CN104197897A - Urban road marker automatic sorting method based on vehicle-mounted laser scanning point cloud - Google Patents
Urban road marker automatic sorting method based on vehicle-mounted laser scanning point cloud Download PDFInfo
- Publication number
- CN104197897A CN104197897A CN201410171408.5A CN201410171408A CN104197897A CN 104197897 A CN104197897 A CN 104197897A CN 201410171408 A CN201410171408 A CN 201410171408A CN 104197897 A CN104197897 A CN 104197897A
- Authority
- CN
- China
- Prior art keywords
- roadmarking
- strip
- point cloud
- point
- line
- 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
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
-
- 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
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Remote Sensing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Radar, Positioning & Navigation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
- Road Repair (AREA)
Abstract
The invention discloses an urban road marker automatic sorting method based on vehicle-mounted laser scanning point cloud. The method includes: S1) a step of subjecting original point cloud data to road surface segmentation based on wheel path data to obtain road surface point cloud data; S2) a step of subjecting the obtained road surface point cloud data to binarization processing and extracting road marker points; S3) a step of clustering the road marker points and separating independent road marker targets; S4) a step of sorting large road markers and small road markers according to the dimensions of the obtained road marker targets; S5) a step of subjecting the large road markers to sorting processing based on wheel paths and road edge lines; and S6) a step of subjecting the small road markers to sorting processing based on deep learning and principal component analysis. The method rapidly and accurately extracts and sorts urban road markers, largely reduces the time and labor cost for data processing, and effectively guarantees traffic safety and intelligent drive reliability.
Description
Technical field
The present invention relates to intelligent transportation system and wisdom urban construction field, relate in particular to a kind of downtown roads graticule automatic classification method based on Vehicle-borne Laser Scanning point cloud.
Background technology
Downtown roads graticule, as the important composition element of traffic monitoring system, is being brought into play irreplaceable effect in numerous urban infrastructures.On the one hand, it can regulation and control vehicle and pedestrian's behavioral activity, has effectively reduced the generation of traffic hazard, for vehicle and pedestrian's safety provides guarantee; On the other hand, its classification and positional information can be used as the important input of intelligent driving system, contribute to improve the reliability of intelligent driving.Therefore, traffic control department and intelligent transportation system are badly in need of a kind of quick, real-time for extracting and the system of the downtown roads graticule of classifying, thereby guarantee the security of traffic and the reliability of intelligent driving.
At present, the extraction of downtown roads graticule and classification are mainly based on image or video data.Main method comprises that shape is cut apart, Texture Segmentation and the dividing method based on geometric properties.Common downtown roads graticule extracting method has: Markov model method, condition random field method and machine learning method.Yet these methods are mainly subject to the constraint of the following aspects: the diversity of (1) downtown roads graticule shape and type; (2) illumination condition of data acquisition and time; (3) shade that moving vehicle causes with block; (4) the roadmarking shape distortion that image or video data produce.Therefore, the method based on image or video also cannot meet the demand that downtown roads graticule automatically extracts and classifies.
In recent years, Vehicle-borne Laser Scanning technical development was very rapid.It fast, accurately obtains the ability of Three Dimensional Ground spatial information, is more and more subject to people's great attention.Unique design form and the two laser head scan modes of staggered form due to Vehicle-borne Laser Scanning system, Vehicle-borne Laser Scanning system not only possesses airborne laser scanning system can gather the characteristic of data on a large scale, and can reach data precision and dot density that territorial laser scanning system possesses.Therefore, Vehicle-borne Laser Scanning system becomes a kind of important technical of city space information acquisition gradually.
Yet how from high density, high-precision magnanimity Vehicle-borne Laser Scanning cloud data, extraction landform, characters of ground object are challenges that the research and development of cloud post-processing technology face automatically.From magnanimity point cloud, extract quickly and automatically and classify accurately, effectively characters of ground object is also still in the starting stage.
Summary of the invention
The object of the present invention is to provide a kind of downtown roads graticule automatic classification method based on Vehicle-borne Laser Scanning point cloud.
For achieving the above object, the present invention is by the following technical solutions:
A downtown roads graticule automatic classification method based on Vehicle-borne Laser Scanning point cloud, comprises the following steps:
S1, based on wheelpath data, original point cloud data is carried out to road surface and cut apart, obtain road surface cloud data;
S2, described road surface cloud data is carried out to binary conversion treatment, and extract roadmarking point;
S3, described roadmarking point is carried out to cluster, isolate roadmarking target independent of each other;
S4, according to the size of described roadmarking target, sort out large scale roadmarking and small scale roadmarking;
S5, the classification that described large scale roadmarking is carried out based on wheelpath and curb line are processed, and sort out stop line, center line and boundary line;
S6, the classification that described small scale roadmarking is carried out based on degree of depth study and principal component analysis (PCA) are processed, and sort out direction mark, pedestrian's warning label, zebra stripes, center line and boundary line.
Preferably, described step S1 specifically comprises step by step following:
S11, original point cloud data is evenly divided into one group of some cloud mass along the direction of wheelpath;
S12, for each some cloud mass, along being syncopated as a some cloud perpendicular to the direction of wheelpath, cut open sheet, and from a cloud, cut open sheet and extract curb point;
S13, all curb points are carried out to matching, obtain curb line;
S14, original point cloud data is cut apart along curb line, obtained road surface cloud data.
Preferably, described step S2 specifically comprises step by step following:
S21, described road surface cloud data is divided into one group road surface point cloud burst to both sides with a certain division interval along wheelpath, adopts OTSU binarization method to carry out respectively binary conversion treatment to each road surface point cloud burst, and extract roadmarking point.
S22, calculate the space density value of each roadmarking point, if when the space density value of certain roadmarking point is less than predefined noise critical value, by its rejecting.
Preferably, described step S5 specifically comprises step by step following:
S51, to each large scale roadmarking, if it comprises multiclass roadmarking, perform step S52, if its roadmarking that comprises one type is directly designated as roadmarking unit by it;
S52, the normalization that the large scale roadmarking that comprises multiclass roadmarking is carried out based on volume elements are cut apart, and obtain semantically independently roadmarking unit;
S53, sampled in each roadmarking unit, and the distribution characteristics of calculating sampling point, whether the sampled point quantity that judgement meets direction verification condition is greater than the first predetermined threshold value, if, this roadmarking unit is labeled as to stop line, if not, perform step S54, the distribution characteristics that described direction verification condition is sampled point is perpendicular to the direction of wheelpath;
Sampled point on S54, calculating roadmarking unit and the distance of curb line, whether the sampled point quantity that judgement meets position verification condition is greater than the second predetermined threshold value, if, this roadmarking unit is labeled as to boundary line, if not, this roadmarking unit is labeled as to center line, to be sampled point be less than 1m to the distance of curb line to described position verification condition.
Preferably, described step S52 specifically comprises following sub-step:
S521, the large scale roadmarking that comprises multiclass roadmarking is carried out to volume elements, and with the volume elements point cloud mass structure full-mesh weighted graph after volume elements;
S522, based on full-mesh weighted graph, large scale roadmarking is normalized and is cut apart.
Preferably, described step S6 specifically comprises following sub-step:
S61, utilize a deep layer Boltzmann machine that comprises two-layer hidden layer of degree of deep learning method training, and the deep layer Boltzmann machine after training is configured to the sorter of a multilayer;
S62, using small scale roadmarking as the input of Multilayer Classifier, the classification information of Multilayer Classifier output small scale roadmarking, described classification information comprises strip roadmarking, direction mark, pedestrian's warning label and other roadmarkings;
S63, to each strip roadmarking P, along its Width to two-sided search width, be w
sidethe neighborhood of=1m, if there is strip roadmarking Q in its neighborhood, performs step S64, if there is not strip roadmarking in this neighborhood, performs step S65;
S64, judge whether the strip roadmarking Q in strip roadmarking P and its neighborhood meets zebra stripes decision condition, if meet, this strip roadmarking P is labeled as to zebra stripes, if do not meet, perform step S65, described zebra stripes decision condition is:
(v
p//v
q)∧(v
p//v
pq)∧(v
q//v
pq)
Wherein, some p is the geometric center of strip roadmarking P in XY plane, v
pfor the distribution characteristics of a p, some q is the geometric center of strip roadmarking Q in XY plane, v
qfor the distribution characteristics of a q, v
pqfor the direction vector of a p to a q;
S65, along the length direction of strip roadmarking P, to two-sided search width, be w
endthe neighborhood of=3m, if there is strip roadmarking G in its neighborhood, judge whether the strip roadmarking G in strip roadmarking P and its neighborhood meets intermittent line decision condition, if meet, the classification of strip roadmarking P being carried out based on wheelpath and curb line is processed, strip roadmarking P is labeled as to boundary line or center line, and described intermittent line decision condition is:
(v
p//v
g)∧(v
p//v
pg)∧(v
g//v
pg)
Wherein, some p is the geometric center of strip roadmarking P in XY plane, v
pfor the distribution characteristics of a p, some g is the geometric center of strip roadmarking G in XY plane, v
gfor the distribution characteristics of a g, v
pgfor the direction vector of a p to a g.
Adopt after technique scheme, the present invention compares with background technology, and tool has the following advantages:
1, the present invention can extract and sort out downtown roads graticule quickly and accurately, greatly reduces time and the labour cost of data processing, has effectively guaranteed the security of traffic and the reliability of intelligent driving.
2, by road pavement cloud data, carry out the burst binary conversion treatment based on wheelpath, solved laser point cloud data intensity and be excited the incident angle of light beam and the problem of target range impact, effectively improved the quality that roadmarking extracts.
3, by large scale roadmarking being carried out to the normalization dividing processing based on volume elements, effectively overlapping stop line and boundary line are separated, improved the accuracy to roadmarking classification.
4, by the classification of small scale roadmarking being carried out based on degree of depth study and principal component analysis (PCA), process, effectively improved the nicety of grading of small scale roadmarking.
Accompanying drawing explanation
Fig. 1 is workflow schematic diagram of the present invention.
Fig. 2 is the extraction result schematic diagram of curb point.
Fig. 3 is the fitting result schematic diagram of curb point.
Fig. 4 has shown the result that road surface cloud data is cut apart.
Fig. 5 has shown the binaryzation result of road surface cloud data.
Fig. 6 has shown carrying out filtered result through the road surface cloud data of binary conversion treatment.
Fig. 7 is the schematic diagram of Multilayer Classifier.
Fig. 8 is principal component analysis (PCA) schematic diagram.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Embodiment
Refer to Fig. 1, the invention discloses a kind of downtown roads graticule automatic classification method based on Vehicle-borne Laser Scanning point cloud, it comprises the following steps:
S1, road surface cloud data are cut apart
Based on wheelpath data, original point cloud data is carried out to road surface and cut apart, obtain road surface cloud data, the wheelpath data of mentioning are here that the inertial navigation system by being integrated in Vehicle-borne Laser Scanning system gathers.This step specifically realizes by following steps:
S11, original point cloud data is evenly divided into one group of some cloud mass along the direction of wheelpath, in the present embodiment, point is spaced apart 3m cutting apart of cloud mass.
S12, for each some cloud mass, along being syncopated as a some cloud perpendicular to the direction of wheelpath, cut open sheet, and from a cloud, cut open sheet and extract curb point (shown in figure 2).According to prophet's experience, the curb of road is normally perpendicular to road surface setting and higher than road surface, as long as therefore find the some cloud of highly sudden change to find curb point.The method of extracting curb point in the present embodiment is specially, and certainly puts intersection location that cloud cuts open sheet and wheelpath to two-sided search, finds the highly some cloud of sudden change, the point using it as curb.
S13, all curb points are carried out to matching, obtain curb line (shown in figure 3).
S14, original point cloud data is cut apart along curb line, obtained road surface cloud data (shown in figure 4).
It should be noted that, in order to show more intuitively extraction result and the fitting result of curb point, in Fig. 2 and Fig. 3, the cloud data of road both sides atural object omits, therefore, Fig. 2 and Fig. 3 have just shown the distribution situation of curb point and curb line, do not represent the result of step S12, S13.
S2, extraction roadmarking point
Road pavement cloud data carries out binary conversion treatment, and extracts roadmarking point.This step specifically realizes by following steps:
S21, road surface cloud data is divided into one group road surface point cloud burst to both sides with a certain division interval along wheelpath, then adopt OTSU binarization method to carry out respectively binary conversion treatment to each road surface point cloud burst, and extract roadmarking point (shown in figure 5).In the present embodiment, the division of some cloud burst is spaced apart 2m.
S22, calculate the space density value of each roadmarking point, if when the space density value of certain roadmarking point is less than predefined noise critical value, rejected (shown in figure 6).For a certain roadmarking point p (x, y, z), its space density value is defined as:
Wherein, the local neighborhood of N (p) representative point p, d
nthe size that represents neighborhood, p
i(x
i, y
i, z
i) be the point in the local neighborhood of a p.
In the present embodiment, d
nget 0.1m, noise critical value is 8.
S3, roadmarking point cluster
Roadmarking point is carried out to cluster, isolate roadmarking target independent of each other.In the present embodiment, roadmarking point is carried out to cluster and specifically with the clustering distance of 0.05m, roadmarking point is carried out to Euclidean distance cluster.In order to reduce time and the data space of subsequent step computing, can be according to the dimensional characteristic of roadmarking, roadmarking after cluster is carried out to simple goal filtering, to reject the non-roadmarking target that some sizes are little (omitting the paint vehicle on road surface, the inspection well cover close with roadmarking color etc. as roadmarking construction wrong).
S4, the classification of roadmarking target size
According to the size of roadmarking target, sort out large scale roadmarking and small scale roadmarking.For each roadmarking target, the three-dimensional coordinate information comprising a little according to it calculates its bounding box, and the catercorner length of computation bound frame.The roadmarking target label of catercorner length size 8m is become to large scale roadmarking, and the roadmarking that catercorner length is less than to 8m is marked as small scale roadmarking.
S5, the classification of large scale roadmarking
The classification that large scale roadmarking is carried out based on wheelpath and curb line is processed, and sorts out stop line, center line and boundary line.This step specifically realizes by following steps:
S51, to each large scale roadmarking, if it comprises multiclass roadmarking, perform step S52, if its roadmarking that comprises one type is directly designated as roadmarking unit by it.Judge whether large scale roadmarking comprises multiclass roadmarking, can be by the diverse location on large scale roadmarking is sampled, and calculate the distribution characteristics of each sampled point.If the distribution characteristics of each sampled point is identical, judge that this large scale roadmarking only comprises the roadmarking of a type; If the distribution characteristics of each sampled point is different, judge that this large scale roadmarking comprises multiclass roadmarking.Certainly, also can adopt artificial means to go to judge whether large scale roadmarking comprises multiclass roadmarking.
S52, the normalization that the large scale roadmarking that comprises multiclass roadmarking is carried out based on volume elements are cut apart, and obtain semantically independently roadmarking unit.This step specifically realizes by following steps:
S521, the large scale roadmarking that comprises multiclass roadmarking is carried out to volume elements with certain volume elements width, and with the volume elements point cloud mass structure full-mesh weighted graph G={V after volume elements, E}, in the present embodiment, volume elements width is got 0.1m.Summit V on this full-mesh weighted graph G each volume elements point cloud mass after by volume elements forms, and the limit E on G is connecting every pair of volume elements point cloud mass.For each volume elements point cloud mass, choose wherein in vitro unit and put the nearest point of cloud mass geometric center as the unique point of this volume elements point cloud mass, and be stored in set P
voxelin.Then, for set P
voxelin any point q, utilize its k-nearest neighbor point p
1, p
2... p
kcalculate its covariance matrix:
By above-mentioned covariance matrix is carried out to Eigenvalues Decomposition, calculate three eigenwerts and three corresponding proper vectors.Using eigenvalue of maximum characteristic of correspondence vector as the distribution characteristics of putting q, put the distribution characteristics of the corresponding volume elements point cloud mass of q.The distribution characteristics of note point q is v
q.The weight connecting on full-mesh weighted graph on the limit on any two summits (i, j) can be defined as follows:
Wherein, qi, qj ∈ P
voxel; v
qiand v
qjfor its corresponding distribution characteristics; σ D and σ A are standard deviation; d
sfor distance restraint condition, for determining the maximum coverage of two volume elements point cloud masses.
S522, based on full-mesh weighted graph, large scale roadmarking is normalized and is cut apart.The method that normalization dividing method is intended to by maximizing similar degree in the class and minimizing similarity between class is divided into two disjoint volume elements set of blocks A and B by weighted graph G.The cost function that normalization is cut apart is defined as:
Wherein, cut (A, B) represents the weight sum on the limit between A and B; Assoc (A, V) represents that whole limit drops on the weight sum on the limit in A; Assoc (B, V) represents that whole limit drops on the weight sum on the limit in B.Finally by resolving generalized eigenvalue decomposition problem that cost function is corresponding, realize cutting apart of the large scale roadmarking that comprises multiclass roadmarking, thereby effectively overlapping multiclass roadmarking (as stop line and boundary line) is separated, be convenient to the classification of subsequent step to roadmarking, improved the accuracy of roadmarking classification.
S53, sampled in each roadmarking unit, and the distribution characteristics of calculating sampling point, whether the sampled point quantity that judgement meets direction verification condition is greater than the first predetermined threshold value, if, this roadmarking unit is labeled as to stop line, if not, perform step S54, the distribution characteristics that direction verification condition is sampled point is perpendicular to the direction of wheelpath.In the present embodiment, to the number of samples of each roadmarking unit, be that 100, the first predetermined threshold value are 95.
Sampled point on S54, calculating roadmarking unit and the distance of curb line, whether the sampled point quantity that judgement meets position verification condition is greater than the second predetermined threshold value, if, this roadmarking unit is labeled as to boundary line, if not, this roadmarking unit is labeled as to center line, to be sampled point be less than 1m to the distance of curb line to position verification condition.In the present embodiment, the second predetermined threshold value is 95.
S6, the classification of small scale roadmarking
The classification that small scale roadmarking is carried out based on degree of depth study and principal component analysis (PCA) is processed, and sorts out direction mark, pedestrian's warning label, zebra stripes, center line and boundary line.This step specifically realizes by following steps:
S61, utilize a deep layer Boltzmann machine that comprises two-layer hidden layer of degree of deep learning method training, and the deep layer Boltzmann machine after training is configured to the sorter of a multilayer.Shown in figure 7, this Multilayer Classifier comprises an input layer, two hidden layers and an output layer.Wherein, W
1, W
2and W
3represent respectively the model parameter of Multilayer Classifier; V representative input data; h
1and h
2represent respectively ground floor and second layer abstract characteristics; Q(h
2| the v) posterior probability of representative based on input data v; Y is the output of Multilayer Classifier.
The energy function of deep layer Boltzmann machine is defined as:
E(v,h
1,h
2；θ)＝-v
TW
1h
1-(h
1)
TW
2h
2
Wherein, θ={ W
1, W
2represent the model parameter of deep layer Boltzmann machine.The definition of probability of a data v of this deep layer Boltzmann machine input is:
Wherein,
partition function for this deep layer Boltzmann machine.By logarithm maximum likelihood learning method, just can train the model parameter of this deep layer Boltzmann machine.Finally, with this deep layer Boltzmann machine structure Multilayer Classifier as shown in Figure 7.
S62, using small scale roadmarking as the input of Multilayer Classifier, the classification information of Multilayer Classifier output small scale roadmarking, classification information comprises strip roadmarking, direction mark, pedestrian's warning label and other roadmarkings.In the present embodiment, Multilayer Classifier output [1,0,0,0]
t, [0,1,0,0]
t, [0,0,1,0]
t, [0,0,0,1]
trepresent respectively strip roadmarking, direction mark, pedestrian's warning label and other roadmarkings.
S63, to each strip roadmarking P, along its Width to two-sided search width, be w
sidethe neighborhood of=1m (shown in figure 8a), if there is strip roadmarking Q in its neighborhood, performs step S64, if there is not strip roadmarking in this neighborhood, performs step S65.Here " Width " mentioned refers to the direction vertical with the long limit of strip roadmarking P.
S64, judge whether the strip roadmarking Q in strip roadmarking P and its neighborhood meets zebra stripes decision condition, if meet, this strip roadmarking P is labeled as to zebra stripes, if do not meet, perform step S65, zebra stripes decision condition is:
(v
p//v
q)∧(v
p//v
pq)∧(v
q//v
pq)
Wherein, some p is the geometric center of strip roadmarking P in XY plane, v
pfor the distribution characteristics of a p, some q is the geometric center of strip roadmarking Q in XY plane, v
qfor the distribution characteristics of a q, v
pqfor the direction vector of a p to a q;
S65, along the length direction of strip roadmarking P, to two-sided search width, be w
endthe neighborhood of=3m (shown in figure 8b), " length direction " mentioned here refers to the direction parallel with the long limit of strip roadmarking P.If there is strip roadmarking G in its neighborhood, judge whether the strip roadmarking G in strip roadmarking P and its neighborhood meets intermittent line decision condition:
(v
p//v
g)∧(v
p//v
pg)∧(v
g//v
pg)
Wherein, some p is the geometric center of strip roadmarking P in XY plane, v
pfor the distribution characteristics of a p, some g is the geometric center of strip roadmarking G in XY plane, v
gfor the distribution characteristics of a g, v
pgfor the direction vector of a p to a g.
If meet, the classification of strip roadmarking P being carried out based on wheelpath and curb line is processed, its concrete treatment step is identical with step S53, S54, only strip roadmarking P need be processed and can sort out boundary line or center line as roadmarking unit.
After above-mentioned steps, can realize the automatic classification to downtown roads graticule.
The above; be only the present invention's embodiment preferably, but protection scope of the present invention is not limited to this, is anyly familiar with in technical scope that those skilled in the art disclose in the present invention; the variation that can expect easily or replacement, within all should being encompassed in protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claim.
Claims (6)
1. the downtown roads graticule automatic classification method based on Vehicle-borne Laser Scanning point cloud, is characterized in that, comprises the following steps:
S1, based on wheelpath data, original point cloud data is carried out to road surface and cut apart, obtain road surface cloud data;
S2, described road surface cloud data is carried out to binary conversion treatment, and extract roadmarking point;
S3, described roadmarking point is carried out to cluster, isolate roadmarking target independent of each other;
S4, according to the size of described roadmarking target, sort out large scale roadmarking and small scale roadmarking;
S5, the classification that described large scale roadmarking is carried out based on wheelpath and curb line are processed, and sort out stop line, center line and boundary line;
S6, the classification that described small scale roadmarking is carried out based on degree of depth study and principal component analysis (PCA) are processed, and sort out direction mark, pedestrian's warning label, zebra stripes, center line and boundary line.
2. a kind of downtown roads graticule automatic classification method based on Vehicle-borne Laser Scanning point cloud as claimed in claim 1, is characterized in that, described step S1 specifically comprises step by step following:
S11, original point cloud data is evenly divided into one group of some cloud mass along the direction of wheelpath;
S12, for each some cloud mass, along being syncopated as a some cloud perpendicular to the direction of wheelpath, cut open sheet, and from a cloud, cut open sheet and extract curb point;
S13, all curb points are carried out to matching, obtain curb line;
S14, original point cloud data is cut apart along curb line, obtained road surface cloud data.
3. a kind of downtown roads graticule automatic classification method based on Vehicle-borne Laser Scanning point cloud as claimed in claim 2, is characterized in that, described step S2 specifically comprises step by step following:
S21, described road surface cloud data is divided into one group road surface point cloud burst to both sides with a certain division interval along wheelpath, adopts OTSU binarization method to carry out respectively binary conversion treatment to each road surface point cloud burst, and extract roadmarking point.
S22, calculate the space density value of each roadmarking point, if when the space density value of certain roadmarking point is less than predefined noise critical value, by its rejecting.
4. a kind of downtown roads graticule automatic classification method based on Vehicle-borne Laser Scanning point cloud as described in claim 1-3 any one, is characterized in that, described step S5 specifically comprises step by step following:
S51, to each large scale roadmarking, if it comprises multiclass roadmarking, perform step S52, if its roadmarking that comprises one type is directly designated as roadmarking unit by it;
S52, the normalization that the large scale roadmarking that comprises multiclass roadmarking is carried out based on volume elements are cut apart, and obtain semantically independently roadmarking unit;
S53, sampled in each roadmarking unit, and the distribution characteristics of calculating sampling point, whether the sampled point quantity that judgement meets direction verification condition is greater than the first predetermined threshold value, if, this roadmarking unit is labeled as to stop line, if not, perform step S54, the distribution characteristics that described direction verification condition is sampled point is perpendicular to the direction of wheelpath;
Sampled point on S54, calculating roadmarking unit and the distance of curb line, whether the sampled point quantity that judgement meets position verification condition is greater than the second predetermined threshold value, if, this roadmarking unit is labeled as to boundary line, if not, this roadmarking unit is labeled as to center line, to be sampled point be less than 1m to the distance of curb line to described position verification condition.
5. a kind of downtown roads graticule automatic classification method based on Vehicle-borne Laser Scanning point cloud as claimed in claim 4, is characterized in that, described step S52 specifically comprises following sub-step:
S521, the large scale roadmarking that comprises multiclass roadmarking is carried out to volume elements, and with the volume elements point cloud mass structure full-mesh weighted graph after volume elements;
S522, based on full-mesh weighted graph, large scale roadmarking is normalized and is cut apart.
6. a kind of downtown roads graticule automatic classification method based on Vehicle-borne Laser Scanning point cloud as claimed in claim 5, is characterized in that, described step S6 specifically comprises following sub-step:
S61, utilize a deep layer Boltzmann machine that comprises two-layer hidden layer of degree of deep learning method training, and the deep layer Boltzmann machine after training is configured to the sorter of a multilayer;
S62, using small scale roadmarking as the input of Multilayer Classifier, the classification information of Multilayer Classifier output small scale roadmarking, described classification information comprises strip roadmarking, direction mark, pedestrian's warning label and other roadmarkings;
S63, to each strip roadmarking P, along its Width to two-sided search width, be w
sidethe neighborhood of=1m, if there is strip roadmarking Q in its neighborhood, performs step S64, if there is not strip roadmarking in this neighborhood, performs step S65;
S64, judge whether the strip roadmarking Q in strip roadmarking P and its neighborhood meets zebra stripes decision condition, if meet, this strip roadmarking P is labeled as to zebra stripes, if do not meet, perform step S65, described zebra stripes decision condition is:
(v
p//v
q)∧(v
p//v
pq)∧(v
q//v
pq)
Wherein, some p is the geometric center of strip roadmarking P in XY plane, v
pfor the distribution characteristics of a p, some q is the geometric center of strip roadmarking Q in XY plane, v
qfor the distribution characteristics of a q, v
pqfor the direction vector of a p to a q;
S65, along the length direction of strip roadmarking P, to two-sided search width, be w
endthe neighborhood of=3m, if there is strip roadmarking G in its neighborhood, judge whether the strip roadmarking G in strip roadmarking P and its neighborhood meets intermittent line decision condition, if meet, the classification of strip roadmarking P being carried out based on wheelpath and curb line is processed, strip roadmarking P is labeled as to boundary line or center line, and described intermittent line decision condition is:
(v
p//v
g)∧(v
p//v
pg)∧(v
g//v
pg)
Wherein, some p is the geometric center of strip roadmarking P in XY plane, v
pfor the distribution characteristics of a p, some g is the geometric center of strip roadmarking G in XY plane, v
gfor the distribution characteristics of a g, v
pgfor the direction vector of a p to a g.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410171408.5A CN104197897B (en) | 2014-04-25 | 2014-04-25 | A kind of downtown roads graticule automatic classification method based on Vehicle-borne Laser Scanning point cloud |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410171408.5A CN104197897B (en) | 2014-04-25 | 2014-04-25 | A kind of downtown roads graticule automatic classification method based on Vehicle-borne Laser Scanning point cloud |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104197897A true CN104197897A (en) | 2014-12-10 |
| CN104197897B CN104197897B (en) | 2017-01-04 |
Family
ID=52083225
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410171408.5A Active CN104197897B (en) | 2014-04-25 | 2014-04-25 | A kind of downtown roads graticule automatic classification method based on Vehicle-borne Laser Scanning point cloud |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104197897B (en) |
Cited By (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069395A (en) * | 2015-05-17 | 2015-11-18 | 北京工业大学 | Road marking automatic identification method based on terrestrial three-dimensional laser scanning technology |
| CN105488498A (en) * | 2016-01-15 | 2016-04-13 | 武汉光庭信息技术股份有限公司 | Lane sideline automatic extraction method and lane sideline automatic extraction system based on laser point cloud |
| CN105551082A (en) * | 2015-12-02 | 2016-05-04 | 百度在线网络技术（北京）有限公司 | Method and device of pavement identification on the basis of laser-point cloud |
| CN105627938A (en) * | 2016-01-07 | 2016-06-01 | 厦门大学 | Pavement asphalt thickness detection method based on vehicle-mounted laser scanning spot cloud |
| CN105957145A (en) * | 2016-04-29 | 2016-09-21 | 百度在线网络技术（北京）有限公司 | Road barrier identification method and device |
| CN106022381A (en) * | 2016-05-25 | 2016-10-12 | 厦门大学 | Automatic extraction technology of street lamp poles based on vehicle laser scanning point clouds |
| CN106067003A (en) * | 2016-05-27 | 2016-11-02 | 山东科技大学 | Road vectors tag line extraction method in a kind of Vehicle-borne Laser Scanning point cloud |
| CN106126816A (en) * | 2016-06-24 | 2016-11-16 | 南京林业大学 | Repeat the extensive ALS building point cloud modeling method building under automatic sensing |
| CN106503678A (en) * | 2016-10-27 | 2017-03-15 | 厦门大学 | Roadmarking automatic detection and sorting technique based on mobile laser scanning point cloud |
| CN106599915A (en) * | 2016-12-08 | 2017-04-26 | 立得空间信息技术股份有限公司 | Vehicle-mounted laser point cloud classification method |
| CN106650809A (en) * | 2016-12-20 | 2017-05-10 | 福州大学 | Method and system for classifying vehicle-borne laser-point cloud targets |
| CN106845321A (en) * | 2015-12-03 | 2017-06-13 | 高德软件有限公司 | The treating method and apparatus of pavement markers information |
| CN107038723A (en) * | 2015-11-20 | 2017-08-11 | 通用汽车环球科技运作有限责任公司 | Bar-shaped pixel method of estimation and system |
| CN107085710A (en) * | 2017-04-26 | 2017-08-22 | 长江空间信息技术工程有限公司(武汉) | A kind of single wooden extraction method based on multispectral LiDAR data |
| CN107679458A (en) * | 2017-09-07 | 2018-02-09 | 中国地质大学（武汉） | The extracting method of roadmarking in a kind of road color laser point cloud based on K Means |
| CN108241819A (en) * | 2016-12-23 | 2018-07-03 | 高德软件有限公司 | The recognition methods of pavement markers and device |
| CN108615452A (en) * | 2018-04-03 | 2018-10-02 | 华南理工大学 | A kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy |
| CN108845569A (en) * | 2018-04-27 | 2018-11-20 | 厦门维斯云景信息科技有限公司 | Generate semi-automatic cloud method of the horizontal bend lane of three-dimensional high-definition mileage chart |
| CN108931786A (en) * | 2018-05-17 | 2018-12-04 | 北京智行者科技有限公司 | Curb detection device and method |
| CN108960326A (en) * | 2018-07-04 | 2018-12-07 | 深圳先进技术研究院 | A kind of point cloud fast partition method and its system based on deep learning frame |
| CN109166128A (en) * | 2018-07-31 | 2019-01-08 | 东华大学 | A kind of non-equivalent three-dimensional point cloud dividing method |
| CN109165549A (en) * | 2018-07-09 | 2019-01-08 | 厦门大学 | Road markings acquisition methods, terminal device and device based on three dimensional point cloud |
| CN109564285A (en) * | 2016-07-29 | 2019-04-02 | 大众汽车有限公司 | For detecting the method and system of the surface mark under the traffic environment of mobile unit |
| CN109670376A (en) * | 2017-10-13 | 2019-04-23 | 神州优车股份有限公司 | Lane detection method and system |
| CN109798903A (en) * | 2018-12-19 | 2019-05-24 | 广州文远知行科技有限公司 | A kind of method and device obtaining road information from map datum |
| CN110008921A (en) * | 2019-04-12 | 2019-07-12 | 北京百度网讯科技有限公司 | A kind of generation method of road boundary, device, electronic equipment and storage medium |
| CN110019627A (en) * | 2017-12-25 | 2019-07-16 | 北京京东尚科信息技术有限公司 | Identify the method and its system, computer system of traffic channelizing line |
| CN110210415A (en) * | 2019-06-05 | 2019-09-06 | 福州大学 | Vehicle-mounted laser point cloud roadmarking recognition methods based on graph structure |
| CN110349260A (en) * | 2019-07-11 | 2019-10-18 | 武汉中海庭数据技术有限公司 | A kind of pavement strip extraction method and device |
| CN110379006A (en) * | 2019-07-24 | 2019-10-25 | 厦门大学 | A kind of three-dimensional zebra stripes method for reconstructing based on mobile laser radar scanning point cloud |
| CN110866449A (en) * | 2019-10-21 | 2020-03-06 | 北京京东尚科信息技术有限公司 | Method and device for identifying target object in road |
| CN111783722A (en) * | 2020-07-13 | 2020-10-16 | 湖北亿咖通科技有限公司 | Lane line extraction method of laser point cloud and electronic equipment |
| CN112059407A (en) * | 2020-09-17 | 2020-12-11 | 苏州快光科技有限公司 | Picosecond ultrafast laser processing system and method based on deep learning |
| CN112070054A (en) * | 2020-09-17 | 2020-12-11 | 福州大学 | Vehicle-mounted laser point cloud marking classification method based on graph structure and attention mechanism |
| CN112435336A (en) * | 2020-11-13 | 2021-03-02 | 武汉中海庭数据技术有限公司 | Curve type identification method and device, electronic equipment and storage medium |
| CN112561944A (en) * | 2020-11-27 | 2021-03-26 | 中央财经大学 | Lane line extraction method based on vehicle-mounted laser point cloud |
| CN112686089A (en) * | 2020-10-10 | 2021-04-20 | 星际空间（天津）科技发展有限公司 | Intelligent automatic extraction method of road information |
| WO2022121177A1 (en) * | 2020-12-07 | 2022-06-16 | 速度时空信息科技股份有限公司 | Scan line-based road point cloud extraction method |
| CN114998770A (en) * | 2022-07-06 | 2022-09-02 | 中国科学院地理科学与资源研究所 | Highway identifier extraction method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3690366B2 (en) * | 2001-12-27 | 2005-08-31 | 日産自動車株式会社 | Front object detection device |
| CN102445186A (en) * | 2011-09-28 | 2012-05-09 | 中交第二公路勘察设计研究院有限公司 | Method for generating road design surface information by laser radar scan |
| CN102779280A (en) * | 2012-06-19 | 2012-11-14 | 武汉大学 | Traffic information extraction method based on laser sensor |
| CN103500338A (en) * | 2013-10-16 | 2014-01-08 | 厦门大学 | Road zebra crossing automatic extraction method based on vehicle-mounted laser scanning point cloud |
| CN103530689A (en) * | 2013-10-31 | 2014-01-22 | 中国科学院自动化研究所 | Deep learning-based clustering method |
-
2014
- 2014-04-25 CN CN201410171408.5A patent/CN104197897B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3690366B2 (en) * | 2001-12-27 | 2005-08-31 | 日産自動車株式会社 | Front object detection device |
| CN102445186A (en) * | 2011-09-28 | 2012-05-09 | 中交第二公路勘察设计研究院有限公司 | Method for generating road design surface information by laser radar scan |
| CN102779280A (en) * | 2012-06-19 | 2012-11-14 | 武汉大学 | Traffic information extraction method based on laser sensor |
| CN103500338A (en) * | 2013-10-16 | 2014-01-08 | 厦门大学 | Road zebra crossing automatic extraction method based on vehicle-mounted laser scanning point cloud |
| CN103530689A (en) * | 2013-10-31 | 2014-01-22 | 中国科学院自动化研究所 | Deep learning-based clustering method |
Non-Patent Citations (2)
| Title |
|---|
| A. MANCINI ET AL.: ""Automatic Road Object Extraction from Mobile Mapping Systems"", 《MECHATRONICS AND EMBEDDED SYSTEMS AND APPLICAIONS,2012 IEEE/ASME INTERNATIONAL CONFERENCE》 * |
| HAIYAN GUAN ET AL.: ""Using mobile laser scanning data for automated extraction of road markings"", 《ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING》 * |
Cited By (63)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069395B (en) * | 2015-05-17 | 2018-10-09 | 北京工业大学 | Roadmarking automatic identifying method based on Three Dimensional Ground laser scanner technique |
| CN105069395A (en) * | 2015-05-17 | 2015-11-18 | 北京工业大学 | Road marking automatic identification method based on terrestrial three-dimensional laser scanning technology |
| CN107038723A (en) * | 2015-11-20 | 2017-08-11 | 通用汽车环球科技运作有限责任公司 | Bar-shaped pixel method of estimation and system |
| CN107038723B (en) * | 2015-11-20 | 2020-09-11 | 通用汽车环球科技运作有限责任公司 | Method and system for estimating rod-shaped pixels |
| CN105551082A (en) * | 2015-12-02 | 2016-05-04 | 百度在线网络技术（北京）有限公司 | Method and device of pavement identification on the basis of laser-point cloud |
| CN105551082B (en) * | 2015-12-02 | 2018-09-07 | 百度在线网络技术（北京）有限公司 | A kind of pavement identification method and device based on laser point cloud |
| CN106845321B (en) * | 2015-12-03 | 2020-03-27 | 高德软件有限公司 | Method and device for processing pavement marking information |
| CN106845321A (en) * | 2015-12-03 | 2017-06-13 | 高德软件有限公司 | The treating method and apparatus of pavement markers information |
| CN105627938A (en) * | 2016-01-07 | 2016-06-01 | 厦门大学 | Pavement asphalt thickness detection method based on vehicle-mounted laser scanning spot cloud |
| CN105488498A (en) * | 2016-01-15 | 2016-04-13 | 武汉光庭信息技术股份有限公司 | Lane sideline automatic extraction method and lane sideline automatic extraction system based on laser point cloud |
| CN105488498B (en) * | 2016-01-15 | 2019-07-30 | 武汉中海庭数据技术有限公司 | A kind of lane sideline extraction method and system based on laser point cloud |
| CN105957145A (en) * | 2016-04-29 | 2016-09-21 | 百度在线网络技术（北京）有限公司 | Road barrier identification method and device |
| CN106022381A (en) * | 2016-05-25 | 2016-10-12 | 厦门大学 | Automatic extraction technology of street lamp poles based on vehicle laser scanning point clouds |
| CN106022381B (en) * | 2016-05-25 | 2020-05-22 | 厦门大学 | Automatic extraction method of street lamp pole based on vehicle-mounted laser scanning point cloud |
| CN106067003B (en) * | 2016-05-27 | 2020-05-19 | 山东科技大学 | Automatic extraction method for road vector identification line in vehicle-mounted laser scanning point cloud |
| CN106067003A (en) * | 2016-05-27 | 2016-11-02 | 山东科技大学 | Road vectors tag line extraction method in a kind of Vehicle-borne Laser Scanning point cloud |
| CN106126816A (en) * | 2016-06-24 | 2016-11-16 | 南京林业大学 | Repeat the extensive ALS building point cloud modeling method building under automatic sensing |
| CN106126816B (en) * | 2016-06-24 | 2019-04-05 | 南京林业大学 | Repeat the extensive ALS building point cloud modeling method under building automatic sensing |
| CN109564285A (en) * | 2016-07-29 | 2019-04-02 | 大众汽车有限公司 | For detecting the method and system of the surface mark under the traffic environment of mobile unit |
| CN106503678A (en) * | 2016-10-27 | 2017-03-15 | 厦门大学 | Roadmarking automatic detection and sorting technique based on mobile laser scanning point cloud |
| CN106599915B (en) * | 2016-12-08 | 2017-11-28 | 立得空间信息技术股份有限公司 | A kind of vehicle-mounted laser point cloud classifications method |
| CN106599915A (en) * | 2016-12-08 | 2017-04-26 | 立得空间信息技术股份有限公司 | Vehicle-mounted laser point cloud classification method |
| CN106650809A (en) * | 2016-12-20 | 2017-05-10 | 福州大学 | Method and system for classifying vehicle-borne laser-point cloud targets |
| CN106650809B (en) * | 2016-12-20 | 2018-02-23 | 福州大学 | A kind of vehicle-mounted laser point cloud objective classification method and system |
| CN108241819A (en) * | 2016-12-23 | 2018-07-03 | 高德软件有限公司 | The recognition methods of pavement markers and device |
| CN108241819B (en) * | 2016-12-23 | 2020-07-28 | 阿里巴巴（中国）有限公司 | Method and device for identifying pavement marker |
| CN107085710B (en) * | 2017-04-26 | 2020-06-02 | 长江空间信息技术工程有限公司(武汉) | Single-tree automatic extraction method based on multispectral LiDAR data |
| CN107085710A (en) * | 2017-04-26 | 2017-08-22 | 长江空间信息技术工程有限公司(武汉) | A kind of single wooden extraction method based on multispectral LiDAR data |
| CN107679458A (en) * | 2017-09-07 | 2018-02-09 | 中国地质大学（武汉） | The extracting method of roadmarking in a kind of road color laser point cloud based on K Means |
| CN107679458B (en) * | 2017-09-07 | 2020-09-29 | 中国地质大学（武汉） | Method for extracting road marking lines in road color laser point cloud based on K-Means |
| CN109670376A (en) * | 2017-10-13 | 2019-04-23 | 神州优车股份有限公司 | Lane detection method and system |
| CN110019627A (en) * | 2017-12-25 | 2019-07-16 | 北京京东尚科信息技术有限公司 | Identify the method and its system, computer system of traffic channelizing line |
| CN110019627B (en) * | 2017-12-25 | 2022-04-12 | 北京京东乾石科技有限公司 | Method, system and computer system for identifying traffic diversion line |
| CN108615452B (en) * | 2018-04-03 | 2019-08-20 | 华南理工大学 | A kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy |
| CN108615452A (en) * | 2018-04-03 | 2018-10-02 | 华南理工大学 | A kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy |
| CN108845569A (en) * | 2018-04-27 | 2018-11-20 | 厦门维斯云景信息科技有限公司 | Generate semi-automatic cloud method of the horizontal bend lane of three-dimensional high-definition mileage chart |
| CN108931786A (en) * | 2018-05-17 | 2018-12-04 | 北京智行者科技有限公司 | Curb detection device and method |
| CN108960326B (en) * | 2018-07-04 | 2021-03-23 | 深圳先进技术研究院 | Point cloud fast segmentation method and system based on deep learning framework |
| CN108960326A (en) * | 2018-07-04 | 2018-12-07 | 深圳先进技术研究院 | A kind of point cloud fast partition method and its system based on deep learning frame |
| CN109165549B (en) * | 2018-07-09 | 2021-03-19 | 厦门大学 | Road identification obtaining method based on three-dimensional point cloud data, terminal equipment and device |
| CN109165549A (en) * | 2018-07-09 | 2019-01-08 | 厦门大学 | Road markings acquisition methods, terminal device and device based on three dimensional point cloud |
| CN109166128B (en) * | 2018-07-31 | 2021-11-26 | 东华大学 | Non-equivalent three-dimensional point cloud segmentation method |
| CN109166128A (en) * | 2018-07-31 | 2019-01-08 | 东华大学 | A kind of non-equivalent three-dimensional point cloud dividing method |
| CN109798903A (en) * | 2018-12-19 | 2019-05-24 | 广州文远知行科技有限公司 | A kind of method and device obtaining road information from map datum |
| CN110008921A (en) * | 2019-04-12 | 2019-07-12 | 北京百度网讯科技有限公司 | A kind of generation method of road boundary, device, electronic equipment and storage medium |
| CN110008921B (en) * | 2019-04-12 | 2021-12-28 | 北京百度网讯科技有限公司 | Road boundary generation method and device, electronic equipment and storage medium |
| CN110210415A (en) * | 2019-06-05 | 2019-09-06 | 福州大学 | Vehicle-mounted laser point cloud roadmarking recognition methods based on graph structure |
| CN110210415B (en) * | 2019-06-05 | 2022-09-30 | 福州大学 | Vehicle-mounted laser point cloud road marking identification method based on graph structure |
| CN110349260A (en) * | 2019-07-11 | 2019-10-18 | 武汉中海庭数据技术有限公司 | A kind of pavement strip extraction method and device |
| CN110349260B (en) * | 2019-07-11 | 2022-06-17 | 武汉中海庭数据技术有限公司 | Automatic pavement marking extraction method and device |
| CN110379006A (en) * | 2019-07-24 | 2019-10-25 | 厦门大学 | A kind of three-dimensional zebra stripes method for reconstructing based on mobile laser radar scanning point cloud |
| CN110866449A (en) * | 2019-10-21 | 2020-03-06 | 北京京东尚科信息技术有限公司 | Method and device for identifying target object in road |
| CN111783722A (en) * | 2020-07-13 | 2020-10-16 | 湖北亿咖通科技有限公司 | Lane line extraction method of laser point cloud and electronic equipment |
| CN112070054A (en) * | 2020-09-17 | 2020-12-11 | 福州大学 | Vehicle-mounted laser point cloud marking classification method based on graph structure and attention mechanism |
| CN112059407A (en) * | 2020-09-17 | 2020-12-11 | 苏州快光科技有限公司 | Picosecond ultrafast laser processing system and method based on deep learning |
| CN112070054B (en) * | 2020-09-17 | 2022-07-29 | 福州大学 | Vehicle-mounted laser point cloud marking classification method based on graph structure and attention mechanism |
| CN112686089B (en) * | 2020-10-10 | 2023-06-13 | 星际空间（天津）科技发展有限公司 | Intelligent automatic extraction method for road information |
| CN112686089A (en) * | 2020-10-10 | 2021-04-20 | 星际空间（天津）科技发展有限公司 | Intelligent automatic extraction method of road information |
| CN112435336A (en) * | 2020-11-13 | 2021-03-02 | 武汉中海庭数据技术有限公司 | Curve type identification method and device, electronic equipment and storage medium |
| CN112435336B (en) * | 2020-11-13 | 2022-04-19 | 武汉中海庭数据技术有限公司 | Curve type identification method and device, electronic equipment and storage medium |
| CN112561944A (en) * | 2020-11-27 | 2021-03-26 | 中央财经大学 | Lane line extraction method based on vehicle-mounted laser point cloud |
| WO2022121177A1 (en) * | 2020-12-07 | 2022-06-16 | 速度时空信息科技股份有限公司 | Scan line-based road point cloud extraction method |
| CN114998770A (en) * | 2022-07-06 | 2022-09-02 | 中国科学院地理科学与资源研究所 | Highway identifier extraction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104197897B (en) | 2017-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104197897A (en) | Urban road marker automatic sorting method based on vehicle-mounted laser scanning point cloud | |
| CN111985322B (en) | Road environment element sensing method based on laser radar | |
| CN105160309B (en) | Three lanes detection method based on morphological image segmentation and region growing | |
| CN106127153B (en) | The traffic sign recognition methods of Vehicle-borne Laser Scanning point cloud data | |
| Yu et al. | Learning hierarchical features for automated extraction of road markings from 3-D mobile LiDAR point clouds | |
| CN104091321A (en) | Multi-level-point-set characteristic extraction method applicable to ground laser radar point cloud classification | |
| CN103942546A (en) | Guide traffic marking identification system and method in municipal environment | |
| KR101822373B1 (en) | Apparatus and method for detecting object | |
| CN115605777A (en) | Dynamic target point cloud rapid identification and point cloud segmentation method based on road side sensing unit | |
| Li et al. | Semantic segmentation of road furniture in mobile laser scanning data | |
| CN103077389A (en) | Text detection and recognition method combining character level classification and character string level classification | |
| CN103971091B (en) | Automatic plane number recognition method | |
| CN102968646A (en) | Plate number detecting method based on machine learning | |
| CN104050447A (en) | Traffic light identification method and device | |
| CN114359876B (en) | Vehicle target identification method and storage medium | |
| Tumen et al. | Recognition of road type and quality for advanced driver assistance systems with deep learning | |
| Omar et al. | Detection of roads potholes using YOLOv4 | |
| CN107274668A (en) | A kind of congestion in road modeling method based on vehicle detection | |
| CN106886757A (en) | A kind of multiclass traffic lights detection method and system based on prior probability image | |
| CN103295003B (en) | A kind of vehicle checking method based on multi-feature fusion | |
| CN103886331A (en) | Method for classifying appearances of vehicles based on multi-feature fusion of surveillance video | |
| Xu et al. | A machine learning approach to vehicle occupancy detection | |
| CN105095914A (en) | Airport runway detection method based on combination of h/q decomposition and Bayesian iterative classification | |
| Toth et al. | Vehicle recognition from LiDAR data | |
| Mohamed et al. | Machine learning for mobile LIDAR data classification of 3D road environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C53 | Correction of patent of invention or patent application | ||
| CB03 | Change of inventor or designer information |
Inventor after: Li Jun Inventor after: Yu Yongtao Inventor after: Guan Haiyan Inventor after: Wang Cheng Inventor before: Yu Yongtao Inventor before: Li Jun Inventor before: Guan Haiyan Inventor before: Wang Cheng |
|
| COR | Change of bibliographic data |
Free format text: CORRECT: INVENTOR; FROM: YU YONGTAO LI JUN GUAN HAIYAN WANG CHENG TO: LI JUN YU YONGTAO GUAN HAIYAN WANG CHENG |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |