CN104656101A - Obstacle detection method - Google Patents
Obstacle detection method Download PDFInfo
- Publication number
- CN104656101A CN104656101A CN201510050173.9A CN201510050173A CN104656101A CN 104656101 A CN104656101 A CN 104656101A CN 201510050173 A CN201510050173 A CN 201510050173A CN 104656101 A CN104656101 A CN 104656101A
- Authority
- CN
- China
- Prior art keywords
- barrier
- point
- detection method
- obstacle
- laser radar
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an obstacle detection method which comprises the following steps: obtaining actually measured linear distance ri between a point i and a light beam i through an all-round looking laser radar; obtaining actually measured linear distance ri-1 between two adjacent light beams i-1 through the all-round looking laser radar, and calculating the actually measured distance difference di=ri-(ri-1); obtaining the anticipated distance difference of the point i; comparing di' with di, and if the absolute value of di-di' is larger than the preset valve, the fact that an obstacle exists at the point i is shown. Through the adoption of the scheme, the detection of the obstacle at a specific height can be realized, so that accidents, which are caused by the fact that a motor vehicle encounters the obstacle during the process of automatically driving, can be avoided.
Description
Technical field
The present invention relates to the Detection Techniques field of barrier in automatic Pilot process, particularly relate to a kind of obstacle detection method.
Background technology
The main challenge of automatic Pilot to evading of barrier, most important for safety traffic.If can not direction barrier in time, then probably cause serious security incident.The prerequisite of avoiding barrier finds barrier, and the information realization that namely will collect by sensor is to the detection of barrier.
The existing detection method to barrier comprises looks around laser ranging method, and looking around laser ranging method is main barrier searching method.Because looking around laser radar is unique 360 degree, the sensor of three-dimensional, panoramic scanning on motor vehicle, so telemetry is based on the data point of looking around laser radar and gathering.
This method Main Basis, contrast is radiated at data point on barrier and the contiguous irradiation data point on (road surface) on non-barrier, and the elevation information that both return exists obviously difference.Barrier common on road, as pedestrian, road sign, other motor vehicles, bicycle, isolated column and curb etc., all shows significantly height distinction.
Although each data point of looking around laser radar both provides relative altitude information, telemetry does not adopt these original elevation informations, because:
1. because real Instrumental exists error, so there is error in the height value in data point.The degree of accuracy of height value can not stablize the lower barrier of some relative heights of differentiation usually.Even and if barrier very little on road (as brick, pedestrian precinct etc.), if can not accurately and timely find, danger may be brought to the traveling of motor vehicle.
2. the distance of this error and barrier is proportional, and data point error far away may be larger.
Another available information is the air line distance information that data point returns.In the process of rotation sweep, each laser beam of looking around laser radar scans downwards with a fixing angle (angle relative to radar).The scanning spot track stayed on object after (360 degree) are enclosed in a beam flying one forms an aperture.When look around Laser Radar Scanning definitely smooth ground time, the radius of each aperture is fixing.When ground unevenness exists barrier, the radius of aperture will correspondingly reduce.
By contrast, in a scanning tangent plane, the difference of two adjacent data point height values is for height change between two analyzing spots (point of laser beam comes into contact barrier), and the difference that can not show a candle to these two data points distances is come responsive.Main because:
1. the height value (decimeter grade) of low obstructions will lower than air line distance (decimeter grade) magnitude.
2. the angle of looking around light beam and ground time laser radar scans downwards is relatively little, and motor-car of disembarking local angle far away is about little, therefore sensitiveer on the contrary for height change.This programme will propose a kind of method that difference based on looking around the data point distance that scanning laser radar gets obtains barrier just.
Summary of the invention
For this reason, need to provide a kind of detection of obstacles scheme, solve motor vehicle to the problem of detection of obstacles and the detection of obstacles problem of looking around laser radar.
For achieving the above object, inventor provide a kind of obstacle detection method, comprise the steps:
By looking around the actual measurement air line distance r of laser radar acquisition point i light beam i
i;
The actual measurement air line distance r of adjacent beams i-1 is obtained by looking around laser radar
i-1;
Calculate measured distance difference d
i=r
i-r
i-1;
The range difference d of acquisition point i expection
i';
Contrast d
i' and d
iif, | d
i-d
i' | be greater than a preset value, then putting i place has barrier.
Further, described " the range difference d of acquisition point i expection
i' " comprise the steps:
Obtain the height h looking around laser radar and ground;
Acquisition point i departs from vertical angle θ;
The range difference d of invocation point i expection is calculated according to h and θ
i'.
Further, pavement-height immediately below the height of unsettled barrier and barrier is obtained;
Judge whether the difference of pavement-height immediately below the height of unsettled barrier and barrier is greater than default safe altitude,
If be greater than, get rid of this unsettled barrier;
Otherwise described unsettled barrier is barrier.
Further, scanned by two dimensional surface scanning laser radar;
Judge whether to get the light beam returned;
If had, then data point corresponding to the light beam returned is for being obstacle object point.
Further, the slope on road surface is obtained;
If slope rising value in unit distance in road surface is greater than slope preset value;
Then assert that described road surface is road edge.
Further, the barrier blocked before road edge is filtered out;
Utilize Ha Er to change, extract road edge point.
Further, according to obstacle information regeneration barrier thing information to barrier map.
Further, according to the information updating obstacle information of obstacle information and barrier corresponding point to barrier map.
Be different from prior art, technique scheme can realize the detection to certain height barrier, thus motor vehicle is accidents caused can avoid encountering barrier in automatic Pilot process after.
Accompanying drawing explanation
Fig. 1 is the detection of obstacles schematic diagram of looking around laser radar.
Embodiment
By describe in detail technical scheme technology contents, structural attitude, realized object and effect, coordinate accompanying drawing to be explained in detail below in conjunction with specific embodiment.
Refer to shown in Fig. 1, the present embodiment provides a kind of obstacle detection method, and this method can be applied in the control module of motor vehicle 1, for realizing the detection to barrier.Control module is connected with looks around laser radar 2, looks around laser radar 2 and is generally arranged on motor vehicle 1 roof, and looking around laser radar can carry out 360.Laser scanning, the environmental information residing for motor vehicle can be got, comprise information of road surface.
This method, when carrying out detection of obstacles, comprises the steps: the actual measurement air line distance r by looking around laser radar acquisition point i light beam i
i; The actual measurement air line distance r of adjacent beams i-1 is obtained by looking around laser radar
i-1; Calculate measured distance difference d
i=r
i-r
i-1; The range difference d of acquisition point i expection
i'; Contrast d
i' and d
iif, | d
i-d
i' | be greater than a preset value, then putting i place has barrier.As shown in Figure 1, when an i does not have barrier time, ri actual measurement (actual measurement) air line distance is looks around the distance of laser radar 2 to some i, now r
i-r
i-1namely be the range difference d of expection
i', i.e. d
i' be range difference when be all plane be on road surface adjacent beams, this differs from relevant with the order of light beam.When there being the barrier of certain altitude, barrier can block the laser beam of an i, and the actual measurement air line distance of light beam i is shortened, if the distance shortened is greater than a preset value, then control module can assert that there is barrier at an i place.Wherein, the obstacle height that this preset value can allow according to motor vehicle sets,
In certain embodiments, the range difference of expection can prestore in the control module by the mode of a table.In certain embodiments, the range difference of expection can by calculating in real time, and concrete calculation procedure comprises: obtain the height h looking around laser radar and ground; Acquisition point i departs from vertical angle θ; The range difference d of invocation point i expection is calculated according to h and θ
i'.Can represent by a funtcional relationship: d
i'=f (i, h, θ).Although desired distance difference d
i' r can be used simply
i'-r
i-1' estimation, but consider in actual travel process, attitude pitch or left and right roll along with motion of vehicle body, looks around laser radar relative to the position that road surface projects also in continuous change.For example, when the Right deviation of motor vehicle, the actual measurement air line distance being positioned at the motor vehicle left side also can become large.Therefore desired value more effectively can get rid of the interference of attitudes vibration with a function relevant with vertical angles.
Highly visibly different object can be considered as barrier by this method without exception, but may produce some false positives like this.As tree crown, other these motor vehicles of unsettled object of bridge can from below by object.In order to filter this kind of false positive, method is:
The height on road surface immediately below the obstacle object point of contrast obstacle object point height and road surface model prediction.If the overall height that difference in height is greater than motor vehicle adds certain safe distance, then get rid of this obstacle object point.Motor vehicle overall height and safe distance and can be regarded as default safe altitude.Namely unsettled barrier is that obstacle object point part does not contact with ground.
Although it is powerful to look around laser radar, but still there are some dead angles.Owing to being arranged on roof, dead angle mainly near vehicle body caused by this vehicle body blocks.In these dead angles, the scanning laser radar of two dimension is installed.
Be different from and look around laser radar, two dimensional surface scanning laser radar is surface level (parallel with road surface), is generally arranged on motorcar body surrounding, and the data point returned does not have height value, only has distance.Therefore, in effective range, the data point of each light beam returned is considered to obstacle object point.Then can carry out scanning by two dimensional surface scanning laser radar and obtain barrier.Judge whether to get the light beam returned; If had, then data point corresponding to the light beam returned is for being obstacle object point.
Pavement edge is also a kind of barrier for motor vehicle, and this method also includes the detection at road pavement edge, utilization be the elevation information of laser data point.From each scanning tangent plane, according to the variation characteristic of height, extract a road edge point.Road edge point on all scanning tangent planes just constitutes road edge feature.This method is all applicable for road edge pattern miscellaneous, no matter is roadside irrigation canals and ditches, embankment or edges of pavements etc.
This method supposition, on a scanning tangent plane, if the road surface slope of relatively flat rises suddenly in short distance, is likely what road edge caused.Then when detecting, the slope on road surface can be obtained; If slope rising value in unit distance in road surface is greater than slope preset value; Then assert that described road surface is road edge.Slope preset value also can be prestored in the control module by manufacturer.
From the data of height, directly accurately and reliably look for road edge point relative difficulty, method is here two steps: the first step, filters out the barrier that may block before road edge.
In a scanning tangent plane, may exist than the barrier (as road cone) of road edge closer to motor vehicle.If these barriers are not filtered out, then can affect the accuracy that road edge detection method extracts feature, because these prospect barriers are taken as road edge possibly.
Particularly, in original laser data:
1. find height apparently higher than road edge, and,
2. be gathered in the data point of a piece, namely data point looks around the point that laser radar sends the road information that light beam gathers.According to the distance grouping between data point, be grouped together apart near data point.Filter out the group of number of data points higher than critical value.
Second step, utilizes Ha Er to change, and extracts road edge point.Wherein, Ha Er transformation energy suppresses noise effectively, presents the average tendency of data under various different wave length (resolution).If Ha Er to be changed the Height value data be used on a tangent plane, the Ha Er coefficient drawn reflects on this tangent plane under certain resolution, through the average gradient of convergent-divergent.The all data values of window involved by this coefficient of calculating that Ha Er coefficient is corresponding, the higher window of resolution is less.
First 2 to be extracted
nindividual height value.In order to carry out the Ha Er conversion under multistage (multiresolution), need the number of height value be 2 whole power (namely 2
n, n is integer), and require that the distance between data point is equal.But the data point number of laser radar on a tangent plane is not probably the whole power of 2, and spacing not etc.So in order to generate 2
nindividual height value, method is:
1. determine that the value of n is, if data point adds up to m on a tangent plane, makes 2
nthe minimum n of > m.
2. according to the sum 2 of data point
n, and the distance r that data point is crossed over, draw mean distance
3. use linear resample method, utilize the height value of original data point, generate every distance d the interpolation that a new height value is contiguous two original height values.Finally draw a height value vector v.The virtual data point (containing the coordinate system informations that interpolation is crossed) that each new height value correspondence one is new.
Then judge the virtual data point belonging to road circle point.Use Ha Er conversion, obtain the Ha Er coefficient vector y of v under different resolution i
i.Being specifically defined as of Ha Er conversion:
The morther wavelet of Haar wavelet transform:
The scaling function of its correspondence is:
Minimum window contains the data point of approximately several centimetres wide.The size of window under each resolution is 2 times of window size under a low class resolution ratio.Make minimum resolution sequence number be i, corresponding Ha Er coefficient vector is y
i, from most end resolution (maximized window):
1. give y
iin each Ha Er coefficient y
igive a label value (label value is 0 or 1, and the 3rd step describes in detail).The label value of the Ha Er coefficient that label value is corresponding under equaling a resolution (i-1).With y
icorresponding Ha Er coefficient is defined as: under a upper resolution, data window includes y
ithe Ha Er coefficient of included data.
2. calculate the average gradient on road surface
the mean value of the label value of all Ha Er coefficients under equaling current resolution.
3. again give label value to all Ha Er coefficients under current resolution, be specifically judged as:
Wherein, d
ifor the threshold values under this resolution
4. under i+1, repeat above step.
Finally, each label virtual data Dian Wei road circle point corresponding to Ha Er coefficient that is 1.
Threshold values d under each resolution
idifference, larger window threshold values is larger.Concrete d
ivalue depends on the road surface/road circle Morphological Features of current road segment, is provided by electronic chart.Electronic chart belongs to the actual detection calibration d of method in the virtual data point of road circle point in advance according to above-mentioned judgement
ivalue, the storage map in the control module that electronic chart namely in advance gathers, as in each navigation software the map that adopts.
Arbitrary particular moment in the process of motor-driven vehicle going, sensor is all an aspect of whole environment for the perception of home environment, because the limited view of sensor is in self position with other barriers.Therefore, only have and time integral is carried out to the various information of sensor, could farthest obtain home environment information the most accurately.
Local barrier map is a grid map, and each grid is square, in the same size, is called cell.Each cell only has two kinds of possible states, has barrier and clear.
Time integral implication is here, sensing data renewal each time triggers certain barrier searching method and produces new obstacle information, all be fused on existing barrier map by a kind of method, namely will according to obstacle information regeneration barrier thing information to barrier map.Therefore barrier map is not instantaneous, but continuously, comprise certain memory.
A kind of simple update rule is, for the obstacle information of each new generation, directly rewrite the barrier state of the cell on the barrier map of its correspondence.But this method have ignored the information value that the original state of this cell comprises---in many cases, the barrier state of the barrier state that cell is new and this cell original is not separate on probability.If this statistical dependence can be utilized, these two kinds of information comprehensive before renewal cell state, namely according to the information updating obstacle information of obstacle information and barrier corresponding point to barrier map, then effectively can improve the accuracy of update rule.
Bayes' theorem provides so framework, can comprehensive two independently information sources:
P(o|A∩B)∝P(o)·P(A∩B|o) (1)
Another form of formula (1) is:
Here, A is the old state of this cell, and B is the new barrier judgment of certain barrier searching method.O represents that this cell is barrier,
represent that this cell is not barrier, A ∩ B represents the simultaneous probability of A and B, P (o|A ∩ B) for this cell be the posterior probability of barrier.
Each different barrier searching method needs to build oneself independently bayesian probability model, and when being used for determining that this barrier searching method produces new obstacle information, cell is the posterior probability of barrier.
After showing that this cell is the posterior probability of barrier, if probability is higher than a threshold values, then this cell is barrier.This threshold values determines according to the situation of reality, and low valve valve produces the relatively many barrier maps of a barrier, otherwise the barrier map that high threshold values produces is relatively conservative.
It should be noted that, laser sensor owing to blocking not regeneration barrier thing map (not supposing any obstacle information) in invisible region.
Information on barrier map retains a period of time.If motor vehicle does not have a updated cell within a certain period of time, so in order to keep the ageing of memory, the information of this cell is eliminated from internal memory.
It should be noted that, in this article, the such as relational terms of first and second grades and so on is only used for an entity or operation to separate with another entity or operational zone, and not necessarily requires or imply the relation that there is any this reality between these entities or operation or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, article or terminal device and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, article or terminal device.When not more restrictions, the key element limited by statement " comprising ... " or " comprising ... ", and be not precluded within process, method, article or the terminal device comprising described key element and also there is other key element.In addition, in this article, " be greater than ", " being less than ", " exceeding " etc. be interpreted as and do not comprise this number; " more than ", " below ", " within " etc. be interpreted as and comprise this number.
Those skilled in the art should understand, the various embodiments described above can be provided as method, device or computer program.These embodiments can adopt the form of complete hardware embodiment, completely software implementation or the embodiment in conjunction with software and hardware aspect.The hardware that all or part of step in the method that the various embodiments described above relate to can carry out instruction relevant by program has come, described program can be stored in the storage medium that computer equipment can read, for performing all or part of step described in the various embodiments described above method.Described computer equipment, includes but not limited to: personal computer, server, multi-purpose computer, special purpose computer, the network equipment, embedded device, programmable device, intelligent mobile terminal, intelligent home device, wearable intelligent equipment, vehicle intelligent equipment etc.; Described storage medium, includes but not limited to: the storage of RAM, ROM, magnetic disc, tape, CD, flash memory, USB flash disk, portable hard drive, storage card, memory stick, the webserver, network cloud storage etc.
The various embodiments described above describe with reference to the process flow diagram of method, equipment (system) and computer program according to embodiment and/or block scheme.Should understand can by the combination of the flow process in each flow process in computer program instructions realization flow figure and/or block scheme and/or square frame and process flow diagram and/or block scheme and/or square frame.These computer program instructions can being provided to the processor of computer equipment to produce a machine, making the instruction performed by the processor of computer equipment produce device for realizing the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
These computer program instructions also can be stored in can in the computer equipment readable memory that works in a specific way of vectoring computer equipment, the instruction making to be stored in this computer equipment readable memory produces the manufacture comprising command device, and this command device realizes the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
These computer program instructions also can be loaded on computer equipment, make to perform sequence of operations step on a computing device to produce computer implemented process, thus the instruction performed on a computing device is provided for the step realizing the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
Although be described the various embodiments described above; but those skilled in the art are once obtain the basic creative concept of cicada; then can make other change and amendment to these embodiments; so the foregoing is only embodiments of the invention; not thereby scope of patent protection of the present invention is limited; every utilize instructions of the present invention and accompanying drawing content to do equivalent structure or equivalent flow process conversion; or be directly or indirectly used in other relevant technical fields, be all in like manner included within scope of patent protection of the present invention.
Claims (8)
1. an obstacle detection method, is characterized in that, comprises the steps:
By looking around the actual measurement air line distance r of laser radar acquisition point i light beam i
i;
The actual measurement air line distance r of adjacent beams i-1 is obtained by looking around laser radar
i-1;
Calculate measured distance difference d
i=r
i-r
i-1;
The range difference d of acquisition point i expection
i';
Contrast d
i' and d
iif, | d
i-d
i' | be greater than a preset value, then putting i place has barrier.
2. obstacle detection method according to claim 1, is characterized in that, described " the range difference d of acquisition point i expection
i' " comprise the steps:
Obtain the height h looking around laser radar and ground;
Acquisition point i departs from vertical angle θ;
The range difference d of invocation point i expection is calculated according to h and θ
i'.
3. obstacle detection method according to claim 1, is characterized in that, also comprises the steps:
Obtain pavement-height immediately below the height of unsettled barrier and barrier;
Judge whether the difference of pavement-height immediately below the height of unsettled barrier and barrier is greater than default safe altitude,
If be greater than, get rid of this unsettled barrier;
Otherwise described unsettled barrier is barrier.
4. obstacle detection method according to claim 1, is characterized in that, also comprises the steps:
Scanned by two dimensional surface scanning laser radar;
Judge whether to get the light beam returned;
If had, then data point corresponding to the light beam returned is for being obstacle object point.
5. obstacle detection method according to claim 1, is characterized in that, also comprises the steps: the slope obtaining road surface;
If slope rising value in unit distance in road surface is greater than slope preset value;
Then assert that described road surface is road edge.
6. obstacle detection method according to claim 5, is characterized in that, also comprises step:
Filter out the barrier blocked before road edge;
Utilize Ha Er to change, extract road edge point.
7. the obstacle detection method according to any one of claim 1-6, is characterized in that, also comprises step:
According to obstacle information regeneration barrier thing information to barrier map.
8. obstacle detection method according to claim 7, is characterized in that, also comprises step:
According to the information updating obstacle information of obstacle information and barrier corresponding point to barrier map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510050173.9A CN104656101B (en) | 2015-01-30 | 2015-01-30 | A kind of obstacle detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510050173.9A CN104656101B (en) | 2015-01-30 | 2015-01-30 | A kind of obstacle detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104656101A true CN104656101A (en) | 2015-05-27 |
| CN104656101B CN104656101B (en) | 2015-11-18 |
Family
ID=53247455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510050173.9A Active CN104656101B (en) | 2015-01-30 | 2015-01-30 | A kind of obstacle detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104656101B (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105466433A (en) * | 2015-12-04 | 2016-04-06 | 北海创思电子科技产业有限公司 | Navigation system with intelligent updating function |
| CN105571599A (en) * | 2015-12-21 | 2016-05-11 | 小米科技有限责任公司 | Road condition information processing method and device |
| CN105891838A (en) * | 2015-08-25 | 2016-08-24 | 乐卡汽车智能科技（北京）有限公司 | Distance detection method and device |
| CN105911553A (en) * | 2016-04-15 | 2016-08-31 | 北京信息科技大学 | Determination method and system for road feasible region |
| CN106705971A (en) * | 2016-11-21 | 2017-05-24 | 上海斐讯数据通信技术有限公司 | Blind people navigation method and system |
| CN107315181A (en) * | 2016-04-26 | 2017-11-03 | 零度智控（北京）智能科技有限公司 | A kind of barrier-avoiding method and device, aircraft |
| CN107368067A (en) * | 2016-05-12 | 2017-11-21 | 深圳市朗驰欣创科技股份有限公司 | A kind of pavement detection method and system of automatic navigation vehicle |
| WO2018119902A1 (en) * | 2016-12-29 | 2018-07-05 | 华为技术有限公司 | Method and apparatus for detecting ground environment |
| CN108363065A (en) * | 2017-01-17 | 2018-08-03 | 德尔福技术有限公司 | Object detecting system |
| CN108398672A (en) * | 2018-03-06 | 2018-08-14 | 厦门大学 | Road surface based on the 2D laser radar motion scans that lean forward and disorder detection method |
| CN108845371A (en) * | 2018-08-20 | 2018-11-20 | 电子科技大学 | A kind of safety inspection method and device based on THz wave |
| CN109254289A (en) * | 2018-11-01 | 2019-01-22 | 百度在线网络技术（北京）有限公司 | The detection method and detection device of road guard |
| CN110008941A (en) * | 2019-06-05 | 2019-07-12 | 长沙智能驾驶研究院有限公司 | Drivable region detection method, device, computer equipment and storage medium |
| CN110215341A (en) * | 2019-06-18 | 2019-09-10 | 深圳市中诺通讯有限公司 | A kind of method and system suitable for blind person's trip |
| CN110598505A (en) * | 2018-06-12 | 2019-12-20 | 海信集团有限公司 | Method and device for judging suspension state of obstacle and terminal |
| CN111337022A (en) * | 2020-04-10 | 2020-06-26 | 深圳市银星智能科技股份有限公司 | Target obstacle detection method and device and robot |
| CN111469793A (en) * | 2016-04-28 | 2020-07-31 | 赵忠尧 | Vehicle-mounted front anti-collision system based on laser radar |
| CN111469127A (en) * | 2020-04-14 | 2020-07-31 | 北京海益同展信息科技有限公司 | Cost map updating method and device, robot and storage medium |
| CN111578932A (en) * | 2020-05-28 | 2020-08-25 | 长沙中联重科环境产业有限公司 | Image establishing method, device, medium and equipment based on multi-line laser radar |
| CN115016024A (en) * | 2022-06-22 | 2022-09-06 | 北京讯通安添通讯科技有限公司 | Obstacle identification method, device, storage medium and device applied to mobile phone |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020091479A1 (en) * | 2001-01-09 | 2002-07-11 | Nissan Motor Co., Ltd. | Braking control system with object detection system interaction |
| US20040119634A1 (en) * | 2002-12-19 | 2004-06-24 | Yoshie Samukawa | Obstacle detection system for automotive vehicle |
| CN1834686A (en) * | 2005-03-17 | 2006-09-20 | 三洋电机株式会社 | Detection device |
| CN101357642A (en) * | 2008-09-03 | 2009-02-04 | 中国科学院上海技术物理研究所 | Vehicle-mounted automatic obstacle avoidance system and obstacle avoidance method for high-speed railway |
| CN103112451A (en) * | 2013-02-06 | 2013-05-22 | 刘兆雄 | Automobile automatic collision avoidance system and method |
-
2015
- 2015-01-30 CN CN201510050173.9A patent/CN104656101B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020091479A1 (en) * | 2001-01-09 | 2002-07-11 | Nissan Motor Co., Ltd. | Braking control system with object detection system interaction |
| US20040119634A1 (en) * | 2002-12-19 | 2004-06-24 | Yoshie Samukawa | Obstacle detection system for automotive vehicle |
| CN1834686A (en) * | 2005-03-17 | 2006-09-20 | 三洋电机株式会社 | Detection device |
| CN101357642A (en) * | 2008-09-03 | 2009-02-04 | 中国科学院上海技术物理研究所 | Vehicle-mounted automatic obstacle avoidance system and obstacle avoidance method for high-speed railway |
| CN103112451A (en) * | 2013-02-06 | 2013-05-22 | 刘兆雄 | Automobile automatic collision avoidance system and method |
Non-Patent Citations (2)
| Title |
|---|
| 蔡自兴，肖正，于金霞: "基于激光雷达的动态障碍物实时检测", 《控制工程》, vol. 15, no. 2, 31 March 2008 (2008-03-31) * |
| 赵一兵，王荣本，李琳辉，金立生，郭烈: "基于激光雷达的无人驾驶车前方障碍物检测", 《交通与计算机》, vol. 25, no. 2, 28 February 2007 (2007-02-28) * |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105891838A (en) * | 2015-08-25 | 2016-08-24 | 乐卡汽车智能科技（北京）有限公司 | Distance detection method and device |
| CN105466433A (en) * | 2015-12-04 | 2016-04-06 | 北海创思电子科技产业有限公司 | Navigation system with intelligent updating function |
| CN105571599A (en) * | 2015-12-21 | 2016-05-11 | 小米科技有限责任公司 | Road condition information processing method and device |
| CN105911553A (en) * | 2016-04-15 | 2016-08-31 | 北京信息科技大学 | Determination method and system for road feasible region |
| CN105911553B (en) * | 2016-04-15 | 2019-01-01 | 北京信息科技大学 | A kind of road feasible zone determines method and system |
| CN107315181A (en) * | 2016-04-26 | 2017-11-03 | 零度智控（北京）智能科技有限公司 | A kind of barrier-avoiding method and device, aircraft |
| CN107315181B (en) * | 2016-04-26 | 2020-11-06 | 天津远度科技有限公司 | Obstacle avoidance method and device and aircraft |
| CN111469793A (en) * | 2016-04-28 | 2020-07-31 | 赵忠尧 | Vehicle-mounted front anti-collision system based on laser radar |
| CN107368067B (en) * | 2016-05-12 | 2022-08-23 | 深圳市朗驰欣创科技股份有限公司 | Road surface detection method and system of automatic navigation vehicle |
| CN107368067A (en) * | 2016-05-12 | 2017-11-21 | 深圳市朗驰欣创科技股份有限公司 | A kind of pavement detection method and system of automatic navigation vehicle |
| CN106705971A (en) * | 2016-11-21 | 2017-05-24 | 上海斐讯数据通信技术有限公司 | Blind people navigation method and system |
| CN106705971B (en) * | 2016-11-21 | 2021-01-08 | 台州市吉吉知识产权运营有限公司 | Navigation method and system for blind people |
| US11455511B2 (en) | 2016-12-29 | 2022-09-27 | Huawei Technologies Co., Ltd. | Ground environment detection method and apparatus |
| CN110114692B (en) * | 2016-12-29 | 2021-09-17 | 华为技术有限公司 | Ground environment detection method and device |
| CN110114692A (en) * | 2016-12-29 | 2019-08-09 | 华为技术有限公司 | A kind of detection method and device of ground environment |
| WO2018119902A1 (en) * | 2016-12-29 | 2018-07-05 | 华为技术有限公司 | Method and apparatus for detecting ground environment |
| CN108363065A (en) * | 2017-01-17 | 2018-08-03 | 德尔福技术有限公司 | Object detecting system |
| CN108398672A (en) * | 2018-03-06 | 2018-08-14 | 厦门大学 | Road surface based on the 2D laser radar motion scans that lean forward and disorder detection method |
| CN108398672B (en) * | 2018-03-06 | 2020-08-14 | 厦门大学 | Pavement and obstacle detection method based on forward tilting 2D lidar mobile scanning |
| CN110598505A (en) * | 2018-06-12 | 2019-12-20 | 海信集团有限公司 | Method and device for judging suspension state of obstacle and terminal |
| CN108845371B (en) * | 2018-08-20 | 2020-11-03 | 电子科技大学 | A security inspection method and device based on terahertz waves |
| CN108845371A (en) * | 2018-08-20 | 2018-11-20 | 电子科技大学 | A kind of safety inspection method and device based on THz wave |
| CN109254289A (en) * | 2018-11-01 | 2019-01-22 | 百度在线网络技术（北京）有限公司 | The detection method and detection device of road guard |
| CN110008941A (en) * | 2019-06-05 | 2019-07-12 | 长沙智能驾驶研究院有限公司 | Drivable region detection method, device, computer equipment and storage medium |
| CN110008941B (en) * | 2019-06-05 | 2020-01-17 | 长沙智能驾驶研究院有限公司 | Method and device for detecting travelable area, computer equipment and storage medium |
| CN110215341A (en) * | 2019-06-18 | 2019-09-10 | 深圳市中诺通讯有限公司 | A kind of method and system suitable for blind person's trip |
| CN110215341B (en) * | 2019-06-18 | 2022-04-08 | 深圳市中诺通讯有限公司 | Method and system suitable for blind people to go out |
| CN111337022B (en) * | 2020-04-10 | 2022-01-21 | 深圳市银星智能科技股份有限公司 | Target obstacle detection method and device and robot |
| CN111337022A (en) * | 2020-04-10 | 2020-06-26 | 深圳市银星智能科技股份有限公司 | Target obstacle detection method and device and robot |
| CN111469127B (en) * | 2020-04-14 | 2022-06-07 | 京东科技信息技术有限公司 | Cost map updating method and device, robot and storage medium |
| CN111469127A (en) * | 2020-04-14 | 2020-07-31 | 北京海益同展信息科技有限公司 | Cost map updating method and device, robot and storage medium |
| CN111578932A (en) * | 2020-05-28 | 2020-08-25 | 长沙中联重科环境产业有限公司 | Image establishing method, device, medium and equipment based on multi-line laser radar |
| CN111578932B (en) * | 2020-05-28 | 2021-12-24 | 长沙中联重科环境产业有限公司 | Image establishing method, device, medium and equipment based on multi-line laser radar |
| CN115016024A (en) * | 2022-06-22 | 2022-09-06 | 北京讯通安添通讯科技有限公司 | Obstacle identification method, device, storage medium and device applied to mobile phone |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104656101B (en) | 2015-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104656101B (en) | A kind of obstacle detection method | |
| CN110850439B (en) | High-precision three-dimensional point cloud map construction method | |
| CN111551958B (en) | Mining area unmanned high-precision map manufacturing method | |
| CN103176185B (en) | Method and system for detecting road barrier | |
| US20240190423A1 (en) | Polyline contour representations for autonomous vehicles | |
| CN105404844B (en) | A kind of Method for Road Boundary Detection based on multi-line laser radar | |
| CN103500338B (en) | Automatic extraction method of road zebra crossing based on vehicle laser scanning point cloud | |
| CN106199558A (en) | Barrier method for quick | |
| CN106842231A (en) | A kind of road edge identification and tracking | |
| KR101822373B1 (en) | Apparatus and method for detecting object | |
| Wang et al. | Automatic road extraction from mobile laser scanning data | |
| EP2948928A1 (en) | Modifying behavior of autonomous vehicles based on sensor blind spots and limitations | |
| CN113009453B (en) | Mine road edge detection and mapping method and device | |
| CN109241855B (en) | A detection method of intelligent vehicle driving area based on stereo vision | |
| CN113870337A (en) | Ground point cloud segmentation method based on polar coordinate grid and plane fitting | |
| Steinke et al. | Groundgrid: Lidar point cloud ground segmentation and terrain estimation | |
| Wu et al. | Grid-based lane identification with roadside LiDAR data | |
| US11555928B2 (en) | Three-dimensional object detection with ground removal intelligence | |
| Prophet et al. | CNN based road course estimation on automotive radar data with various gridmaps | |
| Sun et al. | Mathematical method for Lidar-based obstacle detection of intelligent vehicle | |
| US20220196828A1 (en) | Radar Reference Map Generation | |
| Zhang et al. | Smart-degradation: A dataset for lidar degradation evaluation in rain | |
| Rahman | Uses and Challenges of Collecting LiDAR Data from a Growing Autonomous Vehicle Fleet: Implications for Infrastructure Planning and Inspection Practices | |
| Wu | Data processing algorithms and applications of LiDAR-enhanced connected infrastructure sensing | |
| CN114910881A (en) | Negative obstacle detection method and device and vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |