CN108766031B - Method and device for detecting lane obstacle - Google Patents

Method and device for detecting lane obstacle Download PDF

Info

Publication number
CN108766031B
CN108766031B CN201810534328.XA CN201810534328A CN108766031B CN 108766031 B CN108766031 B CN 108766031B CN 201810534328 A CN201810534328 A CN 201810534328A CN 108766031 B CN108766031 B CN 108766031B
Authority
CN
China
Prior art keywords
lane
driving track
offset
driving
detected
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810534328.XA
Other languages
Chinese (zh)
Other versions
CN108766031A (en
Inventor
鲍捷
郑宇�
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
JD Digital Technology Holdings Co Ltd
Jingdong Technology Holding Co Ltd
Original Assignee
JD Digital Technology Holdings Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by JD Digital Technology Holdings Co Ltd filed Critical JD Digital Technology Holdings Co Ltd
Priority to CN201810534328.XA priority Critical patent/CN108766031B/en
Publication of CN108766031A publication Critical patent/CN108766031A/en
Application granted granted Critical
Publication of CN108766031B publication Critical patent/CN108766031B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/165—Anti-collision systems for passive traffic, e.g. including static obstacles, trees
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/029—Location-based management or tracking services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a method and a device for detecting lane obstacles, and relates to the technical field of computers. One embodiment of the method comprises: determining a reference offset set of a to-be-detected road section of a lane; when the offset in the reference offset set is that the road section to be detected of the lane has no barrier, the distance from the driving track point corresponding to the lane in the road section to be detected to the lane baseline is; determining a detection offset set of a road section to be detected of a lane in a preset time period; detecting the offset in the offset set as the distance from a driving track point corresponding to the lane in the road section to be detected to the lane baseline within a preset time period; and judging whether the obstacle exists on the road section to be detected of the lane or not according to the similarity between the detection offset set and the reference offset set. The method does not need to detect the lane obstacles by means of other detection equipment, also solves the problem of detection blind areas caused by limited coverage in the prior art, and greatly reduces the detection cost.

Description

Method and device for detecting lane obstacle
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for detecting lane obstacles.
Background
The presence of obstacles on a lane can seriously affect the driving of vehicles on the lane, such as illegal parking on a bicycle lane, which not only causes traffic jam, but also is likely to cause traffic accidents. In the prior art, a method for detecting whether an obstacle exists on a lane mainly comprises the following steps: the method comprises the steps of camera monitoring through fixed points and manual identification.
Both manual identification and fixed point video information acquisition are active detection methods, and the probability of detection failure is higher. Moreover, the coverage area of each detection point is very limited (within the sight line of people and cameras), so that the labor and material resources required by the detection point are very large, and the detection cost is high.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for detecting a lane obstacle, which can detect a lane obstacle without using another detection device, and can more accurately detect whether an obstacle exists in a to-be-detected road section of a lane within a preset time period through travel track data of the lane obstacle. Meanwhile, the problem that a detection blind area occurs due to the fact that the coverage range is limited in the prior art is solved, and the detection cost is greatly reduced.
To achieve the above object, according to an aspect of an embodiment of the present invention, a method of detecting a lane obstacle is provided.
The method for detecting the lane obstacle comprises the following steps: determining a reference offset set of a to-be-detected road section of a lane; when the offset in the reference offset set is the distance from a driving track point corresponding to the lane to a lane baseline in the road section to be detected when the road section to be detected of the lane has no barrier;
determining a detection offset set of a to-be-detected road section of the lane within a preset time period; the offset in the detection offset set is the distance from a driving track point corresponding to the lane in the road section to be detected to the lane baseline within a preset time period;
and judging whether the road section to be detected of the lane has the obstacle or not according to the similarity between the detection offset set and the reference offset set.
Optionally, before determining the set of detection offsets of the to-be-detected road segment of the lane within the preset time period, the method further includes: mapping the driving track points to a road network, and determining the offset of each driving track point and a lane road section identifier; and storing the offset of the driving track points according to the lane section identification and the timestamp information of the driving track points.
Optionally, before mapping the driving track points into the road network, the method further includes: grouping the collected driving track points according to the identification information of the equipment for collecting the driving track points; calculating the speed of each driving track point in each group, and determining the sampling frequency of the equipment corresponding to each group; and removing abnormal track points in the collected driving track points according to the speed and the first preset interval of each driving track point, and the sampling frequency and the second preset interval of the equipment corresponding to each track point.
Optionally, after mapping the driving track points to the road network and determining the offset of each driving track point and the lane road segment identifier, and before storing the offset of the driving track points according to the lane road segment identifier and the timestamp information, the method further includes: connecting the driving track points in the road network according to the identification information of the equipment for collecting the driving track points and the lane section identification of the driving track points to obtain the track line of the lane section; dividing the trajectory line into more than one sub-trajectory line; calculating the average offset of the driving track points contained in each sub-track line, determining the sub-track line with the average offset larger than a first preset threshold value, and removing the driving track points contained in the sub-track line; determining the track direction of each sub-track line, and calculating the deflection angle between the track direction and the lane base line; and determining the sub-trajectory line of which the deflection angle is greater than a second preset threshold value, and removing the driving trajectory point contained in the sub-trajectory line.
Optionally, after mapping the driving track points to the road network and determining the offset of each driving track point and the lane road segment identifier, and before storing the offset of the driving track points according to the lane road segment identifier and the timestamp information, the method further includes: connecting the driving track points in the road network according to the identification information of the equipment for collecting the driving track points and the lane section identification of the driving track points to obtain the track line of the lane section; determining the track direction of each track line; and determining a track line with the track direction different from the setting direction of the road section to be detected of the lane, and removing the driving track point contained in the track line.
Optionally, the step of determining the detection offset set of the to-be-detected road segment of the lane within the preset time period includes: determining a starting distance of each driving track point of the lane in a preset time period, wherein the starting distance is a distance between a projection of the driving track point on a lane base line and a starting node of a road section to be detected of the lane; grouping the driving track points according to the starting distance of the driving track points and a preset first average value; and calculating the average offset of the driving track points in each group for the driving track points in each group, and forming a detection offset set by all the average offsets.
Optionally, the step of determining the detection offset set of the to-be-detected road segment of the lane within the preset time period includes: determining a starting distance of each driving track point of the lane in a preset time period, wherein the starting distance is a distance between a projection of the driving track point on a lane base line and a starting node of a road section to be detected of the lane; grouping the driving track points according to the starting distance of the driving track points and a preset second average value; for the driving track points in each group, sorting the offset of the driving track points in the group from big to small, and selecting the first N offsets in the sorting to form a detection offset set; wherein N is a preset positive integer.
Optionally, the step of determining the similarity between the detection offset set and the reference offset set includes: determining whether the distribution of offsets in the set of detected offsets and the set of reference offsets is consistent by a kolmogorov-smirnov test.
Optionally, the lane is a bike lane; and/or the running track points are shared single-vehicle running data.
To achieve the above object, according to another aspect of embodiments of the present invention, there is provided an apparatus for detecting a lane obstacle.
The device for detecting the lane obstacle of the embodiment of the invention comprises: the reference offset determining module is used for determining a reference offset set of a road section to be detected of the lane; when the offset in the reference offset set is the distance from a driving track point corresponding to the lane to a lane baseline in the road section to be detected when the road section to be detected of the lane has no barrier;
the detection offset determining module is used for determining a detection offset set of a road section to be detected of the lane within a preset time period; the offset in the detection offset set is the distance from a driving track point corresponding to the lane in the road section to be detected to the lane baseline within a preset time period;
and the judging module is used for judging whether the road section to be detected of the lane has the obstacle or not according to the similarity between the detection offset set and the reference offset set.
Optionally, the device for detecting a lane obstacle according to the embodiment of the present invention further includes a preprocessing module, configured to map the travel track points to a road network, and determine an offset of each travel track point and a lane road segment identifier; and storing the offset of the driving track points according to the lane section identification and the timestamp information of the driving track points.
Optionally, the preprocessing module is further configured to group the collected driving trace points according to identification information of a device that collects the driving trace points; calculating the speed of each driving track point in each group, and determining the sampling frequency of the equipment corresponding to each group; and removing abnormal track points in the collected driving track points according to the speed and the first preset interval of each driving track point, and the sampling frequency and the second preset interval of the equipment corresponding to each track point.
Optionally, the preprocessing module is further configured to connect the driving track points in the road network according to the identification information of the device for collecting the driving track points and the lane section identifications of the driving track points to obtain the track line of the lane section; dividing the trajectory line into more than one sub-trajectory line; calculating the average offset of the driving track points contained in each sub-track line, determining the sub-track line with the average offset larger than a first preset threshold value, and removing the driving track points contained in the sub-track line; determining the track direction of each sub-track line, and calculating the deflection angle between the track direction and the lane base line; and determining the sub-trajectory line of which the deflection angle is greater than a second preset threshold value, and removing the driving trajectory point contained in the sub-trajectory line.
Optionally, the preprocessing module is further configured to connect the driving track points in the road network according to the identification information of the device for collecting the driving track points and the lane section identifications of the driving track points to obtain the track line of the lane section; determining the track direction of each track line; and determining a track line with the track direction different from the setting direction of the road section to be detected of the lane, and removing the driving track point contained in the track line.
Optionally, the detection offset determining module is further configured to determine a departure distance of each driving track point of the lane within a preset time period, where the departure distance is a distance between a projection of the driving track point on a lane baseline and a starting node of a to-be-detected road section of the lane; grouping the driving track points according to the starting distance of the driving track points and a preset first average value; and calculating the average offset of the driving track points in each group for the driving track points in each group, and forming a detection offset set by all the average offsets.
Optionally, the detection offset determining module is further configured to determine a departure distance of each driving track point of the lane within a preset time period, where the departure distance is a distance between a projection of the driving track point on a lane baseline and a starting node of a to-be-detected road section of the lane; grouping the driving track points according to the starting distance of the driving track points and a preset second average value; for the driving track points in each group, sorting the offset of the driving track points in the group from big to small, and selecting the first N offsets in the sorting to form a detection offset set; wherein N is a preset positive integer.
Optionally, the determining module is further configured to determine whether the distribution of offsets in the set of detected offsets and the set of reference offsets is consistent through a kolmogorov-smirnov test.
Optionally, the lane is a bike lane; and/or the running track points are shared single-vehicle running data.
To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided an electronic device that detects a lane obstacle.
The electronic equipment for detecting the lane obstacle of the embodiment of the invention comprises: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method of detecting a lane obstacle of any of the above.
To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided a computer readable medium having a computer program stored thereon, characterized in that the program, when executed by a processor, implements any of the above-mentioned methods of detecting a lane obstacle.
One embodiment of the above invention has the following advantages or benefits: and judging whether the road section to be detected of the lane has the obstacle or not in the preset time period by mining the driving data of the road section to be detected of the lane in the preset time period and comparing the determined offset of the road section to be detected of the lane in the preset time period with the offset of the road section to be detected of the lane without the obstacle. Different from the manual detection or video information acquisition mode in the prior art, the lane obstacle detection method does not need to use additional detection equipment to detect lane obstacles, and can more accurately detect whether the obstacle exists in the road section to be detected of the lane in the preset time period through the driving track data. Meanwhile, the problem that a detection blind area occurs due to the fact that the coverage range is limited in the prior art is solved, and the detection cost is greatly reduced.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
fig. 1 is a schematic view of a main flow of a method of detecting a lane obstacle according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of mapping travel trace points to distance errors and directionality errors that occur in a road network;
fig. 3 to 5 are schematic diagrams of the determined offset of the road section to be detected of the lane in the preset time period according to the embodiment of the invention;
FIG. 6 is a schematic diagram of a main flow of a method of detecting a bicycle lane obstacle according to an embodiment of the present invention;
FIGS. 7-8 are schematic diagrams of mapping travel track points into a road network;
FIG. 9 is a schematic view of the deflection angle between sub-tracks and a road;
fig. 10 is a schematic view of an apparatus of a method of detecting a lane obstacle according to an embodiment of the present invention;
FIG. 11 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 12 is a schematic structural diagram of a computer system suitable for implementing a terminal device or a server according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram of a main flow of a method for detecting a lane obstacle according to an embodiment of the present invention, and as shown in fig. 1, the method for detecting a lane obstacle of an embodiment of the present invention mainly includes:
step S101: and determining a reference offset set of the to-be-detected road sections of the lane. And when the offset in the reference offset set is that the road section to be detected of the lane has no barrier, the distance from the driving track point corresponding to the lane in the road section to be detected to the lane baseline is calculated. The lane is a bicycle lane, and/or the running track points are shared bicycle running data. The lane base line is a line segment representing a lane in a road network (road system in which various roads are interconnected and interlaced in a mesh distribution in a certain area), and may be a central axis or a boundary line of the lane.
For example, whether an obstacle exists on a bicycle lane or not is detected, a reference travel track point of the bicycle lane of a certain road section or all road sections in a certain range needs to be acquired, and the reference travel track point is a single vehicle travel track point on the bicycle lane acquired through a GPS positioning device when no obstacle exists on the bicycle lane. After reference traveling track points on the road section and the bicycle lane are obtained, the offset of each reference traveling track point, namely the distance from the reference traveling track point to a lane base line, is calculated, and the offsets of all the reference traveling track points form a reference offset set.
Step S102: and determining a detection offset set of the to-be-detected road section of the lane in the preset time period. And detecting the distance from the driving track point corresponding to the lane baseline in the road section to be detected within a preset time period. If the data are preprocessed, the offset of the driving track point of each road section of the lane in the preset time period is calculated, and then the process can directly obtain the detection offset set of the road section to be detected of the lane in the preset time period. Otherwise, the process firstly determines the driving track points on the road section to be detected of the lane within the preset time, then calculates the offset of the driving track points, and the calculated offset forms a set of offset to be detected.
Before step S102, the data is preprocessed, so that the driving track points of the lanes in a certain range can be mapped to the corresponding road segments, which facilitates to quickly find the driving track points on the road segments of the corresponding lanes and the offset of the corresponding driving track points. Specifically, driving track points are mapped into a road network, and the offset and the lane road section identification of each driving track point are determined; and storing the offset of the driving track points according to the lane section identification and the timestamp information of the driving track points. The track points are composed of longitude, latitude and timestamp information, and are generally collected by a GPS positioning device. Through the process, the obtained driving track points of a plurality of lanes or road sections are mapped into the road network and respectively correspond to the lanes and the road sections one by one, and then lane and road section identification of each driving track point is determined. And, based on the travel track points mapped to the road network, the offset of each travel track point can be calculated. And storing the calculated offset according to the determined time stamp information of the lane section identification and the driving track point, so that the offset of the corresponding lane section to be detected can be directly obtained by directly passing through the time and the lane section in the subsequent process.
Some abnormal track points may exist in the acquired running track points, which may affect the accuracy of detection, for example, the speed of the running track points is extremely high or extremely low due to abnormality of GPS positioning equipment or traffic signal lamps, or even the running track points are lost. Aiming at the situation, before the driving track points are mapped into the road network, the collected driving track points are grouped according to the identification information of the equipment for collecting the driving track points; and calculating the speed of each driving track point in each group, and determining the sampling frequency of the equipment corresponding to each group. And removing abnormal track points in the collected driving track points according to the speed and the first preset interval of each driving track point, and the sampling frequency and the second preset interval of the equipment corresponding to each track point. Wherein the sampling frequency, also called sampling speed or sampling rate, defines the number of samples per second extracted from a continuous signal and constituting a discrete signal, which is expressed in hertz (Hz).
Fig. 2 is a schematic diagram of a distance error and a directivity error occurring in mapping a travel track point to a road network. If the road network data is not complete, the Distance Error (Distance Error) caused by mapping the driving track points to wrong positions in the mapping process and the direction Error (Directional Error) easily caused by short-Distance driving can both cause the detection accuracy, so the driving track points mapped to the road network are detected and abnormal points are removed. As shown in fig. 2, the actual driving tracks of the vehicle are a 1-b 1 and b 1-c 1, but since the road network data from b 1-c 1 is not available in the road network, the tracks from b 1-c 1 may be mapped to the road segments from b 1-d 1 in the mapping process, the offset of the driving track point is relatively large in calculation, and when detecting whether an obstacle exists in the road segments from b 1-d 1 in the following process, the data may cause an error, so that the distance error track needs to be removed. And the actual driving trajectories of the vehicle are a2 to b2, c2 to d2, etc., which cause a large error in detecting an obstacle in the lane, and thus are removed. For these misdirectional trajectories, the yaw angles of the trajectory directions a2 through b2, c2 through d2 from the lane base line, for example, may be relatively large, so they can be removed by the yaw angle of the sub-trajectory directions from the lane base line. Specifically, after the driving track points are mapped to the road network and the offset and the lane section mark of each driving track point are determined, and before the offset of the driving track points is stored according to the lane section mark and the timestamp information, the driving track points in the road network are connected according to the mark information of the equipment for collecting the driving track points and the lane section mark of the driving track points, and the track line of the lane section is obtained. The track line is generated by a vehicle continuously driving on a lane, for example, a bicycle continuously driving on a bicycle lane for 20 minutes, and the driving track points are obtained by a GPS positioning device and connected in a road network to form the track line of the driving. Dividing the track line into more than one sub-track line, calculating the average offset of the driving track point contained in each sub-track line, determining the sub-track line with the average offset larger than a first preset threshold value, and removing the driving track point contained in the sub-track line; determining the track direction of each sub-track line, and calculating the deflection angle between the track direction and the lane base line; and determining the sub-trajectory line of which the deflection angle is greater than a second preset threshold value, and removing the driving trajectory point contained in the sub-trajectory line.
If the lane is a single-way lane, vehicles moving backwards on the lane can encounter more driving obstacles, the track data of the vehicles moving backwards on the lane has little reference value for detecting whether obstacles exist on the lane, and the tracks moving backwards can be deleted. Specifically, after the driving track points are mapped into the road network, the offset of each driving track point and the lane road section mark are determined, and before the offset of the driving track points is stored according to the lane road section mark and the timestamp information, the driving track points in the road network are connected according to the mark information of the equipment for collecting the driving track points and the lane road section mark of the driving track points, so that the track line of the lane road section is obtained; determining the track direction of each track line; and determining a track line with the track direction different from the setting direction of the road section to be detected of the lane, and removing the driving track point contained in the track line. The set direction of the road section to be detected of the lane is the correct driving direction of the lane on the road section to be detected.
Fig. 3 to 5 are schematic diagrams of the offset of the road section to be detected of the lane within the preset time period determined according to the embodiment of the present invention, where the abscissa of fig. 3 to 5 represents the departure distance (offset) of the driving track point, the ordinate represents the offset (shift) of the driving track point, the departure distance is the projection of the driving track point on the lane base line, and is the distance from the start node of the road section to be detected of the lane, and the offset is the distance from the driving track point to the lane base line.
As shown in fig. 3, after the driving track points of the road section to be detected of the lane in the preset time period and the offset of each track point are determined, all the offsets can be combined into a detection offset set, all the offsets can be screened for improving the accuracy and reducing subsequent data processing, and the screened offsets are combined into a detection offset set. The screening method mainly comprises the following steps: the average offset and the first N largest offsets are extracted.
Specifically, the starting distance of each driving track point of the lane in a preset time period is determined, and the driving track points are grouped according to the starting distance of the driving track points and a preset first average value. And calculating the average offset of the driving track points in each group for the driving track points in each group, and forming a detection offset set by all the average offsets. As shown in fig. 4, if the preset first average value is 5 meters (m), the driving track points are grouped according to the departure distance of the driving track points and the preset first average value, that is, the driving track points with the departure distance within the range of 0-5m, the driving track points with the departure distance within the range of 5-10m, the driving track points with the departure distance within the range of 10-15m, and the like are determined. And further calculating the average offset of the driving track points in each group, wherein the average offset in each group forms a detection offset set, and the track points indicated by the triangle in fig. 4 are the track points corresponding to the average offset in each group. By the method, the problem of inaccurate detection caused by too high or too low offset can be avoided.
Specifically, a departure distance of each driving track point of a lane in a preset time period is determined, wherein the departure distance is a distance between a projection of the driving track point on a lane base line and a starting node of a road section to be detected of the lane. And grouping the driving track points according to the starting distance of the driving track points and a preset second average value. For the driving track points in each group, sorting the offset of the driving track points in the group from big to small, and selecting the first N offsets in the sorting to form a detection offset set; wherein N is a preset positive integer. As shown in fig. 5, if the preset second average value is 50m and N is 10, the driving track points are grouped according to the departure distance of the driving track points and the preset second average value, that is, the driving track points with the departure distance within the range of 0-50m (the driving track points shown in fig. 5), the driving track points with the departure distance within the range of 50-100m, and the like are determined. And further sequencing the offsets of the driving track points in each group from big to small, selecting the top 10(top-10) offsets in the sequencing, wherein the offsets of the top-10 in each group form a detection offset set, and the track points shown by the triangle in fig. 5 are the track points of the top-10. Because the lane obstacle may cause the highest offset, whether the obstacle exists in the road can be detected more accurately by the method.
Step S103: and judging whether the obstacle exists on the road section to be detected of the lane or not according to the similarity between the detection offset set and the reference offset set. Specifically, it is determined whether the distribution of the offsets in the detection offset set and the reference offset set coincides by Kolmogorov-Smirnov test (KS test). And checking whether the distribution of the offsets in the detected offset set conforms to the distribution of the offsets in the reference offset set or not by using the KS test, and if so, determining that the obstacles exist on the road section to be detected of the lane in a preset time period.
According to the embodiment of the invention, whether the obstacle exists in the road section to be detected of the lane in the preset time period is judged by mining the driving data of the road section to be detected of the lane in the preset time period, comparing the determined offset of the road section to be detected of the lane in the preset time period with the offset of the road section to be detected of the lane without the obstacle. Different from the manual detection or video information acquisition mode in the prior art, the lane obstacle detection method does not need to use additional detection equipment to detect lane obstacles, and can more accurately detect whether the obstacle exists in the road section to be detected of the lane in the preset time period through the driving track data. Meanwhile, the problem that a detection blind area occurs due to the fact that the coverage range is limited in the prior art is solved, and the detection cost is greatly reduced.
Fig. 6 is a schematic view of a main flow of a method of detecting a bicycle lane obstacle according to an embodiment of the present invention. Because the data of traveling on the bicycle lane is more, especially sharing bicycle data of traveling is abundant and high-quality, can effectively detect the barrier on the bicycle lane through sharing bicycle data of traveling, and this barrier includes the parking violating the regulations on the bicycle lane. Wherein, the bicycle is also called as a bicycle or a bicycle, and the bicycle lane is a bicycle special lane.
Shared vehicles have a wide range of uses and users, and are statistically in excess of 2 billion registered users and 3000 million daily trips, and process vehicles record detailed GPS trajectory data. Meanwhile, illegal vehicle parking events generally occur on roadside bicycle lanes, which obstruct the path of bicycle users and significantly affect the bicycle driving trajectory. Thus, by aggregating a large number of bicycle tracks on the same road, it is possible to identify illegal parking events by examining different parts of their tracks. In the prior art, conventional methods of detecting illegal vehicle parking events have relied primarily on human labor, such as police patrols. With the advancement of video object recognition technology, there are also illegal parking events recognized based on surveillance cameras. However, all existing methods (police patrols and surveillance cameras) are active detection methods and can only cover a limited spatial range, which makes them very inefficient, costly, and achieves high levels of coverage especially in large cities.
In the embodiment of the present invention, the sequence of the steps is not limited by fig. 6, for example, step S602 may be executed first, and then step S601 is executed. As shown in fig. 6, the main flow of the method for detecting a obstacle of a bicycle lane according to the embodiment of the present invention includes:
step S601: the method comprises the steps of collecting driving track points on each road section of a bicycle lane in a city at regular time, cleaning the collected driving track points according to speed and sampling rate rules, mapping the cleaned driving track points to a road network, and storing the offset of the driving track points on each road section of the bicycle lane at each time period according to lane road section identification (RID) and timestamp information of the driving track points.
The step S601 is a data preprocessing process, which is to acquire shared single-vehicle driving data of each road section of the bicycle lane at each time interval in the city, and map the cleaned driving data to the road network of the city. And determining the offset of the bicycle lane of each road section based on the track data mapped to the corresponding road section, and storing the offset according to the RID and the time stamp information of the driving data of the bicycle lane of each road section. Furthermore, when a certain road section of the bicycle lane is detected in the city, the corresponding offset is directly acquired according to the RID of the road section to be detected and the preset detection time.
The shared bicycle has the following characteristics: the running speed is lower; even on a one-way road, two-way driving is often performed; the method can enter areas without road networks; short trips are more numerous. In view of the above, there is a need to clean data during data preprocessing. Specifically, speed and sampling rate rules are used to remove erroneous trace points that result from a person using a single vehicle in a variety of ways. The speed and sampling rate rule is to remove abnormal data in the acquired travel track data according to the speed of the track and the sampling frequency of the equipment. The abnormal data mainly comprises the following two conditions: 1) an abnormal speed; because the collected driving track points are based on the positioning system of the mobile phone of the user, if the user forgets to turn off the lock and then takes another vehicle, the collected track points are no longer the driving track points of the bicycle, and the driving track of another vehicle taken by the user subsequently has no reference value for detecting the bicycle lane; or waiting at the intersection for a very slow trajectory generated by the traffic lights. 2) The abnormal track sampling rate is that some equipment can be temporarily disabled in the track recording process due to different GPS data acquisition equipment used by different users, so that jump points of the track are generated, and the data acquired by the GPS data acquisition equipment has no reference value for detecting a bicycle lane.
After the collected single-vehicle driving track points are cleaned through the process, the cleaned driving track points are mapped to the road network. The driving track points generated by the continuous driving of a single vehicle are mapped into the road network to form a track line, and the track line consists of a time sequence of the driving track points. Trace τ ═ { p1, p 2.. pn }, where the trajectory point pi ═ lat (lat)i,lngi,ti) I is more than or equal to 1 and less than or equal to n, n is the number of the acquired single-vehicle driving track points, latiIn latitude, longiIs longitude, tiIs a time stamp. And the road network is a directed graph G ═ (V, E), where V ═ V1, V2, …, vm } is a set of intersections, and E ═ E1, E2, …, es } is a set of bicycle lane baselines, m is the number of intersections of bicycle lanes in the road network, and s is the number of bicycle lane links in the road network. As shown in fig. 7, one track line mapped to the road network is τ ═ { p1, p2, p3, p4, p5}, the intersection point V ═ { V1, V2, V3, V4, V5, V6, V7} in the road network, and the bicycle lane baseline E ═ { E1, E2, E3, E4, E5, E6, E7, E8 }.
And mapping the acquired driving track points to a road network, and then determining the RID, shift and offset of each driving track point. As shown in fig. 8, after the travel track points p1, p2, and p3 are mapped to the road network, the corresponding road segments (frommode-tonde) are determined, and the RID, shift, and offset of the travel track points are further determined: p1(RID 1829, shift 1m, offset 0.5m), p2(RID 1829, shift 1m, offset 4m), and p3(RID 1829, shift 1m, offset 6 m). For positive and negative settings of the shift, as shown in fig. 8, it can be positive on one side of the way (e.g., p1, p2) and negative on the other side of the way (e.g., p 3).
In the embodiment of the invention, after RID, shift and offset of each driving track point are determined, because the mapping is not accurate due to incomplete road network data or short bicycle track, a geometric filter can be used for screening and removing the wrong mapping result. Geometry-based refinement is used to eliminate these errors, taking into account the random shift caused by the GPS sensor. First, if the average degree of deviation of a sub-track is greater than a certain threshold (e.g., 20 meters), the travel track points included in the sub-track are removed to eliminate the distance error. To eliminate the direction error, the yaw angle between the sub-track and the road is calculated, as shown in fig. 9. The sub-track is divided into two parts, such as the Halves of the projector shown in fig. 9, and the Centroid (Centroid) of the two parts is determined. As shown in FIG. 9, the yaw Angle (development Angle) between the sub-track direction and the road baseline is the direct Angle between the centroid point connecting line between the first portion and the second portion and the road baseline. If the yaw angle is greater than a corresponding predetermined threshold value (for example, 60 degrees), the travel track points included in the sub-track are deleted.
Since all roads are considered as bidirectional roads in the map matching process, there are some cases of reverse driving for unidirectional roads. Although the number of reverse travel trajectories is limited, the trajectories that are reversed generally have higher displacement value offsets as they are likely to encounter obstacles other than illegal parking events (bicycles traveling in the normal direction). Therefore, the back trajectory affects the accuracy of the illegal parking detection model. Therefore, the track data of the retrograde motion in the road to be detected can be removed according to the normal driving direction of the road to be detected.
Step S602: when the road section is confirmed to have no barrier, the running track points on each road section of the bicycle lane in the city are collected, the running track points are cleaned according to the speed and sampling rate rules, the cleaned running track points are mapped into the road network, and the offset of the running track points on each road section of the bicycle lane is saved according to the lane section identification of the running track points. For each road section of the bicycle lane, a reference offset is counted firstly, the condition that illegal parking on the bicycle lane is less at night is assumed, the parking condition is stable, and a reference offset set of each road section of the bicycle lane is determined by utilizing track data of large-scale night riding (11: 00 at night to 4: 00 in the morning of the next day). According to the lane section identification of the travel track point, the offset of the travel track point on each section of the bicycle lane is saved, and a reference offset set of a certain section in a certain period can be conveniently searched.
Step S603: determining a lane section mark of the section to be detected of the bicycle lane, acquiring the offset of the section to be detected of the bicycle lane from the offset stored in the step S601 according to the lane section mark, and determining a detection offset set of the section to be detected of the bicycle lane according to the acquired offset.
Determining a lane section identification of a section to be detected of the bicycle lane, and acquiring the offset of the section to be detected within a preset time period (for example, the latest hour) according to the lane section identification to form a detection offset set. The method for determining the detection offset set comprises the following steps: (1) extracting an average offset; extracting features of each track to be analyzed according to the average offset of each driving track point between every 10 meters; (2) and extracting the maximum offset, wherein the maximum N offset values on each track to be analyzed are extracted as features.
Step S604: and according to the lane section identification, acquiring the offset of the section to be detected of the bicycle lane from the offsets stored in the step S603, wherein the acquired offset forms a reference offset set of the section to be detected of the lane.
Step S605: and checking whether the distribution of the offsets in the detected offset set conforms to the distribution of the offsets in the reference offset set or not by using the KS test, and if so, determining that the obstacle exists on the road section to be detected of the bicycle lane in the preset time period. Determining the probability that the distribution of the offsets in the detected offset set is consistent with the distribution of the offsets in the reference offset set through KS (K-class-of-materials) test, and if the probability is lower than a preset judgment threshold, indicating that an obstacle exists in a road section to be detected of the bicycle lane within a preset time period; otherwise, no barrier exists on the road section to be detected of the bicycle lane within the preset time period. The preset judgment threshold is in a range of 0.19-0.35, and in the embodiment of the present invention, the preset threshold is set to be 0.29.
According to the embodiment of the invention, the driving data of the road section to be detected of the bicycle lane in the preset time period are mined, and the driving data of the road section to be detected of the bicycle lane in the absence of the barrier are mined. And further determining the offset distribution of the road section to be detected of the bicycle lane in the preset time period and the offset distribution of the road section to be detected of the bicycle lane without the barrier, and judging whether the two distributions are consistent through KS (stock verification) so as to judge whether the road section to be detected of the bicycle lane has the barrier in the preset time period. Different from the mode of manual patrol or video information acquisition in the prior art, the embodiment of the invention does not need to detect the illegal parking of the obstacles on the bicycle lane by means of additional detection equipment, and can more accurately detect whether the illegal parking exists in the road section to be detected of the bicycle lane in the preset time period by the running track data on the bicycle lane. Meanwhile, the problem that a detection blind area occurs due to the fact that the coverage range is limited in the prior art is solved, and the detection cost is greatly reduced.
Fig. 10 is a schematic diagram of main blocks of an apparatus for detecting a lane obstacle according to an embodiment of the present invention, and as shown in fig. 10, an apparatus 1000 for detecting a lane obstacle according to an embodiment of the present invention includes.
The reference offset determining module 1001 is configured to determine a reference offset set of a road segment to be detected of a lane; and when the offset in the reference offset set is that the road section to be detected of the lane has no barrier, the distance from the driving track point corresponding to the lane in the road section to be detected to the lane baseline is obtained.
The detection offset determining module 1002 is configured to determine a detection offset set of a to-be-detected road segment of a lane in a preset time period; and detecting the offset in the offset set as the distance from the driving track point corresponding to the lane in the road section to be detected to the lane baseline within a preset time period.
The detection offset determining module is further used for determining a starting distance of each driving track point of the lane in a preset time period, wherein the starting distance is a projection of the driving track point on a lane base line and a distance from a starting node of a to-be-detected road section of the lane; grouping the driving track points according to the starting distance of the driving track points and a preset first average value; and calculating the average offset of the driving track points in each group for the driving track points in each group, and forming a detection offset set by all the average offsets.
The detection offset determining module is further used for determining a starting distance of each driving track point of the lane in a preset time period, wherein the starting distance is a projection of the driving track point on a lane base line and a distance from a starting node of a to-be-detected road section of the lane; grouping the driving track points according to the starting distance of the driving track points and a preset second average value; for the driving track points in each group, sorting the offset of the driving track points in the group from big to small, and selecting the first N offsets in the sorting to form a detection offset set; wherein N is a preset positive integer.
The determining module 1003 is configured to determine whether an obstacle exists on the to-be-detected road segment of the lane according to the similarity between the detected offset set and the reference offset set. The judging module is also used for determining whether the distribution of the offset in the detection offset set and the reference offset set is consistent through a Kolmogorov-Schmilov test.
The device for detecting the lane obstacle further comprises a preprocessing module, a detection module and a control module, wherein the preprocessing module is used for mapping the driving track points to a road network and determining the offset of each driving track point and the lane section mark; and storing the offset of the driving track points according to the lane section identification and the timestamp information of the driving track points. The preprocessing module is also used for grouping the collected driving track points according to the identification information of the equipment for collecting the driving track points; calculating the speed of each driving track point in each group, and determining the sampling frequency of the equipment corresponding to each group; and removing abnormal track points in the collected driving track points according to the speed and the first preset interval of each driving track point, and the sampling frequency and the second preset interval of the equipment corresponding to each track point. The preprocessing module is also used for connecting the driving track points in the road network according to the identification information of the equipment for collecting the driving track points and the lane section identification of the driving track points to obtain the track line of the lane section; dividing the trajectory line into more than one sub-trajectory line; calculating the average offset of the driving track points contained in each sub-track line, determining the sub-track line with the average offset larger than a first preset threshold value, and removing the driving track points contained in the sub-track line; determining the track direction of each sub-track line, and calculating the deflection angle between the track direction and the lane base line; and determining the sub-trajectory line of which the deflection angle is greater than a second preset threshold value, and removing the driving trajectory point contained in the sub-trajectory line. The preprocessing module is also used for connecting the driving track points in the road network according to the identification information of the equipment for collecting the driving track points and the lane section identification of the driving track points to obtain the track line of the lane section; determining the track direction of each track line; and determining a track line with the track direction different from the setting direction of the road section to be detected of the lane, and removing the driving track point contained in the track line.
In an embodiment of the invention, the lane is a bicycle lane. The driving track points are shared driving data of the single vehicle.
According to the embodiment of the invention, whether the obstacle exists in the road section to be detected of the lane in the preset time period is judged by mining the driving data of the road section to be detected of the lane in the preset time period, comparing the determined offset of the road section to be detected of the lane in the preset time period with the offset of the road section to be detected of the lane without the obstacle. Different from the manual detection or video information acquisition mode in the prior art, the lane obstacle detection method does not need to use additional detection equipment to detect lane obstacles, and can more accurately detect whether the obstacle exists in the road section to be detected of the lane in the preset time period through the driving track data. Meanwhile, the problem that a detection blind area occurs due to the fact that the coverage range is limited in the prior art is solved, and the detection cost is greatly reduced.
Fig. 11 shows an exemplary system architecture 1100 to which the method of detecting a lane obstacle or the apparatus for detecting a lane obstacle of the embodiments of the present invention may be applied.
As shown in fig. 11, the system architecture 1100 may include terminal devices 1101, 1102, 1103, a network 1104, and a server 1105. The network 1104 is a medium to provide communication links between the terminal devices 1101, 1102, 1103 and the server 1105. Network 1104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
A user may use terminal devices 1101, 1102, 1103 to interact with a server 1105 over a network 1104 to receive or send messages or the like. Various messaging client applications, such as shopping applications, web browser applications, search applications, instant messaging tools, mailbox clients, social platform software, etc. (examples only) may be installed on the terminal devices 1101, 1102, 1103.
The terminal devices 1101, 1102, 1103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 1105 may be a server that provides various services, such as a backend management server (for example only) that provides support for shopping-like websites browsed by users using the terminal devices 1101, 1102, 1103. The background management server can analyze and process the received data such as the product information inquiry request and feed back the processing result to the terminal equipment.
It should be noted that the method for detecting a lane obstacle provided in the embodiment of the present invention is generally executed by the server 1105, and accordingly, the apparatus for detecting a lane obstacle is generally provided in the server 1105.
It should be understood that the number of terminal devices, networks, and servers in fig. 11 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 12, shown is a block diagram of a computer system 1200 suitable for use with a terminal device implementing an embodiment of the present invention. The terminal device shown in fig. 12 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 12, the computer system 1200 includes a Central Processing Unit (CPU)1201, which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)1202 or a program loaded from a storage section 1208 into a Random Access Memory (RAM) 1203. In the RAM 1203, various programs and data necessary for the operation of the system 1200 are also stored. The CPU 1201, ROM 1202, and RAM 1203 are connected to each other by a bus 1204. An input/output (I/O) interface 1205 is also connected to bus 1204.
The following components are connected to the I/O interface 1205: an input section 1206 including a keyboard, a mouse, and the like; an output portion 1207 including a display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 1208 including a hard disk and the like; and a communication section 1209 including a network interface card such as a LAN card, a modem, or the like. The communication section 1209 performs communication processing via a network such as the internet. A driver 1210 is also connected to the I/O interface 1205 as needed. A removable medium 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like, is mounted on the drive 1210 as necessary, so that a computer program read out therefrom is mounted into the storage section 1208 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 1209, and/or installed from the removable medium 1211. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 1201.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes a reference offset determination module, a detection offset determination module, and a determination module. The names of the modules do not form a limitation on the module itself under certain circumstances, for example, the determining module may be further described as a module that determines whether an obstacle exists on the to-be-detected road section of the lane according to the similarity between the detection offset set and the reference offset set.
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: determining a reference offset set of a to-be-detected road section of a lane; when the offset in the reference offset set is that the road section to be detected of the lane has no barrier, the distance from the driving track point corresponding to the lane in the road section to be detected to the lane baseline is; determining a detection offset set of a road section to be detected of a lane in a preset time period; detecting the offset in the offset set as the distance from a driving track point corresponding to the lane in the road section to be detected to the lane baseline within a preset time period; and judging whether the obstacle exists on the road section to be detected of the lane or not according to the similarity between the detection offset set and the reference offset set.
According to the embodiment of the invention, whether the obstacle exists in the road section to be detected of the lane in the preset time period is judged by mining the driving data of the road section to be detected of the lane in the preset time period, comparing the determined offset of the road section to be detected of the lane in the preset time period with the offset of the road section to be detected of the lane without the obstacle. Different from the manual detection or video information acquisition mode in the prior art, the lane obstacle detection method does not need to use additional detection equipment to detect lane obstacles, and can more accurately detect whether the obstacle exists in the road section to be detected of the lane in the preset time period through the driving track data. Meanwhile, the problem that a detection blind area occurs due to the fact that the coverage range is limited in the prior art is solved, and the detection cost is greatly reduced.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (18)

1. A method of detecting a lane obstacle, comprising:
determining a reference offset set of a to-be-detected road section of a lane; when the offset in the reference offset set is the distance from a driving track point corresponding to the lane to a lane baseline in the road section to be detected when the road section to be detected of the lane has no barrier;
determining a detection offset set of a to-be-detected road section of the lane within a preset time period;
the offset in the detection offset set is the distance from a driving track point corresponding to the lane in the road section to be detected to the lane baseline within a preset time period;
judging whether an obstacle exists on a road section to be detected of the lane according to the similarity between the detection offset set and the reference offset set;
before determining a set of detection offset of a road section to be detected of the lane in a preset time period, connecting the driving track points in a road network according to identification information of equipment for collecting the driving track points and lane section identifications of the driving track points to obtain a track line of the lane section;
dividing the trajectory line into more than one sub-trajectory line;
calculating the average offset of the driving track points contained in each sub-track line, determining the sub-track line with the average offset larger than a first preset threshold value, and removing the driving track points contained in the sub-track line;
determining the track direction of each sub-track line, and calculating the deflection angle between the track direction and the lane base line; and determining the sub-trajectory line of which the deflection angle is greater than a second preset threshold value, and removing the driving trajectory point contained in the sub-trajectory line.
2. The method according to claim 1, before determining the set of detection offsets for the to-be-detected road segments of the lane within a preset time period, further comprising:
mapping the driving track points to a road network, and determining the offset of each driving track point and a lane road section identifier;
and storing the offset of the driving track points according to the lane section identification and the timestamp information of the driving track points.
3. The method of claim 2, further comprising, prior to mapping the travel track points into the road network:
grouping the collected driving track points according to the identification information of the equipment for collecting the driving track points;
calculating the speed of each driving track point in each group, and determining the sampling frequency of the equipment corresponding to each group;
and removing abnormal track points in the collected driving track points according to the speed and the first preset interval of each driving track point, and the sampling frequency and the second preset interval of the equipment corresponding to each track point.
4. The method of claim 2, wherein after mapping the driving trace points into the road network and determining the offset of each driving trace point and the lane segment identifier, and before storing the offset of the driving trace points according to the lane segment identifier and the timestamp information, further comprising:
connecting the driving track points in the road network according to the identification information of the equipment for collecting the driving track points and the lane section identification of the driving track points to obtain the track line of the lane section;
determining the track direction of each track line;
and determining a track line with the track direction different from the setting direction of the road section to be detected of the lane, and removing the driving track point contained in the track line.
5. The method according to claim 1, characterized in that the step of determining a set of detection offsets for the to-be-detected section of the lane within a preset time period comprises:
determining a starting distance of each driving track point of the lane in a preset time period, wherein the starting distance is a distance between a projection of the driving track point on a lane base line and a starting node of a road section to be detected of the lane;
grouping the driving track points according to the starting distance of the driving track points and a preset first average value;
and calculating the average offset of the driving track points in each group for the driving track points in each group, and forming a detection offset set by all the average offsets.
6. The method according to claim 1, characterized in that the step of determining a set of detection offsets for the to-be-detected section of the lane within a preset time period comprises:
determining a starting distance of each driving track point of the lane in a preset time period, wherein the starting distance is a distance between a projection of the driving track point on a lane base line and a starting node of a road section to be detected of the lane;
grouping the driving track points according to the starting distance of the driving track points and a preset second average value;
for the driving track points in each group, sorting the offset of the driving track points in the group from big to small, and selecting the first N offsets in the sorting to form a detection offset set; wherein N is a preset positive integer.
7. The method of claim 1, wherein determining the similarity of the set of detected offsets to a set of reference offsets comprises:
determining whether the distribution of offsets in the set of detected offsets and the set of reference offsets is consistent by a kolmogorov-smirnov test.
8. The method of any one of claims 1-7, wherein the roadway is a bike roadway; and/or the running track points are shared single-vehicle running data.
9. An apparatus for detecting a lane obstacle, comprising:
the reference offset determining module is used for determining a reference offset set of a road section to be detected of the lane; when the offset in the reference offset set is the distance from a driving track point corresponding to the lane to a lane baseline in the road section to be detected when the road section to be detected of the lane has no barrier;
the detection offset determining module is used for determining a detection offset set of a road section to be detected of the lane within a preset time period; the offset in the detection offset set is the distance from a driving track point corresponding to the lane in the road section to be detected to the lane baseline within a preset time period;
the judging module is used for judging whether an obstacle exists on the road section to be detected of the lane according to the similarity between the detection offset set and the reference offset set;
the preprocessing module is further used for connecting the driving track points in the road network according to the identification information of the equipment for collecting the driving track points and the lane section identification of the driving track points to obtain the track line of the lane section;
dividing the trajectory line into more than one sub-trajectory line; calculating the average offset of the driving track points contained in each sub-track line, determining the sub-track line with the average offset larger than a first preset threshold value, and removing the driving track points contained in the sub-track line; determining the track direction of each sub-track line, and calculating the deflection angle between the track direction and the lane base line; and determining the sub-trajectory line of which the deflection angle is greater than a second preset threshold value, and removing the driving trajectory point contained in the sub-trajectory line.
10. The device of claim 9, further comprising a preprocessing module for mapping the driving track points into a road network and determining an offset of each driving track point and a lane section identifier; and storing the offset of the driving track points according to the lane section identification and the timestamp information of the driving track points.
11. The device according to claim 10, wherein the preprocessing module is further configured to group the collected driving trace points according to identification information of a device that collects the driving trace points; calculating the speed of each driving track point in each group, and determining the sampling frequency of the equipment corresponding to each group; and removing abnormal track points in the collected driving track points according to the speed and the first preset interval of each driving track point, and the sampling frequency and the second preset interval of the equipment corresponding to each track point.
12. The device according to claim 10, wherein the preprocessing module is further configured to connect the driving track points in the road network according to the identification information of the device for collecting the driving track points and the lane section identification of the driving track points to obtain the track line of the lane section; determining the track direction of each track line; and determining a track line with the track direction different from the setting direction of the road section to be detected of the lane, and removing the driving track point contained in the track line.
13. The device according to claim 9, wherein the detection offset determining module is further configured to determine a departure distance of each driving track point of the lane within a preset time period, where the departure distance is a distance between a projection of the driving track point on a lane base line and a start node of a to-be-detected road segment of the lane; grouping the driving track points according to the starting distance of the driving track points and a preset first average value; and calculating the average offset of the driving track points in each group for the driving track points in each group, and forming a detection offset set by all the average offsets.
14. The device according to claim 9, wherein the detection offset determining module is further configured to determine a departure distance of each driving track point of the lane within a preset time period, where the departure distance is a distance between a projection of the driving track point on a lane base line and a start node of a to-be-detected road segment of the lane; grouping the driving track points according to the starting distance of the driving track points and a preset second average value; for the driving track points in each group, sorting the offset of the driving track points in the group from big to small, and selecting the first N offsets in the sorting to form a detection offset set; wherein N is a preset positive integer.
15. The apparatus of claim 9, wherein the determining module is further configured to determine whether the distribution of offsets in the set of detected offsets and the set of reference offsets is consistent through a kolmogorov-smirnov test.
16. The apparatus of any one of claims 9-15, wherein the roadway is a bike roadway; and/or the running track points are shared single-vehicle running data.
17. An electronic device that detects a lane obstacle, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-8.
18. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-8.
CN201810534328.XA 2018-05-29 2018-05-29 Method and device for detecting lane obstacle Active CN108766031B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810534328.XA CN108766031B (en) 2018-05-29 2018-05-29 Method and device for detecting lane obstacle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810534328.XA CN108766031B (en) 2018-05-29 2018-05-29 Method and device for detecting lane obstacle

Publications (2)

Publication Number Publication Date
CN108766031A CN108766031A (en) 2018-11-06
CN108766031B true CN108766031B (en) 2020-11-24

Family

ID=64003638

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810534328.XA Active CN108766031B (en) 2018-05-29 2018-05-29 Method and device for detecting lane obstacle

Country Status (1)

Country Link
CN (1) CN108766031B (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109816271A (en) * 2019-02-25 2019-05-28 东南大学 Cycle track service level evaluation method based on shared bicycle track data
CN111325986B (en) * 2019-04-04 2020-12-22 北京嘀嘀无限科技发展有限公司 Abnormal parking monitoring method and device, electronic equipment and storage medium
CN110136442A (en) * 2019-05-20 2019-08-16 东南大学 Pedestrian based on shared bicycle GPS track data occupies road Activity recognition method
CN111578839B (en) * 2020-05-25 2022-09-20 阿波罗智联(北京)科技有限公司 Obstacle coordinate processing method and device, electronic equipment and readable storage medium
CN113158759A (en) * 2021-02-19 2021-07-23 合肥海赛信息科技有限公司 Video analysis-based store-out operation intelligent detection method
CN113641734B (en) * 2021-08-12 2024-04-05 驭势科技（北京）有限公司 Data processing method, device, equipment and medium
CN114724407B (en) * 2022-03-25 2023-05-30 中电达通数据技术股份有限公司 Correct lane identifying method based on multiple data sources in road fitting
CN115830872B (en) * 2022-12-23 2023-09-01 东南大学 Method for judging elastic influence of accident occurrence on bicycle use

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101140699B (en) * 2007-09-27 2010-09-08 深圳华强信息产业有限公司 Circuit inspection method based on vehicle mounted GPS terminal
JP5796481B2 (en) * 2011-12-21 2015-10-21 トヨタ自動車株式会社 Trajectory control device and trajectory control method
US9633564B2 (en) * 2012-09-27 2017-04-25 Google Inc. Determining changes in a driving environment based on vehicle behavior
CN104318766B (en) * 2014-10-22 2016-06-08 北京建筑大学 A kind of road network method of public transport GPS track data
JP6308186B2 (en) * 2015-08-28 2018-04-11 トヨタ自動車株式会社 Collision avoidance support device

Also Published As

Publication number Publication date
CN108766031A (en) 2018-11-06

Similar Documents

Publication Publication Date Title
CN108766031B (en) Method and device for detecting lane obstacle
US10403138B2 (en) Traffic accident warning method and traffic accident warning apparatus
US9459626B2 (en) Learning signs from vehicle probes
EP3078937B1 (en) Vehicle position estimation system, device, method, and camera device
Koukoumidis et al. Leveraging smartphone cameras for collaborative road advisories
CN109472884B (en) Unmanned vehicle data storage method, device, equipment and storage medium
CN103903465B (en) A kind of congestion in road reason real-time release method and system
US10984275B1 (en) Determining location coordinates of a vehicle based on license plate metadata and video analytics
US20230066501A1 (en) Method, apparatus, and system for traffic estimation based on anomaly detection
CN110942038A (en) Traffic scene recognition method, device, medium and electronic equipment based on vision
CN111489555A (en) Traffic running state prediction method, device and system
CN113899355A (en) Map updating method and device, cloud server and shared riding equipment
CN112885112B (en) Vehicle driving detection method, vehicle driving early warning method and device
CN112101223A (en) Detection method, device, equipment and computer storage medium
CN111380544A (en) Method and device for generating map data of lane line
CN111737377A (en) Method and device for identifying drift trajectory, computing equipment and storage medium
JP2023524623A (en) Method, apparatus, equipment, storage medium and program for detecting traffic anomalies
Garg et al. Mining bus stops from raw GPS data of bus trajectories
US20180260401A1 (en) Distributed video search with edge computing
CN104299445B (en) A kind of parking gap real-time information collection, process, delivery system and method
CN109308806B (en) Driving detection method of vehicle and server
CN110956809A (en) System and method for monitoring vehicle passing intersection
Yue et al. Smart phone application for connected vehicles and smart transportation
Zhu et al. Mining large-scale GPS streams for connectivity refinement of road maps
Bhandari et al. Fullstop: A camera-assisted system for characterizing unsafe bus stopping

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information

Address after: 101111 Room 221, 2nd Floor, Block C, 18 Kechuang 11th Street, Beijing Economic and Technological Development Zone

Applicant after: JINGDONG DIGITAL TECHNOLOGY HOLDINGS Co.,Ltd.

Address before: 101111 Room 221, 2nd Floor, Block C, 18 Kechuang 11th Street, Beijing Economic and Technological Development Zone

Applicant before: BEIJING JINGDONG FINANCIAL TECHNOLOGY HOLDING Co.,Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant
CP01 Change in the name or title of a patent holder

Address after: 101111 Room 221, 2nd Floor, Block C, 18 Kechuang 11th Street, Beijing Economic and Technological Development Zone

Patentee after: Jingdong Technology Holding Co.,Ltd.

Address before: 101111 Room 221, 2nd Floor, Block C, 18 Kechuang 11th Street, Beijing Economic and Technological Development Zone

Patentee before: Jingdong Digital Technology Holding Co.,Ltd.

Address after: 101111 Room 221, 2nd Floor, Block C, 18 Kechuang 11th Street, Beijing Economic and Technological Development Zone

Patentee after: Jingdong Digital Technology Holding Co.,Ltd.

Address before: 101111 Room 221, 2nd Floor, Block C, 18 Kechuang 11th Street, Beijing Economic and Technological Development Zone

Patentee before: JINGDONG DIGITAL TECHNOLOGY HOLDINGS Co.,Ltd.

CP01 Change in the name or title of a patent holder