present invention and spirit, should be included in of the invention
In protection scope.
Claims (12)
1. a kind of adaptability object classification method for having parallel framework, this method includes more scenario parameters of storage and more classification
The step of device parameter, which is characterized in that the adaptability object classification method includes the following steps:
Capture an at least image data；
Frame selects multiple barrier images in the image data, and selectes frame appropriate according to each barrier image capturing range
Select range；
More barrier characteristics for calculating multiple barrier image are respectively corresponded using multiple image process units, and
The corresponding scenario parameters and corresponding multiple classifier parameters are chosen according to multiple barrier characteristic and are transported
It calculates, to obtain more classification data, each classification data is multiplied by the corresponding classification by each barrier characteristic
Device parameter, and add up and obtain；And
Whether more multiple classification data is greater than a floating threshold, which corresponds to an obstacle species and according to the barrier
Hinder species and multiple scenario parameters different and corresponding threshold values, if so, determining the corresponding barrier of the classification data
Type, and export institute's frame and select the position of the barrier image, if it is not, then determining any one not corresponding barrier of classification data
Type.
2. the adaptability object classification method according to claim 1 for having parallel framework, which is characterized in that select this more in frame
Before the step of a barrier image, further includes steps of and select an interesting region from the image data, then from
The interesting region center selects multiple barrier image in the image data.
3. the adaptability object classification method according to claim 2 for having parallel framework, which is characterized in that select this more in frame
After a barrier image step, the selection range size for adjusting each barrier image is further included steps of.
4. the adaptability object classification method according to claim 1 for having parallel framework, which is characterized in that each image
Each barrier image is divided into multiple block of cells using a direction gradient algorithm by processing unit, and counts each cell
Nine feature vectors in block obtain the barrier characteristic of the barrier image.
5. the adaptability object classification method according to claim 4 for having parallel framework, which is characterized in that direction gradient
Algorithm is the following steps are included: first calculate the marginal value of each barrier image, then calculate each picture in each block of cells
The direction of element and edge parameter value simultaneously add up, to obtain nine feature vectors.
6. the adaptability object classification method according to claim 1 for having parallel framework, which is characterized in that multiple scene
Parameter includes overexposure scene, night scenes, on the sunny side scene or dusk scene；Multiple classifier parameters include different obstacle species
More direction gradient characteristic parameters of class.
7. a kind of adaptability object sorter for having parallel framework, which stores more scenario parameters and more classifiers
Parameter, which is characterized in that the adaptability object sorter includes:
An at least video capture device, for capturing an at least image data, and frame selects multiple barriers in the image data
Image, and selection range appropriate is selected according to each barrier image capturing range；And
One image processor is electrically connected the video capture device, which includes multiple image process units, Duo Geying
More barrier characteristics of multiple barrier image are calculated as processing unit is used to respectively correspond, according to multiple barrier
Hinder object characteristic to choose corresponding contextual data and corresponding classifier parameters and carry out operation, to obtain more classification numbers
According to, each classification data is multiplied by the corresponding classifier parameters by each barrier characteristic, and adds up and obtain,
Again by multiple classification data compared with a floating threshold, the corresponding obstacle species of the floating threshold, according to the obstacle species
Class and multiple scenario parameters are different and corresponding threshold values, and the institute's frame for exporting the corresponding floating threshold selects the barrier image
Position.
8. the adaptability object sorter according to claim 7 for having parallel framework, which is characterized in that the image capture
Device can select an interesting region from the image data, then select being somebody's turn to do in the image data from the region center of being interested in
Multiple barrier images.
9. the adaptability object sorter according to claim 8 for having parallel framework, which is characterized in that the image processing
Device includes multiple adjustment dimension cells, and multiple image process unit, multiple tune are electrically connected in multiple adjustment dimension cells
Whole dimension cells capture the distance of the image data according to the video capture device, adjust using each adjustment dimension cells are corresponding
The selection range size of each barrier image.
10. the adaptability object sorter according to claim 7 for having parallel framework, which is characterized in that each shadow
As each barrier image is divided into multiple block of cells using a direction gradient algorithm by processing unit, and count that each this is small
Nine feature vectors in block obtain the barrier characteristic of the barrier image.
11. the adaptability object sorter according to claim 7 for having parallel framework, which is characterized in that multiple field
Scape parameter includes overexposure scene, night scenes, on the sunny side scene or dusk scene；Multiple classifier parameters include the different obstacles
More direction gradient characteristic parameters of species.
12. the adaptability object sorter according to claim 7 for having parallel framework, which is characterized in that the image is picked
Device and the image processor is taken to be built into the anti-collision system of a vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510960147.XA CN105574511B (en) | 2015-12-18 | 2015-12-18 | Have the adaptability object sorter and its method of parallel framework |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510960147.XA CN105574511B (en) | 2015-12-18 | 2015-12-18 | Have the adaptability object sorter and its method of parallel framework |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105574511A CN105574511A (en) | 2016-05-11 |
| CN105574511B true CN105574511B (en) | 2019-01-08 |
Family
ID=55884619
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510960147.XA Active CN105574511B (en) | 2015-12-18 | 2015-12-18 | Have the adaptability object sorter and its method of parallel framework |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105574511B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI638332B (en) * | 2016-11-29 | 2018-10-11 | 財團法人車輛研究測試中心 | Hierarchical object detection system with parallel architecture and method thereof |
| CN107025429A (en) * | 2016-12-02 | 2017-08-08 | 财团法人车辆研究测试中心 | Have the hierarchy type subject matter detecting system and its method of parallel framework |
| US20240051568A1 (en) * | 2022-08-09 | 2024-02-15 | Motional Ad Llc | Discriminator network for detecting out of operational design domain scenarios |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101425228A (en) * | 2007-10-29 | 2009-05-06 | 三菱扶桑卡客车株式会社 | Monitoring target detecting apparatus associated with collision damage reducing apparatus |
| CN101751549A (en) * | 2008-12-03 | 2010-06-23 | 财团法人工业技术研究院 | Method for tracking moving object |
| CN102508246A (en) * | 2011-10-13 | 2012-06-20 | 吉林大学 | Method for detecting and tracking obstacles in front of vehicle |
| CN103559791A (en) * | 2013-10-31 | 2014-02-05 | 北京联合大学 | Vehicle detection method fusing radar and CCD camera signals |
| CN103745241A (en) * | 2014-01-14 | 2014-04-23 | 浪潮电子信息产业股份有限公司 | Intelligent driving method based on self-learning algorithm |
-
2015
- 2015-12-18 CN CN201510960147.XA patent/CN105574511B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101425228A (en) * | 2007-10-29 | 2009-05-06 | 三菱扶桑卡客车株式会社 | Monitoring target detecting apparatus associated with collision damage reducing apparatus |
| CN101751549A (en) * | 2008-12-03 | 2010-06-23 | 财团法人工业技术研究院 | Method for tracking moving object |
| CN102508246A (en) * | 2011-10-13 | 2012-06-20 | 吉林大学 | Method for detecting and tracking obstacles in front of vehicle |
| CN103559791A (en) * | 2013-10-31 | 2014-02-05 | 北京联合大学 | Vehicle detection method fusing radar and CCD camera signals |
| CN103745241A (en) * | 2014-01-14 | 2014-04-23 | 浪潮电子信息产业股份有限公司 | Intelligent driving method based on self-learning algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105574511A (en) | 2016-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460709B (en) | RTG visual barrier detection method based on RGB and D information fusion | |
| CN103824066B (en) | A kind of licence plate recognition method based on video flowing | |
| Masmoudi et al. | Object detection learning techniques for autonomous vehicle applications | |
| CN104885122B (en) | Vehicle periphery monitoring device | |
| Byeon et al. | A performance comparison of pedestrian detection using faster RCNN and ACF | |
| CN110659550A (en) | Traffic sign recognition method, traffic sign recognition device, computer equipment and storage medium | |
| Yang et al. | Real-time pedestrian and vehicle detection for autonomous driving | |
| Bougharriou et al. | Linear SVM classifier based HOG car detection | |
| EP2813973B1 (en) | Method and system for processing video image | |
| CN109886086B (en) | Pedestrian detection method based on HOG (histogram of oriented gradient) features and linear SVM (support vector machine) cascade classifier | |
| CN105574511B (en) | Have the adaptability object sorter and its method of parallel framework | |
| CN105260715A (en) | Remote-area-oriented small-animal target detecting method | |
| CN111967396A (en) | Processing method, device and equipment for obstacle detection and storage medium | |
| Jeong et al. | Fast pedestrian detection using a night vision system for safety driving | |
| CN105354547A (en) | Pedestrian detection method in combination of texture and color features | |
| Shafie et al. | Smart video surveillance system for vehicle detection and traffic flow control | |
| Arthi et al. | Object detection of autonomous vehicles under adverse weather conditions | |
| US9633283B1 (en) | Adaptive device and adaptive method for classifying objects with parallel architecture | |
| Fleischmann et al. | An adaptive detection approach for autonomous forest path following using stereo vision | |
| Shin et al. | Real-time vehicle detection using deep learning scheme on embedded system | |
| Wen et al. | An improved algorithm based on AdaBoost for vehicle recognition | |
| Cosma et al. | Part-based pedestrian detection using HoG features and vertical symmetry | |
| CN111160224B (en) | High-speed rail contact net foreign matter detection system and method based on FPGA and horizon line segmentation | |
| EP2583216B1 (en) | Method of predetermined road object recognition in images and vehicle driving assistance device | |
| CN111062311B (en) | Pedestrian gesture recognition and interaction method based on depth-level separable convolution network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |