CN111077539B - Bird detection system based on laser radar - Google Patents
Bird detection system based on laser radar Download PDFInfo
- Publication number
- CN111077539B CN111077539B CN201911401873.2A CN201911401873A CN111077539B CN 111077539 B CN111077539 B CN 111077539B CN 201911401873 A CN201911401873 A CN 201911401873A CN 111077539 B CN111077539 B CN 111077539B
- Authority
- CN
- China
- Prior art keywords
- bird
- point cloud
- dynamic
- processing module
- bird detection
- 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
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
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention relates to the technical field of bird detection, in particular to a laser radar-based bird detection system, which comprises a collection module, a processing module and a bird detection module, wherein the collection module collects an environment image through a laser radar imaging method; the processing module is used for acquiring an environment image forming point cloud set and sending the environment image forming point cloud set to the bird detection module; the bird detection module filters the environment image and divides the environment image into dynamic points and static points, the bird detection module clusters the dynamic points with a clustering radius to obtain a dynamic point cloud subset, the bird detection module calculates the circumscribed sphere radius of the set of the dynamic point cloud subset, takes the point cloud with the circumscribed sphere radius smaller than a third threshold value as a pre-stage suspected bird point, searches the suspected bird point at the current moment, has the suspected bird point in a second threshold value range when the current moment is the previous moment, and judges that birds are explored when no static point exists in a first threshold value range of the suspected bird point at the current moment. The invention greatly improves the real-time performance, and the bird detection algorithm can be basically synchronous with the laser acquisition without hysteresis.
Description
Technical Field
The invention relates to the technical field of bird detection, in particular to a laser radar-based bird detection system.
Background
With the acceleration of the urban process and the increase of the environmental awareness of human beings, birds often fly and forge in human living environments, and people and birds are harmonious and co-located, but birds have certain dangers to places such as airports and substations, the birds easily cause dangers to places such as airports or substations due to the randomness of flight trajectories, for example, the birds strike an airplane to cause damage to parts of a fuselage, or the birds cause faults of a power transmission line due to nesting or inhabiting, and the like, so the detection of the birds is very important for accurately driving birds in part of places.
The existing bird detection system is carried out through technologies such as radar, infrared and the like, doppler radar is commonly used for radar bird detection, and the Doppler radar is huge in size and poor in mobility.
Disclosure of Invention
The invention aims to provide a laser radar-based bird detection system so as to solve the problem of poor universality of the existing bird detection technology.
The bird detection system based on the laser radar in the scheme comprises an acquisition module, a processing module and a bird detection module:
the acquisition module continuously acquires environment images of the target by a laser radar imaging method;
the processing module is used for acquiring an environment image forming point cloud set and sending the environment image forming point cloud set to the bird detection module;
the bird detection module filters the environment image and divides the environment image into dynamic points and static points, the bird detection module clusters the dynamic points with a clustering radius to obtain a dynamic point cloud subset, the bird detection module calculates the circumscribed sphere radius of the set of the dynamic point cloud subset and takes point clouds with the circumscribed sphere radius smaller than a third threshold value as early-stage suspected bird points, the bird detection module searches that the early-stage suspected bird points at the current moment have suspected bird points in a second threshold value range when the current moment is the previous moment, and the bird detection module searches that birds are detected when no static points exist in a first threshold value range of the early-stage suspected bird points at the current moment.
The beneficial effect of this scheme is:
when birds are detected, an acquisition module acquires an environment image of a target, such as an image around a transformer substation, a processing module acquires the environment image to form a point cloud set and then sends the point cloud set to a bird detection module, the bird detection module classifies the point cloud set of the environment image into dynamic points and static points in a filtering mode, the classified dynamic points are clustered to obtain a dynamic point cloud subset, suspected bird points are searched in the dynamic point cloud subset, and the bird is judged by combining a scheme of screening the distance between the clustered suspected bird points and the static point cloud, so that the real-time performance is greatly improved, the bird detection algorithm can be basically synchronous with the laser acquisition without hysteresis, and compared with the existing detection mode, the calculation amount of judging one by one in the environment image is reduced by finding out the dynamic clustering target and judging.
Further, the bird detection module comprises a filtering unit, the filtering unit is used for filtering in the horizontal direction of each pixel point of the environment image through a filtering window, the filtering unit sends a static signal when the distance between the current time point cloud and the previous time point cloud in the filtering window is smaller than a first threshold value, and the filtering unit sends a dynamic signal when the distance between the current time point cloud and the previous time point cloud in the filtering window is larger than the first threshold value.
The beneficial effects are that: and filtering the pixel points in the environment image, comparing and classifying the distances between the point cloud at the current moment and the point cloud at the previous moment of the filtering window, and searching the pixel points in the environment image one by one to avoid missing the characteristics of the pixel points.
Further, the bird detection module further comprises a tag unit, the processing module acquires static signals and dynamic signals and sends the static signals and the dynamic signals to the tag unit, the tag unit adds static tags to the point cloud at the current moment according to the static signals, the tag unit adds dynamic tags to the point cloud at the current moment according to the dynamic signals, the processing module forms static point clouds according to the static tags, and the processing module forms dynamic point clouds according to the dynamic tags.
The beneficial effects are that: and after classifying the pixel points in the environment image, adding labels, and forming different point clouds, so that the dynamic point clouds can be conveniently processed in the subsequent set, and the processed data volume is reduced.
Further, the bird detection module further comprises a clustering unit, and the clustering unit clusters the dynamic point cloud set with a clustering radius to obtain a dynamic point cloud subset.
The beneficial effects are that: because the laser beam is fan-shaped and shoots out when the acquisition module detects the bird, the closer the acquisition module is to, the smaller the point cloud distance between the adjacent laser beams vertically projected onto the target is, the clustering unit clusters through the changed clustering radius, and compared with the existing clustering mode with fixed clustering radius, the accuracy of detecting the bird is improved.
Further, the bird detection module further comprises a first screening unit, the processing module obtains the circumscribed sphere radius of the set of the dynamic point cloud subsets, the point cloud with the circumscribed sphere radius smaller than a third threshold value is used as a pre-suspected bird point, the first screening unit searches that the pre-suspected bird point at the current moment has a suspected bird point in a second threshold value range in the previous moment, the first screening unit searches that no static point exists in the first threshold value range of the pre-suspected bird point at the current moment, and the processing module sends a confirmation signal to the processing module, and the processing module judges the target as birds according to the confirmation signal.
The beneficial effects are that: and traversing the dynamic point cloud of the suspected bird to search the static point, so that the interference of the static point in the environment image is prevented, and the accuracy of bird detection is improved.
Further, the bird detection module further comprises a second screening unit, the processing module obtains the reflectivity of the light reflected by the acquisition module from the environment image and sends the reflectivity to the second screening unit, the second screening unit sends a noise signal to the processing module when the reflectivity is smaller than a preset value, and the processing module records the point cloud as a noise.
The beneficial effects are that: because the reflectors such as glass and the like can form isolated noise points in space, the noise points can be misjudged as suspected bird point clouds, the noise points are screened out, and the accuracy of bird detection is improved.
Further, the clustering radius is calculated according to the distance between the target and the acquisition module, and the clustering radius is in direct proportion to the distance between the target and the acquisition module.
The beneficial effects are that: the clustering radius is set in proportion to the distance from the target to the acquisition module, so that the accuracy of bird detection is improved.
Further, the third threshold is adaptively determined by the processing module based on bird size.
The beneficial effects are that: the suspected bird spots are divided according to the bird sizes, interference factors such as people, moving vehicles and the like are eliminated, and the accuracy of analyzing the bird positions according to the suspected bird spots is improved.
Further, the first threshold is calculated by the processing module according to the laser vertical angle resolution and the detection range.
The beneficial effects are that: and searching dead points of suspected bird points within a first threshold range, eliminating interference factors and improving bird detection accuracy.
Further, the bird detection module comprises a speed measurement unit, the speed measurement unit is used for measuring the flying speed of birds, and the second threshold value is calculated by the processing module according to the flying speed of birds and the last moment.
The beneficial effects are that: the suspected bird point at the previous moment is searched according to the range determined by the flying speed of the birds, so that the continuity is improved, and the bird detection is more accurate.
Drawings
FIG. 1 is a logic block diagram of a first embodiment of a lidar-based bird detection system;
FIG. 2 is a flowchart illustrating an embodiment of a lidar-based bird detection system.
Detailed Description
Further details are provided below with reference to the specific embodiments.
Example 1
The bird detection system based on the laser radar comprises an acquisition module, a processing module and a bird detection module, wherein the acquisition module is in signal connection with the processing module, and the bird detection module is in signal connection with the processing module as shown in fig. 1.
The acquisition module continuously acquires the environment images of the target by a laser radar imaging method, the acquisition module can use the existing RS-LiDAR-16 type laser radar, and the acquisition module generates a reflected light beam after encountering the target by sending a plurality of laser beams, and obtains the environment images according to the reflected light beam.
The bird detection module comprises a filtering unit, a tag unit, a clustering unit, a first screening unit and a second screening unit.
The processing module acquires an environment image, forms a point cloud set and sends the point cloud set to the filtering unit, the filtering unit filters the environment image in the horizontal direction of each pixel point of the environment image through the filtering window, the filtering unit sends a static signal when the distance between the point cloud at the current moment and the point cloud at the previous moment in the filtering window is smaller than a first threshold value, and the filtering unit sends a dynamic signal when the distance between the point cloud at the current moment and the point cloud at the previous moment in the filtering window is larger than the first threshold value.
The processing module obtains a static signal and sends the static signal to the tag unit, the tag unit adds a static tag to the point cloud at the current moment according to the static signal, the processing module obtains a dynamic signal and sends the dynamic signal to the tag unit, the tag unit adds a dynamic tag to the point cloud at the current moment according to the dynamic signal, the static tag and the dynamic tag can be represented by different English letters, for example, the static tag is J, the dynamic tag is D, the processing module forms a static point cloud set according to the static tag, the processing module forms a dynamic point cloud set according to the dynamic tag, and the processing module can use a server of the existing background cloud.
The processing module sends the dynamic point cloud set to the clustering unit, the clustering unit clusters the dynamic point cloud set with a clustering radius to obtain a dynamic point cloud subset, the clustering radius is calculated according to the distance between the target and the acquisition module, and the clustering radius is in direct proportion to the distance between the target and the acquisition module.
The processing module obtains a dynamic point cloud subset, calculates the circumscribed sphere radius of the set of the dynamic point cloud subset, judges whether the target of the early suspected bird point is bird according to the confirmation signal, sends the reflectivity of the reflected light to the second screening unit when the environment image is obtained by the processing module, the second screening unit searches for the suspected bird point in the second threshold range when the early suspected bird point is in the previous time, and sends a confirmation signal to the processing module when the first screening unit is not provided with a static point when the first screening unit is in the first threshold range of the early suspected bird point at the current time, namely judges whether the target of the early suspected bird point is bird in the images of the previous time and the later time, the processing module judges the target of the early suspected bird point as bird according to the confirmation signal, the second screening unit sends a noise point signal to the processing module when the reflectivity is smaller than a preset value, for example, the processing module records the noise point as the noise point when the reflectivity is larger than 100.
As shown in fig. 2, the specific implementation process is as follows:
when bird detection is carried out around an airport or a transformer substation, a plurality of radar lasers emitted by an acquisition module generate reflected beams when radar laser beams meet targets, the acquisition module forms an environment image according to the reflected beams, for example, acquires the environment image around the airport or the transformer substation, the environment image mainly uses UDP protocol, an Ethernet medium is used for transmitting data packets, then a processing module analyzes MSOP packets to extract laser ranging values, echo reflectivity, horizontal rotation angles and time stamps, the horizontal angle resolution is 0.18 degrees when the sampling frequency of 10Hz is used, the time is within 0.1s, each laser circle is 2000 sampling points, so that the sampling points of one frame are 16 x 2000 when the 16 laser beams rotate one circle, and the image data similar to 16 x 2000 pixels can be organized.
After the data are acquired, the processing module acquires an environment image, then forms a point cloud set, the point cloud set is sent to the filtering unit, the filtering unit filters a window of 1 pixel on the left and right adjacent to each pixel point in the image data in the horizontal direction, when the distance between the current time point cloud in the filtering window and the previous time point cloud is smaller than a first threshold value, the filtering unit sends a static signal to the processing module, the processing module sends the static signal to the tag unit, the tag unit adds a static tag to the previous time point cloud according to the static signal, otherwise, the filtering unit sends a dynamic signal to the processing module, the processing module sends a dynamic signal to the tag unit, and the tag unit adds a dynamic tag to the previous time point cloud.
After the point cloud is tagged, the processing module divides the point cloud into a dynamic point cloud and a static point cloud according to the tag type, the processing module sends the dynamic point cloud to the clustering unit for cluster analysis, and clusters are carried out with a variable cluster radius to obtain a dynamic point cloud subset during the cluster analysis, wherein the cluster radius can be expressed as r= (2 x pi/360) x d+s, 2 represents the vertical angle resolution of the laser beam, d represents the distance between the laser point and the light source, s represents micro distance noise, for example, the cluster radius calculated at 50m is 1.717m, the measured vertical height is 1.728m, so s can be 1.728-1.717m, and a series of pixel points with the cluster radius r form the dynamic point cloud subset.
After the dynamic point cloud subset is obtained, the processing module obtains the circumscribed sphere radius of the set of the dynamic point cloud subset, the processing module takes the point cloud with the circumscribed sphere radius smaller than the third threshold value as a pre-suspected bird point, the pre-suspected bird point is sent to the first screening unit, the first screening unit searches the suspected bird point of which the pre-suspected bird point at the current moment is in the second threshold value range at the previous moment, the first screening unit searches the non-static point in the first threshold value range of the pre-suspected bird point at the current moment at the same time, at the moment, the first screening module sends a confirmation signal to the processing module, and the processing module judges that birds exist according to the confirmation signal.
The processing module acquires the reflectivity of the light reflected by the acquisition module from the image data and sends the reflectivity to the second screening unit, the reflectivity can be obtained when the image data is acquired, the second screening unit sends a noise signal to the processing module when the reflectivity is smaller than a preset value, and the processing module records the point cloud as a noise point.
According to the embodiment, after the environment image is acquired, the point clouds of the environment image are filtered and classified, then the dynamic point clouds are clustered and analyzed according to the changed clustering radius, and the real-time performance is greatly improved by combining the scheme of static point cloud distance screening, and the bird detection algorithm can be synchronously carried out with laser acquisition basically without hysteresis.
Example two
The difference from the first embodiment is that the first threshold is calculated by the processing module according to the vertical angular resolution of the laser and the detection range, the vertical angular resolution is 0.18 °, the detection range is 50m as an example, the detection range is a radius, the vertical angular resolution is a central angle, and then the first threshold = (0.18×pi/180) ×50 is obtained according to the arc length calculation formula of the sector; the second threshold value is obtained by multiplying the flying speed of the bird by the laser sampling period through the processing module, the bird detection module comprises a speed measurement unit, the speed measurement unit is used for measuring the flying speed of the bird, for example, the flying speed of the bird is 9m/s, and the flying speed of the bird can be 32-48 km/h of the flying speed of a common bird; the third threshold value is adaptively determined by the processing module according to the bird size, the suspected bird points are divided according to the bird size, for example, the bird size is 0.3m, the third threshold value can be set to be 0.3m, interference factors such as people and moving vehicles are eliminated, the accuracy of analyzing bird positions according to the suspected bird points is improved, the static points of the suspected bird points in the range of the first threshold value are searched, the interference factors are eliminated, the suspected bird points at the last moment are searched according to the range determined by the bird flight speed, the continuity is improved, and the bird detection is more accurate.
The foregoing is merely exemplary embodiments of the present invention, and specific structures and features that are well known in the art are not described in detail herein. It should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present invention, and these should also be considered as the scope of the present invention, which does not affect the effect of the implementation of the present invention and the utility of the patent. The protection scope of the present application shall be subject to the content of the claims, and the description of the specific embodiments and the like in the specification can be used for explaining the content of the claims.
Claims (10)
1. Bird detection system based on laser radar, its characterized in that includes collection module, processing module and surveys the bird module:
the acquisition module continuously acquires environment images of the target by a laser radar imaging method;
the processing module is used for acquiring an environment image forming point cloud set and sending the environment image forming point cloud set to the bird detection module;
the bird detection module filters the environment image and divides the environment image into dynamic points and static points, the bird detection module clusters the dynamic points with a clustering radius to obtain a dynamic point cloud subset, the bird detection module calculates the circumscribed sphere radius of the set of the dynamic point cloud subset and takes point clouds with the circumscribed sphere radius smaller than a third threshold value as early-stage suspected bird points, the bird detection module searches that the early-stage suspected bird points at the current moment have suspected bird points in a second threshold value range when the current moment is the previous moment, and the bird detection module searches that birds are detected when no static points exist in a first threshold value range of the early-stage suspected bird points at the current moment.
2. The lidar-based bird detection system of claim 1, wherein: the bird detection module comprises a filtering unit, wherein the filtering unit is used for filtering in the horizontal direction of each pixel point of the environment image through a filtering window, the filtering unit sends a static signal when the distance between the current time point cloud and the previous time point cloud in the filtering window is smaller than a first threshold value, and the filtering unit sends a dynamic signal when the distance between the current time point cloud and the previous time point cloud in the filtering window is larger than the first threshold value.
3. The lidar-based bird detection system of claim 2, wherein: the bird detection module further comprises a tag unit, the processing module acquires static signals and dynamic signals and sends the static signals and the dynamic signals to the tag unit, the tag unit adds static tags to the point cloud at the current moment according to the static signals, the tag unit adds dynamic tags to the point cloud at the current moment according to the dynamic signals, the processing module forms static point clouds according to the static tags, and the processing module forms dynamic point clouds according to the dynamic tags.
4. A lidar-based bird detection system according to claim 3, wherein: the bird detection module further comprises a clustering unit, and the clustering unit clusters the dynamic point cloud sets with a clustering radius to obtain a dynamic point cloud subset.
5. The lidar-based bird detection system of claim 4, wherein: the bird detection module further comprises a first screening unit, the processing module obtains the circumscribed sphere radius of the set of the dynamic point cloud subsets, the point cloud with the circumscribed sphere radius smaller than a third threshold value is used as a pre-suspected bird point, the first screening unit searches that the pre-suspected bird point at the current moment has a suspected bird point in a second threshold value range in the previous moment, the first screening unit searches that no static point exists in the first threshold value range of the pre-suspected bird point at the current moment, and the processing module sends a confirmation signal to the processing module, and the processing module judges the target as birds according to the confirmation signal.
6. The lidar-based bird detection system of claim 5, wherein: the bird detection module further comprises a second screening unit, the processing module obtains the reflectivity of the light reflected by the acquisition module from the environment image and sends the reflectivity to the second screening unit, the second screening unit sends a noise signal to the processing module when the reflectivity is smaller than a preset value, and the processing module records the point cloud as a noise.
7. The lidar-based bird detection system of claim 5, wherein: the clustering radius is calculated according to the distance between the target and the acquisition module, and the clustering radius is in direct proportion to the distance between the target and the acquisition module.
8. The lidar-based bird detection system of claim 1, wherein: the third threshold is adaptively determined by the processing module based on bird size.
9. The lidar-based bird detection system of claim 8, wherein: the first threshold is calculated by the processing module according to the laser vertical angle resolution and the detection range.
10. The lidar-based bird detection system of claim 9, wherein: the bird detection module comprises a speed measurement unit, the speed measurement unit is used for measuring the flying speed of birds, and the second threshold value is calculated by the processing module according to the flying speed of birds and the last moment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911401873.2A CN111077539B (en) | 2019-12-30 | 2019-12-30 | Bird detection system based on laser radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911401873.2A CN111077539B (en) | 2019-12-30 | 2019-12-30 | Bird detection system based on laser radar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111077539A CN111077539A (en) | 2020-04-28 |
| CN111077539B true CN111077539B (en) | 2023-06-02 |
Family
ID=70320050
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911401873.2A Active CN111077539B (en) | 2019-12-30 | 2019-12-30 | Bird detection system based on laser radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111077539B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111765882A (en) * | 2020-06-18 | 2020-10-13 | 浙江大华技术股份有限公司 | Laser radar positioning method and related device thereof |
| CN112364888A (en) * | 2020-10-16 | 2021-02-12 | 爱驰汽车（上海）有限公司 | Point cloud data processing method and device, computing equipment and computer storage medium |
| CN112800935B (en) * | 2021-01-25 | 2022-04-15 | 山东大学 | Layout method of equipment for predicting pest group trajectories and evaluating pest control effect |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101414006A (en) * | 2008-11-28 | 2009-04-22 | 北京航空航天大学 | Flying bird object identifying and tracking method based on radar image |
| CN101697007A (en) * | 2008-11-28 | 2010-04-21 | 北京航空航天大学 | Radar image-based flyer target identifying and tracking method |
| WO2014085328A1 (en) * | 2012-11-27 | 2014-06-05 | Wood, Lowell L., Jr. | Methods and systems for directing birds away from equipment |
| CN108828608A (en) * | 2018-03-29 | 2018-11-16 | 苏州大学张家港工业技术研究院 | Laser radar background data filtering method in vehicle checking method |
| US10139493B1 (en) * | 2016-07-06 | 2018-11-27 | Near Earth Autonomy, Inc. | Rotor safety system |
| CN109799760A (en) * | 2019-01-30 | 2019-05-24 | 华通科技有限公司 | The bird-repellent robots control system and control method of power industry |
| CN110133669A (en) * | 2019-05-24 | 2019-08-16 | 中铁科学技术开发有限公司 | A kind of three-dimensional laser foreign body intrusion monitoring method and system |
| CN110428008A (en) * | 2019-08-02 | 2019-11-08 | 深圳市唯特视科技有限公司 | A kind of target detection and identification device and method based on more merge sensors |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9523772B2 (en) * | 2013-06-14 | 2016-12-20 | Microsoft Technology Licensing, Llc | Object removal using lidar-based classification |
| WO2016033795A1 (en) * | 2014-09-05 | 2016-03-10 | SZ DJI Technology Co., Ltd. | Velocity control for an unmanned aerial vehicle |
| US11480681B2 (en) * | 2018-03-26 | 2022-10-25 | Research Foundation Of The City University Of New York | Lidar system for detection of small flying objects |
-
2019
- 2019-12-30 CN CN201911401873.2A patent/CN111077539B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101414006A (en) * | 2008-11-28 | 2009-04-22 | 北京航空航天大学 | Flying bird object identifying and tracking method based on radar image |
| CN101697007A (en) * | 2008-11-28 | 2010-04-21 | 北京航空航天大学 | Radar image-based flyer target identifying and tracking method |
| WO2014085328A1 (en) * | 2012-11-27 | 2014-06-05 | Wood, Lowell L., Jr. | Methods and systems for directing birds away from equipment |
| US10139493B1 (en) * | 2016-07-06 | 2018-11-27 | Near Earth Autonomy, Inc. | Rotor safety system |
| CN108828608A (en) * | 2018-03-29 | 2018-11-16 | 苏州大学张家港工业技术研究院 | Laser radar background data filtering method in vehicle checking method |
| CN109799760A (en) * | 2019-01-30 | 2019-05-24 | 华通科技有限公司 | The bird-repellent robots control system and control method of power industry |
| CN110133669A (en) * | 2019-05-24 | 2019-08-16 | 中铁科学技术开发有限公司 | A kind of three-dimensional laser foreign body intrusion monitoring method and system |
| CN110428008A (en) * | 2019-08-02 | 2019-11-08 | 深圳市唯特视科技有限公司 | A kind of target detection and identification device and method based on more merge sensors |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111077539A (en) | 2020-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111077539B (en) | Bird detection system based on laser radar | |
| CN110456343B (en) | Instant positioning method and system based on FMCW millimeter wave radar | |
| CN111158013B (en) | Multi-algorithm fusion bird detection system | |
| CN107607925B (en) | Target RCS real-time evaluation method for radar application | |
| CN109102702A (en) | Vehicle speed measuring method based on video encoder server and Radar Signal Fusion | |
| US8718323B2 (en) | Batch detection association for enhanced target descrimination in dense detection environments | |
| US9262838B2 (en) | Method and apparatus for detecting traffic video information | |
| CN110568433A (en) | High-altitude parabolic detection method based on millimeter wave radar | |
| CN113835074B (en) | Dynamic people flow monitoring method based on millimeter wave radar | |
| CN112946630B (en) | Personnel counting and tracking method based on millimeter wave radar | |
| CN112285698B (en) | Multi-target tracking device and method based on radar sensor | |
| Bennett et al. | Use of symmetrical peak extraction in drone micro-doppler classification for staring radar | |
| CN103149569A (en) | Method for recognizing high-voltage wire by laser radar based on wavelet transformation | |
| Sengupta et al. | Automatic radar-camera dataset generation for sensor-fusion applications | |
| CN110764083B (en) | Anti-intrusion data fusion method and system for millimeter wave radar | |
| CN111158014B (en) | Multi-radar comprehensive bird detection system | |
| CN210572736U (en) | Low, small and slow target automatic detection, tracking and identification system | |
| CN107783090B (en) | Millimeter wave radar-based radar signal processing method for collision avoidance system of fixed-wing unmanned aerial vehicle | |
| Long et al. | Wideband Radar System Applications | |
| WO2020154962A1 (en) | Target credibility determination method, target recognition method and system, vehicle, and storage medium | |
| CN113721214A (en) | Helicopter hovering detection method based on air traffic control radar | |
| CN207992067U (en) | A kind of device suitable for the detection of contact net running environment safe condition | |
| Huang et al. | An efficient multi-threshold selection method for lane detection based on lidar | |
| Tang et al. | Experimental results of target classification using mm wave corner radar sensors | |
| Yang et al. | Fusion of Millimeter-Wave Radar and Camera Vision for Pedestrian Tracking |
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 |