CN110865394A - Target classification system based on laser radar data and data processing method thereof - Google Patents
Target classification system based on laser radar data and data processing method thereof Download PDFInfo
- Publication number
- CN110865394A CN110865394A CN201910904542.4A CN201910904542A CN110865394A CN 110865394 A CN110865394 A CN 110865394A CN 201910904542 A CN201910904542 A CN 201910904542A CN 110865394 A CN110865394 A CN 110865394A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- computer
- laser radar
- data
- height
- 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.)
- Pending
Links
Images
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
Abstract
The invention belongs to the field of monitoring and intelligent control in an amphibious unmanned platform technology, and relates to data acquisition and target labeling of a platform monitoring system, in particular to a target classification system based on laser radar data, which comprises an amphibious platform, wherein the target classification system comprises a 32-line laser radar, a vehicle-mounted reinforced computer, a display and a vehicle-mounted power supply, the 32-line laser radar is arranged above the roof of the amphibious platform, and the vehicle-mounted reinforced computer, the display and the vehicle-mounted power supply are arranged in a vehicle of the amphibious platform; the signal output end of the 32-line laser radar is connected with the vehicle-mounted ruggedized computer, and the data output end of the vehicle-mounted ruggedized computer is connected with the display; the 32-line laser radar is used for carrying out ground detection on the external environment of the amphibious platform, and the vehicle-mounted reinforcement computer processes the signals and expresses the signals through the displayer.
Description
Technical Field
The invention belongs to the field of monitoring and intelligent control in an amphibious unmanned platform technology, relates to data acquisition and target marking of a platform monitoring system, and particularly relates to a target classification system based on laser radar data.
Background
An amphibious unmanned platform is a special motion platform with both land running and water navigation, is an integration of unmanned vehicles and unmanned boats in function, and has running environment adaptability beyond that of common unmanned vehicles and unmanned boats. The amphibious unmanned platform has the characteristics of 'rapidness and concealment on water, maneuverability and flexibility on land, unique traffic performance at an amphibious junction' and the like, and is widely applied to military and civil fields such as safety protection, information acquisition, replenishment operation, independent combat, amphibious integrated combat and the like. The amphibious unmanned platform is different from the traditional unmanned platform, and the operation environment comprises island reefs, water edges, boundary rivers, inland rivers, coasts, shoals and other areas besides land.
Therefore, the perception of the amphibious environment is one of the key tasks of the perception system of the amphibious unmanned platform. Among various sensors for sensing systems, the laser radar has the characteristics of high ranging precision, good real-time performance, wide application range and the like, and therefore, the laser radar is used as a main obstacle detection sensor in an unmanned amphibious platform. A target classification system is developed based on a laser radar device so as to determine a target classification system of obstacles around an amphibious platform.
Disclosure of Invention
The invention provides a target classification system based on a 32-line radar device and used for judging and identifying obstacles around an amphibious platform.
The utility model provides a target classification system based on laser radar data, includes a amphibian platform, its characterized in that: the amphibious platform comprises a 32-line laser radar, a vehicle-mounted reinforced computer, a display and a vehicle-mounted power supply, wherein the 32-line laser radar is arranged above the roof of the amphibious platform, and the vehicle-mounted reinforced computer, the display and the vehicle-mounted power supply are arranged in a vehicle of the amphibious platform; the signal output end of the 32-line laser radar is connected with the vehicle-mounted ruggedized computer, and the data output end of the vehicle-mounted ruggedized computer is connected with the display; the 32-line laser radar is used for carrying out ground detection on the external environment of the amphibious platform, and the vehicle-mounted reinforcement computer processes the signals and expresses the signals through the displayer.
Further, the vehicle-mounted ruggedized computer comprises an industrial personal computer 1, an industrial personal computer 2, an industrial personal computer 3, a laser inertial navigation system, a satellite navigation system and a switch, wherein a signal output end of the laser inertial navigation system is connected with the industrial personal computer 2, and the industrial personal computer 2 is used for preprocessing output data of the laser inertial navigation system; the signal output end of the satellite navigation system is connected with the industrial personal computer 3, and the industrial personal computer 3 is used for preprocessing the satellite navigation system; industrial computer 2 and industrial computer 3 all communicate with industrial computer 1 two-way, and industrial computer 1, industrial computer 2 and industrial computer 3 all can be connected with the switch and realize the data exchange with external network.
Further, the vehicle-mounted ruggedized computer performs ground detection on the point cloud data based on a RANSAC algorithm.
Further, the 32-line laser radar is preferably arranged at a position 30 cm above the vehicle roof, and no shelter exists at the same horizontal height around the vehicle roof.
Furthermore, the display adopts a multithreading receiving mode.
Further, the data processing method of the target classification system based on the laser radar data is characterized in that:
the method comprises the following steps:
step 1: using 32 lines of laser radar to perform grid projection;
step 2: loading a multi-scale map and establishing a planar matrix;
and step 3: on the basis of the multi-scale map loaded in the step 2, separating plane blocks by matching with the grid projection in the step 1;
and 4, step 4: judging each plane block, and judging the ground block into a road block or an obstacle layer;
and 5: and determining the corresponding obstacle position for the determined obstacle layer in the step 4.
And in the step 3, the point cloud data generated by the 32-line laser radar located in the same grid in the grid projection in the step 1 is sorted from small to large according to the height, so as to obtain a data point list, and whether two points belong to the same plane block is judged according to the size of the vertical height interval of two adjacent data points.
Moreover, in the step 3, the corresponding height threshold value H is selected according to the loaded scene of the multi-scale mapthTraversing the whole raster image, and when the interval between the upper point and the lower point is larger than the height threshold valueWhen the two points belong to different plane blocks, all the plane blocks are divided.
The upper limit of the height determination value selected in step 3 is HbLower limit of Ha(ii) a Selecting the plane block with the minimum vertical height as a ground candidate plane block, obtaining the maximum and minimum height to obtain the height difference delta H of the plane block, and obtaining the height difference delta H when the delta H is the minimum>Hb(ii) a Then the plane block is judged as an obstacle when the height is delta H<HaJudging that the plane block is a road surface; when H is presenta<ΔH<HbWhen the intensity characteristic is introduced, when the intensity mean value of the plane block is at the intensity mean value threshold value IameanAnd IbmeanIn between, the intensity variance is less than the variance threshold ItvarJudging the road surface; the height average is taken as the height H of the pavement layer in the gridg。
And measuring the height of the laser radar at the top of the amphibious platform as HvAnd the height is judged to be Hg-Hg+HvIs the barrier layer and determines the vertical height position of the barrier.
The invention has the advantages and positive effects that:
in the invention, the 32-line laser radar is used for acquiring point cloud information of the surrounding environment of the amphibious platform in real time and sending the point cloud information to an appointed IP address in time through a network, the vehicle-mounted reinforced computer receives the point cloud data from the laser radar in real time and divides and processes the point cloud data, a display interface arranged in the display adopts multi-thread receiving, and other data are processed in time when a CPU is idle, so that the utilization rate of the CPU is improved to realize real-time performance, and the 32-line laser radar is arranged at a position of 30 centimeters above the amphibious platform, thereby being beneficial to reducing blind areas of radar scanning.
The vehicle-mounted ruggedized computer comprises an industrial personal computer 1, an industrial personal computer 2, an industrial personal computer 3, a laser inertial navigation system, a satellite navigation system and a switch, wherein the industrial personal computer 2 and the industrial personal computer 3 are respectively used for processing data output by the laser inertial navigation system and the satellite navigation system, the preprocessed data are divided and processed by the industrial personal computer 1, then the data are displayed by a display, and the communication with the outside is realized through the switch.
The data processing method of the target classification system based on the laser radar data comprises the following steps: step 1: using 32 lines of laser radar to perform grid projection; step 2: loading a multi-scale map and establishing a planar matrix; and step 3: on the basis of the multi-scale map loaded in the step 2, separating plane blocks by matching with the grid projection in the step 1; and 4, step 4: judging each plane block, and judging the ground block into a road block or an obstacle layer; and 5: and determining the corresponding obstacle position for the determined obstacle layer in the step 4.
In the processing process, a multi-scale map of a corresponding geographic position is manually loaded, 32-line laser radar is applied to carry out grid projection on the basis of the multi-scale map, and the area is divided into a plurality of plane blocks. The point cloud data generated by the 32-line laser radar are sorted from small to large according to the height to obtain a data point list, whether two points belong to the same plane block or not is judged according to the size of the vertical height interval of the two adjacent data points, and then each plane block is divided. And then, judging the vertical height of each plane block, dividing the vertical height into a road surface block and a barrier layer, and finally judging the height position of the barrier layer.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a block diagram of the present invention;
FIG. 3 is a block diagram of a portion of the on-board ruggedized computer;
FIG. 4 is a flow chart of the algorithm of the present invention;
FIG. 5 is a diagram of the effect of laser radar point cloud data off-line processing.
Detailed Description
The present invention is further illustrated by the following examples, which are intended to be illustrative, not limiting and are not intended to limit the scope of the invention.
The invention discloses a target classification system based on laser radar data, which comprises an amphibious platform, and is characterized by comprising a 32-line laser radar, a vehicle-mounted reinforcement computer, a display and a vehicle-mounted power supply, wherein the 32-line laser radar is arranged above the roof of the amphibious platform, and the vehicle-mounted reinforcement computer, the display and the vehicle-mounted power supply are arranged in a vehicle of the amphibious platform; the signal output end of the 32-line laser radar is connected with the vehicle-mounted ruggedized computer, and the data output end of the vehicle-mounted ruggedized computer is connected with the display; the 32-line laser radar is used for carrying out ground detection on the external environment of the amphibious platform, and the vehicle-mounted reinforcement computer processes the signals and expresses the signals through the displayer.
In the embodiment, the vehicle-mounted ruggedized computer comprises an industrial personal computer 1, an industrial personal computer 2, an industrial personal computer 3, a laser inertial navigation system, a satellite navigation system and a switch, wherein a signal output end of the laser inertial navigation system is connected with the industrial personal computer 2, and the industrial personal computer 2 is used for preprocessing output data of the laser inertial navigation system; the signal output end of the satellite navigation system is connected with the industrial personal computer 3, and the industrial personal computer 3 is used for preprocessing the satellite navigation system; industrial computer 2 and industrial computer 3 all communicate with industrial computer 1 two-way, and industrial computer 1, industrial computer 2 and industrial computer 3 all can be connected with the switch and realize the data exchange with external network.
In this embodiment, the vehicle-mounted ruggedized computer performs ground detection on the point cloud data based on the RANSAC algorithm.
In this embodiment, the 32-line laser radar 2 is preferably installed at a position 30 cm above the roof 3, no shelter exists at the same horizontal height around the roof, and the wide-angle monitoring camera 1 is further installed in the frame above the roof for collecting actual pictures.
In this embodiment, the display adopts a multithread receiving mode.
The data processing method of the target classification system based on the laser radar data, which is disclosed by the invention, comprises the following steps of:
step 1: using 32 lines of laser radar to perform grid projection;
step 2: loading a multi-scale map and establishing a planar matrix;
and step 3: on the basis of the multi-scale map loaded in the step 2, separating plane blocks by matching with the grid projection in the step 1;
and 4, step 4: judging each plane block, and judging the ground block into a road block or an obstacle layer;
and 5: and determining the corresponding obstacle position for the determined obstacle layer in the step 4.
In this embodiment, in step 3, the point cloud data generated by the 32-line laser radar located in the same grid in the grid projection in step 1 is sorted from small to large according to the height, so as to obtain a data point list, and whether two points belong to the same plane block is determined according to the size of the vertical height interval between two adjacent data points.
In this embodiment, in step 3, the corresponding height threshold H is selected according to the loaded scene of the multi-scale mapthAnd traversing the whole grid graph, and when the interval between the upper point and the lower point is larger than the height threshold value, dividing the two points into different plane blocks so as to divide all the plane blocks.
In this embodiment, the upper limit of the height determination value selected in step 3 is HbLower limit of Ha(ii) a Selecting the plane block with the minimum vertical height as a ground candidate plane block, obtaining the maximum and minimum height to obtain the height difference delta H of the plane block, and obtaining the height difference delta H when the delta H is the minimum>Hb(ii) a Then the plane block is judged as an obstacle when the height is delta H<HaJudging that the plane block is a road surface; when H is presenta<ΔH<HbWhen the intensity characteristic is introduced, when the intensity mean value of the plane block is at the intensity mean value threshold value IameanAnd IbmeanIn between, the intensity variance is less than the variance threshold ItvarJudging the road surface; the height average is taken as the height H of the pavement layer in the gridg。
In this example, the height of the laser radar at the top of the amphibious platform was measured as HvAnd the height is judged to be Hg-Hg+HvIs the barrier layer and determines the vertical height position of the barrier.
In this embodiment, the euclidean-based clustering is to calculate the density ρ (i) and the distance δ (i) of each data point in the data set, where ρ (i) is the distance from the data point m (i) to the rest of the points and is less than dc(number of truncation distances), δ (i) being the minimum distance value of data points greater than their density valueAnd finally, selecting the data points with larger density and distance values as the clustering center points.
For a data set M of size N2 ^ N, the steps of using Euclidean clustering are as follows:
1) for all data points M (i) e M, the distance d from each point to the rest is calculatedij(i, j ═ 1, 2.., N) and stored;
2) for all data points M (i) e M, the density is calculated as follows using the formula
ρ(i)＝∑β(dij-dc)
Wherein the expression is a symbolic function, β (m) is 1 when m is less than 0, and β (m) is 0 when m is more than or equal to 0.
3) Finding the point where ρ (i) has the maximum value, its distance dijCalculated using the following formula:
δ(i)＝maxj(dij)
4) for each of the other data points, the distance is calculated as follows:
δ(i)＝minj，p(i)＞p(j)(dij)
5) and determining that the values of rho (i) and d (i) are larger than the data points as cluster center points.
Claims (10)
1. The utility model provides a target classification system based on laser radar data, includes a amphibian platform, its characterized in that: the amphibious platform comprises a 32-line laser radar, a vehicle-mounted reinforced computer, a display and a vehicle-mounted power supply, wherein the 32-line laser radar is arranged above the roof of the amphibious platform, and the vehicle-mounted reinforced computer, the display and the vehicle-mounted power supply are arranged in a vehicle of the amphibious platform; the signal output end of the 32-line laser radar is connected with the vehicle-mounted ruggedized computer, and the data output end of the vehicle-mounted ruggedized computer is connected with the display; the 32-line laser radar is used for carrying out ground detection on the external environment of the amphibious platform, and the vehicle-mounted reinforcement computer processes the signals and expresses the signals through the displayer.
2. The lidar data based object classification system of claim 1, wherein: the vehicle-mounted ruggedized computer comprises an industrial personal computer 1, an industrial personal computer 2, an industrial personal computer 3, a laser inertial navigation system, a satellite navigation system and a switch, wherein a signal output end of the laser inertial navigation system is connected with the industrial personal computer 2, and the industrial personal computer 2 is used for preprocessing output data of the laser inertial navigation system; the signal output end of the satellite navigation system is connected with the industrial personal computer 3, and the industrial personal computer 3 is used for preprocessing the satellite navigation system; industrial computer 2 and industrial computer 3 all communicate with industrial computer 1 two-way, and industrial computer 1, industrial computer 2 and industrial computer 3 all can be connected with the switch and realize the data exchange with external network.
3. A lidar data-based target classification system according to claim 1 or 2, wherein: and the vehicle-mounted reinforcement computer performs ground detection on the point cloud data based on the RANSAC algorithm.
4. The lidar data based object classification system of claim 1, wherein: the 32-line laser radar is preferably arranged at a position 30 cm above the roof of the vehicle, and no shelter exists at the same horizontal height around the vehicle.
5. The lidar data based object classification system of claim 1, wherein: the display adopts a multithreading receiving mode.
6. The method for data processing of a lidar data based object classification system according to any of claims 1 to 5, wherein: the method comprises the following steps:
step 1: using 32 lines of laser radar to perform grid projection;
step 2: loading a multi-scale map and establishing a planar matrix;
and step 3: on the basis of the multi-scale map loaded in the step 2, separating plane blocks by matching with the grid projection in the step 1;
and 4, step 4: judging each plane block, and judging the ground block into a road block or an obstacle layer;
and 5: and determining the corresponding obstacle position for the determined obstacle layer in the step 4.
7. The data processing method of the lidar data-based target classification system according to claim 6, wherein: in the step 3, the point cloud data generated by the 32-line laser radar located in the same grid in the grid projection in the step 1 is sorted from small to large according to the height, so as to obtain a data point list, and whether two points belong to the same plane block is judged according to the size of the vertical height interval between two adjacent data points.
8. The data processing method of the lidar data-based target classification system according to claim 7, wherein: selecting a corresponding height threshold H according to the loaded scene of the multi-scale map in the step 3thAnd traversing the whole grid graph, and when the interval between the upper point and the lower point is larger than the height threshold value, dividing the two points into different plane blocks so as to divide all the plane blocks.
9. The data processing method of the lidar data-based target classification system according to claim 8, wherein: the upper limit of the height determination value selected in step 3 is HbLower limit of Ha(ii) a Selecting the plane block with the minimum vertical height as a ground candidate plane block, obtaining the maximum and minimum height to obtain the height difference delta H of the plane block, and obtaining the height difference delta H when the delta H is the minimum>Hb(ii) a Then the plane block is judged as an obstacle when the height is delta H<HaJudging that the plane block is a road surface; when H is presenta<ΔH<HbWhen the intensity characteristic is introduced, when the intensity mean value of the plane block is at the intensity mean value threshold value IameanAnd IbmeanIn between, the intensity variance is less than the variance threshold ItvarJudging the road surface; the height average is taken as the height H of the pavement layer in the gridg。
10. The lidar data-based target classification system of claim 9The system data processing method is characterized in that: h is measured as height of laser radar on top of amphibious platformvAnd the height is judged to be Hg-Hg+HvIs the barrier layer and determines the vertical height position of the barrier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910904542.4A CN110865394A (en) | 2019-09-24 | 2019-09-24 | Target classification system based on laser radar data and data processing method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910904542.4A CN110865394A (en) | 2019-09-24 | 2019-09-24 | Target classification system based on laser radar data and data processing method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110865394A true CN110865394A (en) | 2020-03-06 |
Family
ID=69652083
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910904542.4A Pending CN110865394A (en) | 2019-09-24 | 2019-09-24 | Target classification system based on laser radar data and data processing method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110865394A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111427059A (en) * | 2020-03-20 | 2020-07-17 | 燕山大学 | Method and system for detecting terrain in front of vehicle |
| CN111580131A (en) * | 2020-04-08 | 2020-08-25 | 西安邮电大学 | Method for identifying vehicles on expressway by three-dimensional laser radar intelligent vehicle |
| CN112882059A (en) * | 2021-01-08 | 2021-06-01 | 中国船舶重工集团公司第七0七研究所 | Unmanned ship inland river obstacle sensing method based on laser radar |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102227612A (en) * | 2008-10-24 | 2011-10-26 | 格瑞股份公司 | Control and systems for autonomously driven vehicles |
| CN103778681A (en) * | 2014-01-24 | 2014-05-07 | 青岛秀山移动测量有限公司 | Vehicle-mounted high-speed road inspection system and data acquisition and processing method |
| CN105607637A (en) * | 2016-01-25 | 2016-05-25 | 重庆德新机器人检测中心有限公司 | Unmanned vehicle autopilot system |
| CN105741635A (en) * | 2016-03-01 | 2016-07-06 | 武汉理工大学 | Multifunctional road experiment vehicle platform |
| CN106991430A (en) * | 2017-02-28 | 2017-07-28 | 浙江工业大学 | A kind of cluster number based on point of proximity method automatically determines Spectral Clustering |
| CN107203783A (en) * | 2017-05-24 | 2017-09-26 | 西北工业大学 | Remote sensing images Pixel-level sorting technique based on adaptive convolution kernel convolutional neural networks |
| CN108226951A (en) * | 2017-12-23 | 2018-06-29 | 天津国科嘉业医疗科技发展有限公司 | A kind of quick moving obstacle method for real time tracking based on laser sensor |
| CN108845579A (en) * | 2018-08-14 | 2018-11-20 | 苏州畅风加行智能科技有限公司 | A kind of automated driving system and its method of port vehicle |
| CN108873013A (en) * | 2018-06-27 | 2018-11-23 | 江苏大学 | A kind of road using multi-line laser radar can traffic areas acquisition methods |
-
2019
- 2019-09-24 CN CN201910904542.4A patent/CN110865394A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102227612A (en) * | 2008-10-24 | 2011-10-26 | 格瑞股份公司 | Control and systems for autonomously driven vehicles |
| CN103778681A (en) * | 2014-01-24 | 2014-05-07 | 青岛秀山移动测量有限公司 | Vehicle-mounted high-speed road inspection system and data acquisition and processing method |
| CN105607637A (en) * | 2016-01-25 | 2016-05-25 | 重庆德新机器人检测中心有限公司 | Unmanned vehicle autopilot system |
| CN105741635A (en) * | 2016-03-01 | 2016-07-06 | 武汉理工大学 | Multifunctional road experiment vehicle platform |
| CN106991430A (en) * | 2017-02-28 | 2017-07-28 | 浙江工业大学 | A kind of cluster number based on point of proximity method automatically determines Spectral Clustering |
| CN107203783A (en) * | 2017-05-24 | 2017-09-26 | 西北工业大学 | Remote sensing images Pixel-level sorting technique based on adaptive convolution kernel convolutional neural networks |
| CN108226951A (en) * | 2017-12-23 | 2018-06-29 | 天津国科嘉业医疗科技发展有限公司 | A kind of quick moving obstacle method for real time tracking based on laser sensor |
| CN108873013A (en) * | 2018-06-27 | 2018-11-23 | 江苏大学 | A kind of road using multi-line laser radar can traffic areas acquisition methods |
| CN108845579A (en) * | 2018-08-14 | 2018-11-20 | 苏州畅风加行智能科技有限公司 | A kind of automated driving system and its method of port vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 郑正扬: "基于三维激光雷达的智能汽车障碍物检测与跟踪", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111427059A (en) * | 2020-03-20 | 2020-07-17 | 燕山大学 | Method and system for detecting terrain in front of vehicle |
| CN111427059B (en) * | 2020-03-20 | 2022-02-11 | 燕山大学 | Method and system for detecting terrain in front of vehicle |
| CN111580131A (en) * | 2020-04-08 | 2020-08-25 | 西安邮电大学 | Method for identifying vehicles on expressway by three-dimensional laser radar intelligent vehicle |
| CN112882059A (en) * | 2021-01-08 | 2021-06-01 | 中国船舶重工集团公司第七0七研究所 | Unmanned ship inland river obstacle sensing method based on laser radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108647646B (en) | Low-beam radar-based short obstacle optimized detection method and device | |
| KR20220155559A (en) | Autonomous navigation method using image segmentation | |
| CN108226951B (en) | Laser sensor based real-time tracking method for fast moving obstacle | |
| US9255805B1 (en) | Pose estimation using long range features | |
| CN111326023A (en) | Unmanned aerial vehicle route early warning method, device, equipment and storage medium | |
| CN108509972A (en) | A kind of barrier feature extracting method based on millimeter wave and laser radar | |
| US11475678B2 (en) | Lane marker detection and lane instance recognition | |
| CN106257242A (en) | For regulating unit and the method for road boundary | |
| US20220024549A1 (en) | System and method for measuring the distance to an object in water | |
| CN102222236A (en) | Image processing system and position measurement system | |
| CN110865394A (en) | Target classification system based on laser radar data and data processing method thereof | |
| CN114442101B (en) | Vehicle navigation method, device, equipment and medium based on imaging millimeter wave radar | |
| CN111461048B (en) | Vision-based parking lot drivable area detection and local map construction method | |
| KR102466804B1 (en) | Autonomous navigation method using image segmentation | |
| WO2022041706A1 (en) | Positioning method, positioning system, and vehicle | |
| CN112674646B (en) | Self-adaptive welting operation method based on multi-algorithm fusion and robot | |
| CN102201054A (en) | Method for detecting street lines based on robust statistics | |
| CN111913177A (en) | Method and device for detecting target object and storage medium | |
| US20230264715A1 (en) | Puddle occupancy grid for autonomous vehicles | |
| CN114048536A (en) | Road structure prediction and target detection method based on multitask neural network | |
| Zhao et al. | Environmental perception and sensor data fusion for unmanned ground vehicle | |
| US11397439B1 (en) | System for tuning parameters of a thermal sensor to improve object detection | |
| CN111089580B (en) | Unmanned war chariot simultaneous positioning and map construction method based on covariance intersection | |
| EP4155759A1 (en) | Systems and method for lidar grid velocity estimation | |
| CN116524454A (en) | Object tracking device, object tracking method, and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200306 |