CN114002708B - Tail wave filtering method for unmanned ship application - Google Patents
Tail wave filtering method for unmanned ship application Download PDFInfo
- Publication number
- CN114002708B CN114002708B CN202111220246.6A CN202111220246A CN114002708B CN 114002708 B CN114002708 B CN 114002708B CN 202111220246 A CN202111220246 A CN 202111220246A CN 114002708 B CN114002708 B CN 114002708B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- tail wave
- height difference
- point
- cloud data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000001914 filtration Methods 0.000 title claims abstract description 47
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 38
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000017525 heat dissipation Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 description 14
- 230000011218 segmentation Effects 0.000 description 11
- 230000000694 effects Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 5
- 230000008447 perception Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- KRTSDMXIXPKRQR-AATRIKPKSA-N monocrotophos Chemical compound CNC(=O)\C=C(/C)OP(=O)(OC)OC KRTSDMXIXPKRQR-AATRIKPKSA-N 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Radar Systems Or Details Thereof (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention discloses a tail wave filtering method applied to an unmanned ship, and belongs to the field of unmanned ship water surface environment sensing and understanding. Comprising the following steps: s1, acquiring point cloud data of the water surface environment around an unmanned ship, wherein the point cloud data are obtained through multi-line rotary laser radar scanning; s2, clutter and noise points of the point cloud data are removed; s3, identifying tail wave points of the filtered point cloud data, wherein the tail wave point identification comprises the following steps: s31, calculating the actual height difference of two adjacent laser reflection points in the vertical direction in the point cloud data; s32, calculating the ratio of the actual height difference to the theoretical height difference of each point cloud data point to be used as a normalized height difference; s33, identifying a point with the normalized height difference lower than a first threshold as a tail wave point; s4, removing tail wave points from the point cloud data. According to the invention, the ratio of the actual height difference to the theoretical height difference of each point cloud data point is used as the characteristic of the normalized height difference, so that the tail wave point cloud can be accurately identified, all tail wave points are ensured to be found, and the tail wave point cloud is simply and efficiently removed.
Description
Technical Field
The invention belongs to the field of unmanned ship water surface environment sensing and understanding, and particularly relates to a tail wave filtering method for unmanned ship application.
Background
The laser radar is one of the most important environment sensing sensors for unmanned ships to navigate independently avoiding obstacles. The laser radar periodically scans the surrounding water surface environment to acquire the azimuth and geometric shape information of the obstacle targets, and the unmanned ship recognizes and positions the obstacles in the surrounding environment through an environment sensing algorithm, so that autonomous obstacle avoidance navigation is completed. However, when the ship sails on the water surface, the generated tail waves reflect laser so as to generate echo point clouds in the laser radar field of view, and the echo point clouds are often misjudged as water surface obstacles by an environment perception algorithm, so that 'target false alarms' are caused; and when an obstacle exists in the tail wave area, the tail wave point cloud can interfere with an environment sensing algorithm, so that 'target misjudgment' is caused. Therefore, a certain algorithm is needed to filter the tail wave point cloud.
Tail wave filtering is always a technical difficulty in the field of unmanned boat water surface environment sensing and understanding, and no better solution exists at present. In practical unmanned boat applications, some simple and inefficient processing of the tail wave point cloud is often only possible. For example, the point cloud in the fixed sector of the stern is directly subtracted based on the a priori that the stern wave is generated at the stern. Obviously, the size of the tail wave area changes in real time along with the change of the ship speed and the sea condition, and the sector range is difficult to determine, so that the method can only be used in the low-ship speed and low-sea condition scenes; in addition, the method can reduce the perception capability of the unmanned ship on the near-distance target, and has larger application limitation. Meanwhile, as the method can not completely filter tail wave point clouds, a certain problem of 'target false alarm' and 'target misjudgment' still exists, and time-consuming 'target judgment and false alarm removal' processing still needs to be carried out in the subsequent steps. Therefore, a simple and efficient tail wave filtering method is needed.
The water surface scene point cloud can be regarded as being composed of an obstacle target point cloud, a tail wave point cloud and a clutter noise point. Clutter noise is usually represented as "outliers", and can be removed well by using a filter method, and at this time, the problem of tail wave filtering can be modeled as a problem of dividing the target point cloud and the tail wave point cloud, namely, a classification problem of the target point and the tail wave point. Therefore, the key to solve the problem of tail wave filtering is to find the characteristics of strong classifying ability for the target point and the tail wave point, high scene adaptability, namely strong accuracy and good robustness. At present, few related researches are specially used for tail wave filtering. One method is based on the assumption that tail wave point clouds are positioned at relatively low height in the whole water surface scene point clouds, and the low-height point clouds in the whole scene are directly removed by using a height threshold screening method; this can result in that part of the point cloud in the target, which is close to the water surface, is also removed, namely "over-segmentation", so that the target is "broken", thereby affecting the subsequent detection and identification of the target, and in high sea conditions, the height range covered by the tail wave point cloud is generally overlapped with the water surface target to a certain extent, so that the assumption is no longer satisfied, and the algorithm is disabled. One method is based on the characteristic that the height difference of the local area of the tail wave point cloud is small, and the height difference of the local area of the target point cloud is large, voxel filtering or grid filtering is carried out on the whole scene point cloud, the height difference of point cloud clusters in voxel grids or grids is calculated, and the point cloud clusters in the voxel grids or grids with the height difference lower than a certain threshold value are removed; similarly, a simple threshold strategy is difficult to adapt to various sea conditions, partial tail wave point clouds are usually remained in the method, namely 'under segmentation', partial point clouds with smaller local height difference in the target are also removed through 'over segmentation', and subsequent target detection and recognition are affected, so that the method is poor in effect. The existing methods can not find out the characteristics of strong classifying ability for the target point and the tail wave point and high scene adaptation, so that partial tail wave filtering effect can be realized only in a specific scene, the problem of 'under segmentation' or 'over segmentation' appears, and the problem of tail wave filtering can not be solved well.
Disclosure of Invention
Aiming at the defects and improvement demands of the prior art, the invention provides a tail wave filtering method applied to an unmanned ship, which aims to simply and efficiently filter tail wave point clouds in a water surface scene by constructing the characteristics of strong classifying capability for target points and tail wave points and high scene adaptability; the problems of under-segmentation and over-segmentation existing in the existing tail wave filtering method are solved; and time-consuming 'target discrimination and false alarm removal' processing in the subsequent environment sensing algorithm is avoided.
In order to achieve the above object, according to a first aspect of the present invention, there is provided a tailwave filtering method for unmanned ship application, the method comprising:
S1, acquiring point cloud data of the water surface environment around an unmanned ship, wherein the point cloud data are obtained through multi-line rotary laser radar scanning;
S2, clutter and noise points of the point cloud data are removed;
S3, identifying tail wave points of the point cloud data after clutter noise filtering, wherein the method comprises the following steps:
S31, calculating the actual height difference of two adjacent laser reflection points in the vertical direction in the point cloud data according to the plane geometry;
s32, calculating the ratio of the actual height difference to the theoretical height difference of each point cloud data point to be used as a normalized height difference;
S33, identifying points with the normalized height difference lower than a first threshold as tail wave points, and adding the tail wave points into a tail wave point set;
S4, removing the identified tail wave point set from point cloud data of the water surface environment.
Preferably, after step S33, further comprising:
S34, calculating the absolute height of each point in the Z-axis direction according to the plane geometry;
s35, eliminating points with absolute heights larger than or equal to a second threshold value in the tail wave point set.
Preferably absolute heightThe calculation formula is as follows:
wherein, d n is used for the treatment of the heat dissipation, The target distance and the vertical emission angle obtained by the nth laser are shown, respectively.
The beneficial effects are that: aiming at the problem of easy 'over-segmentation' in tail wave filtering (namely, part of a water surface obstacle target point cloud is classified as a tail wave point cloud), the invention eliminates the part with the absolute height characteristic value larger than or equal to a second threshold value from a tail wave point cloud set determined in the step S33 by constructing the absolute height of the point cloud in the Z-axis direction based on the prior knowledge that the obstacle target is usually far higher than the tail wave plane, and the rest is a real tail wave point set. Because the target point cloud (namely the water surface obstacle point cloud) which is misclassified as the tail wave point is removed, the accuracy of tail wave point cloud identification is ensured on the premise of not reducing the recall ratio, and the problem of over-segmentation in tail wave filtering is avoided.
Preferably, the second threshold is determined by: the variance of the absolute height between the two classes of target point and tail wave point is maximized to determine a second threshold.
The beneficial effects are that: the absolute height characteristic values of the tail wave point cloud and the target point cloud are distributed in a certain value range, the value range is continuously changed due to the change of the conditions such as the target type, the sea condition and the like, and a simple threshold strategy is generally difficult to deal with. According to the invention, by maximizing the variance of the absolute heights of the target point and the tail wave point, a corresponding screening threshold value is adaptively calculated for each frame of water surface scene point cloud, and the method can be robustly adapted to various condition changes, so that the tail wave point cloud and the target point cloud can be accurately distinguished.
Preferably, the height difference is normalizedThe calculation formula is as follows:
wherein, d n is used for the treatment of the heat dissipation, The target distance and vertical emission angle, d n+k,Respectively representing the target distance and the vertical emission angle obtained by the n+k laser; the harness numbers n, n+k denote two adjacent lasers in the vertical direction that strike the obstacle.
The beneficial effects are that: aiming at the problem of 'under-segmentation' which is easy to occur in tail wave filtering (namely tail wave point clouds in a scene are not completely identified), the problem is analyzed by the method because the characteristics of classifying target points and tail wave points in the prior art are not accurate enough, and the normalized height difference characteristics of reflection points of two adjacent lasers in the vertical direction are further constructed. The normalized height difference characteristic value of the target point is usually large and is close to 1, and the normalized height difference characteristic value of the tail wave point is small and is close to 0, so that the screening mode can effectively classify the target point and the tail wave point, ensure that all the tail wave points are found out, ensure the recall ratio of the tail wave point, and further avoid the problem of undersegmentation in tail wave filtering.
Preferably, step S2 employs a statistical filter.
The beneficial effects are that: aiming at the clutter noise problem in point cloud data, the invention is based on priori knowledge of clutter noise in water surface environment point cloud data, which is usually scattered points caused by electromagnetic noise, water surface ripple reflection and the like, a statistical filter is preferably adopted in step S2, and the scattered clutter noise in the water surface scene point cloud is accurately filtered by counting the average distance from each data point in European space to k nearest points and eliminating the 'outlier' with too far distance. Compared with general point cloud filtering methods such as voxel filtering and grid filtering, the method can cause the problem of downsampling of the original point cloud, the original point cloud and the tail wave point cloud are not affected, and the follow-up accurate filtering of the tail wave point cloud is ensured.
To achieve the above object, according to a second aspect of the present invention, there is provided a computer-readable storage medium storing one or more first programs, which are executed by one or more processors to implement the steps of a wake filtering method for unmanned aerial vehicle applications as described in the first aspect.
In general, through the above technical solutions conceived by the present invention, the following beneficial effects can be obtained:
(1) Aiming at the problem that classification characteristics of target points and tail wave points are not accurate enough in the prior art, the invention constructs the normalized height difference characteristics of reflection points of two adjacent lasers in the vertical direction. When two adjacent lasers in the vertical direction strike an obstacle and a tail wave, the characteristic of great difference of vertical height is shown, and the target point and the tail wave point in the scene point cloud of the water surface can be accurately distinguished through a threshold screening strategy.
(2) Aiming at the problem that classification characteristics of target points and tail wave points are not robust enough in the prior art, the invention normalizes the characteristic value of the height difference to a value range of 0-1 by solving the ratio of the actual height difference to the theoretical height difference, namely normalizing the height difference, solves the problem that the characteristic value of the height difference changes along with the target distance due to the inherent characteristic that the imaging distance of the laser radar is longer and sparser, and achieves the effect of normalizing the characteristic value of the height difference on the robustness of the imaging distance. Meanwhile, when the unmanned ship jolts due to sea condition change, the normalized height difference feature provided by the invention can still accurately distinguish the target point cloud and the tail wave point cloud, ensure the tail wave filtering effect and achieve the effect of robustness of the normalized height difference feature to sea condition conditions.
Therefore, the normalized height difference feature provided by the invention can accurately classify the target point cloud and the tail wave point cloud, ensure the recall ratio of tail wave point cloud identification, and avoid the problem of under segmentation caused by inaccurate classification in tail wave filtering. Meanwhile, the characteristic robustness is good, the influence of the condition changes such as the target distance and sea conditions can be overcome, and the tail wave filtering effect is ensured.
(3) Aiming at the problem of easy 'over-segmentation' in tail wave filtering, the invention constructs the absolute height characteristic of the point cloud in the Z-axis direction based on the prior knowledge that the obstacle target is usually far higher than the tail wave plane, eliminates the target point cloud which is misclassified as 'tail wave point' through a threshold value screening strategy, ensures the 'accuracy' of tail wave point cloud identification on the premise of not reducing the 'recall ratio', and avoids the 'over-segmentation' problem in tail wave filtering.
In conclusion, the tail wave filtering method applied to the unmanned ship has the advantages that the constructed normalized height difference and absolute height characteristics can accurately identify tail wave point clouds in a scene, the robustness is good, the problems of under segmentation and over segmentation are effectively solved, tail wave filtering tasks are simply and efficiently completed, and time-consuming target discrimination and false alarm removal processing in a subsequent environment sensing algorithm is avoided. The method is simple and easy to transplant, and can be directly used as a sub-link to be applied to the unmanned ship environment perception requirement.
Drawings
Fig. 1 is a flowchart of a wake filtering method applied to an unmanned ship.
FIG. 2 is a schematic diagram showing the calculation of the height difference of a target point by a laser beam impinging on an obstacle.
FIG. 3 is a schematic view showing the calculation of the target point height difference by striking the laser beam onto the obstacle when the unmanned boat bumps.
FIG. 4 is a schematic diagram showing the calculation of the reflection point height difference by striking the laser beam onto the tail wave.
Fig. 5 is a schematic view showing the calculation of the target point height difference by laser beam impinging on the obstacle flat surface.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
As shown in fig. 1, the invention provides a tailwave filtering method for unmanned ship application, which comprises the following steps:
Step 1: and acquiring point cloud data of the water surface environment around the unmanned ship, wherein the point cloud data is obtained through multi-line rotary laser radar scanning.
The laser radar used in this example is a Pandar model number Pandar laser radar from Shanghai He Seisaku. The radar employs a multi-line rotary scanning type, with a total of N groups of laser transmitters, where N has a value of 40. The laser transmitters are vertically arranged at a certain angle interval, periodically and simultaneously transmit laser beams, and measure the time difference from the laser beam transmission to the return, and calculate the distance of the target by multiplying the speed of light. The radar rotates at a constant speed at a certain speed and can scan the surrounding environment to acquire point cloud data. In the embodiment, the radar is horizontally arranged at the non-shielding position at the top of the unmanned ship so as to acquire the water surface environment point cloud data within the 360-degree view field range around the unmanned ship.
The laser beam is irradiated onto the target object and reflected, a point cloud data point is obtained, wherein the data point comprises 4 attributes (index, theta horizontal,θvertical, d) which respectively represent the number of the laser beam, the horizontal emission angle, the vertical emission angle and the target distance to which the point belongs. All data points acquired by rotating the radar by 360 degrees form one frame of point cloud data.
Step 2: and (3) removing clutter and noise points from the point cloud data obtained in the step (1).
Any method can be adopted to carry out filtering denoising treatment on the point cloud data. Clutter noise points in the water surface environment point cloud data are scattered points caused by electromagnetic noise, water surface ripple reflection and the like, and the embodiment preferably adopts a statistical filter method to remove the clutter noise points in the point cloud. Specifically, by counting the average distance of each data point in the European space to its nearest k points, the "outliers" that are too far away are eliminated. Compared with general point cloud filtering methods such as voxel filtering and grid filtering, the method can cause the problem of downsampling of the original point cloud, the method can not influence the original water surface scene point cloud, and the follow-up accurate filtering of the tail wave point cloud is ensured.
After clutter noise is removed, the problem of tail wave filtering is simplified into two classification problems of a target point and a tail wave point.
Step 3: and (3) calculating the characteristic of 'normalized height difference' of the point cloud data after the denoising processing in the step (2), and dividing a 'suspected tail wave point' set from the scene point cloud.
Calculating a "normalized height difference" feature:
As shown in fig. 2, when the laser radar rotates to scan the surrounding water surface environment and two adjacent laser beams in the vertical direction strike an obstacle, if the reflecting surface of the obstacle is perpendicular to the water surface, the height difference of the two reflecting points obtained by the radar is a line segment D' n in the figure, that is, a "theoretical height difference". Normally, the surface of the obstacle is inclined to a certain degree, so the actual height difference of the reflection points of the two laser beams is a line segment D n in the figure.
As shown in fig. 2, the obstacle on the water surface is usually very inclined, and when the laser strikes the obstacle, the value of the obtained actual height difference D n is usually closer to the value of the theoretical height difference D' n and is far greater than 0; in contrast to fig. 4, the tail wave exhibits a local water surface waving, which is generally "flat", and when the laser impinges on the tail wave, the actual height difference D n is obtained which is generally much smaller than the theoretical height difference D' n and is close to 0. This property can be used to segment the target point cloud and the tail wave point cloud in the scene point cloud.
The water surface environment is complex and changeable, the unmanned ship sails often in a bumpy state, the laser radar is not always vertical to the horizontal plane, as shown in fig. 3, when the unmanned ship is in the bumpy state, two adjacent laser beams in the vertical direction strike an obstacle, and the obtained actual height difference D n still meets the quantity relation which is not greatly different from the theoretical height difference D' n and is far greater than 0; likewise, when the laser strikes the tail wave, the actual height difference D n still satisfies the quantitative relationship that is much smaller than the theoretical height difference D' n and is close to 0. Therefore, when the unmanned ship jolts due to the change of sea conditions, the characteristic can be used for dividing the target point cloud and the tail wave point cloud.
The imaging characteristic of the laser radar is that the included angle between the laser beams in the vertical direction is fixed, the farther the same obstacle is from the radar, the larger the obtained height difference D n of the reflection points of two adjacent laser beams is, so that threshold screening is carried out only through a single height difference feature D n, and a proper threshold is difficult to select to cope with the change of the obstacle distance. Therefore, the present invention proposes a "normalized height difference" feature, denoted as D n, defined as the ratio of the actual height difference D n to the theoretical height difference D' n. The characteristic can eliminate the influence of the change of the target distance, and the specific calculation formula is as follows:
wherein, d n is used for the treatment of the heat dissipation, The target distance and vertical emission angle, d n+k,Respectively representing the target distance and the vertical emission angle obtained by the n+k laser; the harness numbers n, n+k denote two adjacent lasers in the vertical direction that strike the obstacle. Since not every laser beam will be reflected, the value of k is not always 1, as can be seen,/>The range of the value of (2) is 0-1.
Segmentation of the "suspected tail wave points":
Specifically, traversing the point cloud data set subjected to the denoising processing in the step 2, calculating the normalized height difference characteristic for each point cloud data point, and screening the characteristics of the point cloud data set to partition a 'suspected tail wave point' set. The normalized height difference feature value of the "target point" is typically large, close to 1; the normalized height difference characteristic value of the suspected tail wave point is usually small and is close to 0; therefore, the present embodiment adopts a threshold screening method to screen and classify the "target point" and the "suspected tail wave point". Any threshold screening method may be used herein. The present embodiment simply uses a fixed threshold for screening, preferably 0.5. From the above analysis, that is, the data points with the normalized height difference characteristic value smaller than 0.5 are regarded as "suspected tail wave points", and those greater than or equal to 0.5 are regarded as "target points".
The normalized height difference features can effectively classify target points and tail wave points, and the step can ensure finding out all the tail wave points, namely ensuring the recall ratio of the tail wave points and solving the problem of under segmentation of tail wave filtering.
Step 4: and (3) calculating the characteristic of the absolute height of the set of the suspected tail wave points obtained by the segmentation in the step (3), and segmenting the set of the tail wave points from the set of the suspected tail wave points.
Calculating an "absolute height" feature:
As shown in fig. 5, when the surface of the obstacle is relatively flat, the calculated actual height difference D n is still small, and when the obstacle is determined by using the normalized height difference feature, the obstacle point cloud is misdetermined to be the tail wave point cloud and filtered, so that the defect of the obstacle point cloud is caused, and the subsequent detection and recognition step is affected, which is the "over-segmentation" problem. It can be seen that the obstacle on the water surface is usually far above the horizontal plane, and the height of the obstacle point cloud in the Z-axis direction in the three-dimensional rectangular coordinate system of the laser radar is far above the tail wave point cloud, so that the flat part in the obstacle point cloud can be distinguished from the tail wave point cloud through the prior knowledge, the height of the point cloud in the Z-axis direction is defined as the absolute height, and the height is recorded as the absolute height The calculation formula is as follows:
wherein, d n is used for the treatment of the heat dissipation, The target distance and the vertical emission angle obtained by the nth laser are shown, respectively.
The "suspected tail wave point" set obtained by segmentation in the step 3 includes point clouds reflected by the flat surface in the obstacle, and in this embodiment, the "suspected tail wave point" set is subjected to a second threshold screening according to the absolute height characteristics, where any threshold screening method may be adopted. The absolute height characteristic values of the tail wave point cloud and the target point cloud are distributed in a certain value range, the value range is continuously changed due to the change of the conditions such as the target type, the sea condition and the like, and a simple threshold strategy is generally difficult to deal with. The method preferably adopts a maximum inter-class variance method, and a corresponding screening threshold value is calculated for each frame of water surface scene point cloud in a self-adaptive manner by maximizing the variance difference of absolute height characteristics between the target point and the tail wave point, so that the method can be adapted to various condition changes in a robust manner, and the tail wave point cloud and the target point cloud can be distinguished accurately. From the previous analysis, the absolute height characteristic value of the water surface obstacle point cloud is far greater than that of the tail wave point cloud, the part with the absolute height characteristic value greater than or equal to the screening threshold value is removed from the suspected tail wave point set, and the rest part is the tail wave point set.
The method eliminates the target point cloud which is misclassified as the tail wave point through the absolute height characteristics, ensures the accuracy of tail wave filtering on the premise of not reducing the recall ratio, and solves the problem of over-segmentation.
Step 5: and (3) removing tail wave points in the water surface scene point cloud according to the tail wave point set obtained in the step (3-4).
The tail wave filtering method applied to the unmanned ship can simply and efficiently remove the tail wave part in the scene point cloud on the water surface, can be used as a sub-link, and can be directly applied to the environmental perception requirement of the unmanned ship.
It will be readily appreciated by those skilled in the art that the foregoing description is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents, improvements or alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (7)
1. The tail wave filtering method for unmanned ship application is characterized by comprising the following steps:
S1, acquiring point cloud data of the water surface environment around an unmanned ship, wherein the point cloud data are obtained through multi-line rotary laser radar scanning;
S2, clutter and noise points of the point cloud data are removed;
S3, identifying tail wave points of the point cloud data after clutter noise filtering, wherein the method comprises the following steps:
S31, calculating the actual height difference of two adjacent laser reflection points in the vertical direction in the point cloud data according to the plane geometry;
s32, calculating the ratio of the actual height difference to the theoretical height difference of each point cloud data point to be used as a normalized height difference;
S33, identifying points with the normalized height difference lower than a first threshold as tail wave points, and adding the tail wave points into a tail wave point set;
S4, removing the identified tail wave point set from point cloud data of the water surface environment.
2. The method of claim 1, further comprising, after step S33:
S34, calculating the absolute height of each point in the Z-axis direction according to the plane geometry;
s35, eliminating points with absolute heights larger than or equal to a second threshold value in the tail wave point set.
3. The method of claim 2, wherein the absolute heightThe calculation formula is as follows:
wherein, d n is used for the treatment of the heat dissipation, The target distance and the vertical emission angle obtained by the nth laser are shown, respectively.
4. The method of claim 2, wherein the second threshold is determined by: the variance of the absolute height between the two classes of target point and tail wave point is maximized to determine a second threshold.
5. The method of any one of claims 1 to 4, wherein the height difference is normalizedThe calculation formula is as follows:
wherein, d n is used for the treatment of the heat dissipation, Respectively representing the target distance and the vertical emission angle obtained by the nth laser, d n+k,/>Respectively representing the target distance and the vertical emission angle obtained by the n+k laser; the harness numbers n, n+k denote two adjacent lasers in the vertical direction that strike the obstacle.
6. The method according to any one of claims 1 to 4, wherein step S2 employs a statistical filter.
7. A computer readable storage medium storing one or more first programs for execution by one or more processors to implement the steps of the tailwave filtering method for unmanned aerial vehicle-oriented applications of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111220246.6A CN114002708B (en) | 2021-10-20 | 2021-10-20 | Tail wave filtering method for unmanned ship application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111220246.6A CN114002708B (en) | 2021-10-20 | 2021-10-20 | Tail wave filtering method for unmanned ship application |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114002708A CN114002708A (en) | 2022-02-01 |
| CN114002708B true CN114002708B (en) | 2024-06-14 |
Family
ID=79923280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111220246.6A Active CN114002708B (en) | 2021-10-20 | 2021-10-20 | Tail wave filtering method for unmanned ship application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114002708B (en) |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110275153B (en) * | 2019-07-05 | 2021-04-27 | 上海大学 | Water surface target detection and tracking method based on laser radar |
| WO2021072709A1 (en) * | 2019-10-17 | 2021-04-22 | 深圳市大疆创新科技有限公司 | Method for detecting and tracking target, system, device, and storage medium |
| CN112464994B (en) * | 2020-11-05 | 2024-03-26 | 航天时代(青岛)海洋装备科技发展有限公司 | PointNet network-based boat tail wave recognition and removal method |
-
2021
- 2021-10-20 CN CN202111220246.6A patent/CN114002708B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| Metric Reliability Analysis of Autonomous Marine LiDAR Systems under Extreme Wind Loads;Bing Liang 等;J. Mar. Sci. Eng;20231225;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114002708A (en) | 2022-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111239766B (en) | Water surface multi-target rapid identification and tracking method based on laser radar | |
| CN109444911B (en) | Unmanned ship water surface target detection, identification and positioning method based on monocular camera and laser radar information fusion | |
| CN110275153B (en) | Water surface target detection and tracking method based on laser radar | |
| CN112464994B (en) | PointNet network-based boat tail wave recognition and removal method | |
| CN108562913B (en) | Unmanned ship false target detection method based on three-dimensional laser radar | |
| CN111899568B (en) | Bridge anti-collision early warning system, method and device and storage medium | |
| CN112513679B (en) | Target identification method and device | |
| CN109283538A (en) | A kind of naval target size detection method of view-based access control model and laser sensor data fusion | |
| Haghbayan et al. | An efficient multi-sensor fusion approach for object detection in maritime environments | |
| CN111126335B (en) | SAR ship identification method and system combining significance and neural network | |
| CN112881993B (en) | Method for automatically identifying false flight path caused by radar distribution clutter | |
| CN112731307B (en) | RATM-CFAR detector based on distance-angle joint estimation and detection method | |
| CN111913177A (en) | Method and device for detecting target object and storage medium | |
| CN110596728A (en) | Water surface small target detection method based on laser radar | |
| CN113570005A (en) | Long-distance ship type identification method based on airborne photon radar | |
| CN111929653A (en) | Target detection and tracking method and system based on unmanned ship marine radar | |
| CN113888589A (en) | Water surface obstacle detection and multi-target tracking method based on laser radar | |
| CN114002708B (en) | Tail wave filtering method for unmanned ship application | |
| CN117496165A (en) | Rain and snow noise filtering method and device, electronic equipment and storage medium | |
| CN115267827B (en) | Laser radar harbor area obstacle sensing method based on high density screening | |
| CN114879180A (en) | Seamless situation perception method for real-time fusion of unmanned ship-borne multi-element multi-scale radar | |
| CN110827257B (en) | Visual navigation positioning method for embedded airborne infrared image | |
| CN113625266A (en) | Method, device, storage medium and equipment for detecting low-speed target by using radar | |
| WO2024060209A1 (en) | Method for processing point cloud, and radar | |
| CN116879863B (en) | Multi-target measuring method and system for continuous wave 4D millimeter wave radar |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |