CN111596309A

CN111596309A - Vehicle queuing measurement method based on laser radar

Info

Publication number: CN111596309A
Application number: CN202010299678.XA
Authority: CN
Inventors: 刘磊; 赵彦峰
Original assignee: Nanjing Zhuoyu Intelligent Technology Co ltd
Current assignee: Nanjing Zhuoyu Intelligent Technology Co ltd
Priority date: 2020-04-16
Filing date: 2020-04-16
Publication date: 2020-08-28
Anticipated expiration: 2040-04-16
Also published as: CN111596309B

Abstract

The invention relates to the technical field of laser radar measurement, in particular to a vehicle queuing measurement method based on a laser radar. The invention has the beneficial effects that: the method can quickly filter the ground point cloud, eliminate irrelevant noise interference, and has the advantages of high reliability, high precision, wide application range, accurate calculation of vehicle queuing length and small error.

Description

Vehicle queuing measurement method based on laser radar

Technical Field

The invention relates to the technical field of laser radar measurement, in particular to a vehicle queuing measurement method based on a laser radar.

Background

Lidar is a generic term for active detection of sensor devices by laser. For the measurement imaging laser radar, the main working principle is to realize three-dimensional scanning measurement (imaging) of the target profile through high-frequency ranging and scanning angle measurement. Surveying imaging LiDAR is largely comprised of two broad categories, survey-type LiDAR and navigation-type LiDAR. The measurement type LiDAR is mainly used for high-precision mapping; the navigation type LiDAR is mainly used for navigation obstacle avoidance of intelligent vehicles, robots and flying equipment. The measurement principle and the technical basis of the two types of products are similar, and the main difference is the difference of the operation mode, the detection distance and the measurement precision. The navigational LiDAR products trade off the reduction in the size and weight of the device and the increase in the number of laser scan lines at the expense of detection distance, range/angle measurement accuracy, and detection imaging gray scale. In addition, navigational LiDAR performs three-dimensional contouring of a target via multiple scan lines. Compared with auxiliary driving sensors such as a camera, an ultrasonic radar and a millimeter wave radar, the laser radar is the 'intelligent vehicle eye' really having the space three-dimensional resolution capability.

The conventional lidar filtering ground algorithm mainly adopts a PCL-based RANSAC algorithm, and the RANSAC is an abbreviation of "Random Sample Consensus". It can iteratively estimate the parameters of the mathematical model from a set of observed data sets comprising "outliers". It is an uncertain algorithm-it has a certain probability to get a reasonable result; the number of iterations must be increased in order to increase the probability.

The basic assumptions of RANSAC are:

(1) the data consists of "local points", for example: the distribution of the data can be interpreted with some model parameters;

(2) "outliers" are data that cannot fit into the model;

(3) the data beyond this is noise.

The reasons for the occurrence of the out-of-office points are: an extremum of noise; the wrong measurement method; an erroneous assumption of the data. RANSAC also makes the following assumptions: given a set of (usually small) local interior points, there is a process that can estimate the model parameters; and the model can be interpreted or adapted to the local site. A certain distance threshold is set through a RANSAC filtering algorithm of PCL, no matter the threshold is set too large or too small, the ground cannot be well filtered, and the point cloud of other objects can be filtered out if the threshold is set too large.

Disclosure of Invention

The invention aims to overcome the problems in the prior art and provides a vehicle queuing measurement method based on a laser radar, which can solve the problems in the prior art at least to a certain extent.

In order to achieve the technical purpose and achieve the technical effect, the invention is realized by the following technical scheme:

a vehicle queuing measurement method based on laser radar comprises the following steps:

1) filtering the point cloud close to the ground, comprising the following steps:

filtering ground point clouds by using a RANSAC algorithm and laser radar height included angle information in the ground filtering process by using a multi-thread laser radar, and then acquiring point cloud information of an upper layer on a road;

2) calculating the length of the vehicle based on a K-means algorithm, comprising the following steps:

2.1) selecting some classes/groups and randomly initializing their respective center points;

2.2) calculating the distance from each data point to the central point, and dividing the data point into which class as the data point is closest to which central point;

2.3) calculating the central point in each class as a new central point;

2.4) repeating the steps until the change of each type of center is not large after each iteration;

3) and determining the position of the automobile based on a clustering algorithm and the reflection intensity of the laser radar, wherein the data point cloud format output by the multi-thread laser radar is (x, y, r), x and y are coordinate values of a scanning point, and r is the reflection intensity.

As a further optimization of the above technical solution, in the step 1), the point cloud is filtered by a straight-line distance from each thread in the multi-thread laser radar to the ground.

As a further optimization of the above technical solution, in step 3), the reflection intensity of the multi-thread lidar is set to (0,255).

The invention has the beneficial effects that: the method can quickly filter the ground point cloud, eliminate irrelevant noise interference, and has the advantages of high reliability, high precision, wide application range, accurate calculation of vehicle queuing length and small error.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a demonstration diagram of the step of calculating the length of a vehicle based on the K-means algorithm in the present invention;

FIG. 2 is an illustration of the steps in the present invention for determining vehicle location based on clustering algorithm and laser radar reflection intensity.

Detailed Description

In order to make the technical means, the creation features, the achievement purposes and the effects of the invention easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

filtering ground point clouds by using a multi-thread laser radar and using a RANSAC algorithm and laser radar height included angle information in the process of filtering the ground, then obtaining point cloud information of upper layers of roads, wherein the straight line distance from each thread to the ground is known, and the point clouds close to the ground can be filtered according to the information;

referring to fig. 1, 2) the calculation of the vehicle length based on the K-means algorithm is mainly an algorithm work performed on the point cloud remaining after the removal of the ground, and includes the following steps:

2.1) first we select some classes/groups and randomly initialize their respective center points. The center point is the same length position as each data point vector. This requires us to predict the number of classes (i.e. the number of center points) in advance;

2.3) calculating the central point in each class as a new central point;

2.4) repeating the above steps until the center of each class does not change much after each iteration. Or the central point can be initialized randomly for many times, and then the best one of the operation results is selected;

please refer to fig. 2) the position of the vehicle is determined based on the clustering algorithm and the reflection intensity of the laser radar, the data point cloud output by the multi-thread laser radar has a format of (x, y, r), x and y are coordinate values of the scanning point, r is the reflection intensity, the reflection intensity of the multi-thread laser radar is (0,255), generally, the reflection intensity of the object which is more bright and opaque is stronger, so the reflection intensity of the vehicle is far greater than that of other objects, such as a road and a green belt, and the intensity of the point cloud which is scanned by the laser radar on the vehicle is usually greater than 200.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A vehicle queuing measurement method based on laser radar is characterized by comprising the following steps:

2.3) calculating the central point in each class as a new central point;

2. The method for laser radar-based vehicle queuing measurement according to claim 1, wherein in step 1), the point cloud is filtered by the linear distance from each thread in the multi-thread laser radar to the ground.

3. The method for laser radar-based vehicle queuing measurement according to claim 1, wherein in step 3), the reflection intensity of the multi-thread laser radar is (0, 255).