CN112540383A - Efficient following method based on laser human body detection - Google Patents
Efficient following method based on laser human body detection Download PDFInfo
- Publication number
- CN112540383A CN112540383A CN202010819446.2A CN202010819446A CN112540383A CN 112540383 A CN112540383 A CN 112540383A CN 202010819446 A CN202010819446 A CN 202010819446A CN 112540383 A CN112540383 A CN 112540383A
- Authority
- CN
- China
- Prior art keywords
- data processing
- processing device
- human body
- laser
- point cloud
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000001514 detection method Methods 0.000 title claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 31
- 238000010801 machine learning Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 7
- 230000006399 behavior Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G01S7/481—Constructional features, e.g. arrangements of optical elements
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)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention discloses a high-efficiency following method based on laser human body detection, which comprises a laser radar; the robot identification system comprises a data processing device and a control device, wherein the control device can be used for controlling the robot to move, a laser radar is used for collecting point cloud information in the environment, the point cloud information is transmitted into the data processing device, the data processing device carries out point cloud classification according to a human leg recognizer of a human leg identification model obtained through machine learning training in advance, and meanwhile, the data processing device can output alternative human leg information.
Description
Technical Field
The invention relates to the technical field of human body detection, in particular to a laser-based high-efficiency following method for human body detection.
Background
The Chinese invention patent 'pedestrian following system and method based on UWB and laser radar hybrid location' (publication number: CN107765220A) proposes a pedestrian following system and method based on UWB and laser radar hybrid location, although the method relates to human body detection by laser radar, but has the following disadvantages:
disadvantage 1: the patent mentions that detecting a human body by a lidar relies on UWB information, and if the UWB device fails, the lidar detects that the human body is disabled. And (2) disadvantage: according to the method, the laser radar only screens the human leg point cloud in each frame of laser point cloud through UWB information, actually due to the characteristics of UWB, the data obtained after being shielded is inaccurate, the obtained human leg point cloud data is not necessarily accurate, and therefore the method is prone to error identification. Disadvantage 3: this patent does not mention processing in which the human body is followed whenever the user goes backward, the user turns around, or the like.
In addition, the prior art which is similar to the invention and realizes the following of the human body through other sensors also has the following defects: disadvantage 1: if the technology of collecting and identifying human body images by using the camera is used, the situations of incapability of identification and error identification are easy to occur in a scene with insufficient illumination. And (2) disadvantage: if a camera is used for acquiring and identifying human body images, image information is more abundant than that of a laser radar, and the occupancy rates of a CPU and an internal memory are large. Disadvantage 3: if external source positioning devices such as bluetooth and UWB are used, the current technical level is limited, and the positioning accuracy of the method is not accurate, which affects the following effect.
Disclosure of Invention
The invention aims to solve the technical problem of providing a high-efficiency following method based on laser human body detection, which has higher accuracy and flexibility in pedestrian detection and identification.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a high-efficiency following method based on laser human body detection comprises a laser radar; the robot system comprises a data processing device and a control device, wherein the control device can be used for controlling the robot to move, the laser radar is used for collecting point cloud information in the environment, the point cloud information is transmitted into the data processing device, the data processing device carries out point cloud classification according to a human leg recognizer of a human leg recognition model obtained through machine learning training in advance, and meanwhile, the data processing device can output alternative human leg information.
Preferably, a following controller is arranged in the data processing device, and the following controller controls the robot to execute different actions according to the motion mode of the pedestrian.
Preferably, the human leg recognizer may recognize human body information, and the human leg recognizer transmits the recognized human body information to a following controller operating in the data processing device.
Preferably, an inference model is further provided in the data processing apparatus.
By adopting the technical scheme, the machine learning algorithm is adopted for human body recognition, so that compared with the traditional manually designed model, the model obtained through machine learning training has higher accuracy and is more reliable.
The laser radar is adopted for human body identification and obstacle avoidance, other sensors are not needed, the system is simpler in structure, and the manufacturing and maintenance cost is lower.
The following controller that can realize has covered various pedestrian's motion action modes to all there are different modes to different modes, consequently follow efficiency higher, the robot follows the action more nimble.
Drawings
FIG. 1 is a schematic representation of the application of the method of the present invention;
FIG. 2 is a schematic flow chart of a laser human body detection following method according to the present invention.
In the figure, 1-laser radar, 2-data processing device and 3-control device.
Detailed Description
The following further describes embodiments of the present invention with reference to the drawings. It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
In the embodiment, an efficient following method based on laser human body detection, as shown in fig. 1 and 2, includes a laser radar; the robot system comprises a data processing device and a control device, wherein the control device can be used for controlling the robot to move, a laser radar is used for collecting point cloud information in the environment, the point cloud information is transmitted into the data processing device, the data processing device carries out point cloud classification according to a human leg recognizer of a human leg recognition model obtained through machine learning training in advance, and meanwhile, the data processing device can output alternative human leg information.
The data processing device is provided with a following controller, and the following controller controls the robot to execute different actions according to the motion mode of the pedestrian.
Secondly, the human body information can be identified by the human leg identifier, and the human leg identifier transmits the identified human body information to the following controller running in the data processing device.
In this embodiment, an inference model is also provided in the data processing apparatus.
The method comprises the steps that a laser radar collects point cloud information in an environment, the point cloud information is transmitted to a data processing device, the data processing device carries out point cloud classification according to a human leg recognizer of a human leg recognition model obtained through machine learning training in advance, and alternative human leg information is output.
Specifically, a large number of human leg point cloud positive samples and negative samples are collected in advance and input into a machine learning trainer for training, and finally, an inference model which can identify whether the point cloud is a human leg only by inputting point cloud information can be obtained, and the model runs in a data processing device.
The pedestrian stands in a certain distance in front of the laser radar in advance, the human leg recognizer recognizes human body information and transmits the human body information to the following controller running on the data processing device, and the following controller controls the robot to execute different actions according to the motion mode of the pedestrian. When the pedestrian moves forward, the following controller adopts a path planner comprising a time-varying elastic belt method to plan a path and keeps a certain distance from the pedestrian. The path planner comprising the time-varying elastic band method can plan a collision-free path according to the positions of pedestrians and laser point cloud data of the surrounding environment. When the pedestrian retreats, the following controller gives a retreating instruction to the robot moving device to control the robot to synchronously retreat, and when the pedestrian retreats within a certain range, the robot is controlled to retreatWhen the obstacle is in place, the robot stops moving backwards to avoid collision. The sensor for detecting the presence or absence of an obstacle behind the sensor does not necessarily have to be a laser radar, and may be another distance sensor. When the pedestrian walks around the robot by taking the robot as a center, the following controller sends a rotation instruction to the robot movement device to control the robot to synchronously rotate. Specifically, the coordinate deviation (Δ x, Δ y) of the pedestrian position in the laser data frame with respect to the previous frame is first solved if Δ x > 0, and
(angle 45 °), determining artificial forward behavior; if Δ x < 0, and
(angle 45 degrees), judging the artificial retreating behavior; if it is
(angle 45 °), the pedestrian is determined to be a detour. The specific process of the laser human body detection high-efficiency following method.
The invention discloses a pedestrian position acquisition mode: based on the laser radar, the point cloud data are processed by adopting a machine learning algorithm, and the position information of the pedestrian is obtained.
The following action judgment method of the invention: and deducing the motion mode of the pedestrian by comparing the position information of the pedestrian before and after two times. The threshold setting in the determination mode may be set according to actual conditions.
The installation mode of the laser radar of the invention is as follows: the device does not need to be installed on a robot moving device, and can be fixedly installed in the surrounding environment.
The output result of the inventor detection algorithm is not necessarily input into the robot motion device, and can be output to other devices for other purposes.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. It will be apparent to those skilled in the art that various changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, and the scope of protection is still within the scope of the invention.
Claims (4)
1. A high-efficiency following method based on laser human body detection is characterized in that: comprises a laser radar; the robot system comprises a data processing device and a control device, wherein the control device can be used for controlling the robot to move, the laser radar is used for collecting point cloud information in the environment, the point cloud information is transmitted into the data processing device, the data processing device carries out point cloud classification according to a human leg recognizer of a human leg recognition model obtained through machine learning training in advance, and meanwhile, the data processing device can output alternative human leg information.
2. The laser-based human body detection efficient following method according to claim 1, characterized in that: and the data processing device is internally provided with a following controller, and the following controller controls the robot to execute different actions according to the motion mode of the pedestrian.
3. The laser-based human body detection efficient following method according to claim 1, characterized in that: the human leg recognizer can recognize human body information, and the human leg recognizer transmits the recognized human body information to a following controller running in the data processing device.
4. The laser-based human body detection efficient following method according to claim 1, characterized in that: and the data processing device is also provided with an inference model.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201921541206X | 2019-09-17 | ||
| CN201921541206 | 2019-09-17 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112540383A true CN112540383A (en) | 2021-03-23 |
Family
ID=75013378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010819446.2A Pending CN112540383A (en) | 2019-09-17 | 2020-08-14 | Efficient following method based on laser human body detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112540383A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117471484A (en) * | 2023-12-28 | 2024-01-30 | 深圳市镭神智能***有限公司 | Pedestrian navigation method, computer-readable storage medium and electronic equipment |
-
2020
- 2020-08-14 CN CN202010819446.2A patent/CN112540383A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117471484A (en) * | 2023-12-28 | 2024-01-30 | 深圳市镭神智能***有限公司 | Pedestrian navigation method, computer-readable storage medium and electronic equipment |
| CN117471484B (en) * | 2023-12-28 | 2024-03-05 | 深圳市镭神智能***有限公司 | Pedestrian navigation method, computer-readable storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112683288B (en) | Intelligent guiding method for assisting blind in crossing street in intersection environment | |
| CN108052097B (en) | Method for training heterogeneous sensing system and heterogeneous sensing system | |
| WO2021134296A1 (en) | Obstacle detection method and apparatus, and computer device and storage medium | |
| CN110765894B (en) | Target detection method, device, equipment and computer readable storage medium | |
| KR102420476B1 (en) | Apparatus and method for estimating location of vehicle and computer recordable medium storing computer program thereof | |
| WO2017133453A1 (en) | Method and system for tracking moving body | |
| KR102016549B1 (en) | System and methof of detecting vehicle and lane position | |
| TWI481980B (en) | Electronic apparatus and navigation method thereof | |
| CN110653831B (en) | Hazardous gas leakage source positioning system and method for multi-flavor-searching robot of underground comprehensive pipe gallery | |
| WO2013011543A1 (en) | Autonomous locomotion equipment and control method therefor | |
| JP2020502654A (en) | Human-machine hybrid decision-making method and apparatus | |
| CN108230254A (en) | A kind of full lane line automatic testing method of the high-speed transit of adaptive scene switching | |
| WO2017041225A1 (en) | Robot following method | |
| JP2019099138A (en) | Lane-keep auxiliary method and device | |
| US20210213619A1 (en) | Robot and control method therefor | |
| US11335099B2 (en) | Proceedable direction detection apparatus and proceedable direction detection method | |
| KR20090061355A (en) | Method for controlling driving of moving robot and moving robot using the same | |
| KR20130054637A (en) | Apparatus and method detecting object in automatic parking system | |
| JP2019074458A (en) | Information processor, learned model, method for processing information, and program | |
| KR101944497B1 (en) | Control system and method of unmanned driving vehicle using intelligent CCTV | |
| JP2008310440A (en) | Pedestrian detection device | |
| US11080562B1 (en) | Key point recognition with uncertainty measurement | |
| US10867192B1 (en) | Real-time robust surround view parking space detection and tracking | |
| CN112540383A (en) | Efficient following method based on laser human body detection | |
| CN108931979A (en) | Vision tracking mobile robot and control method based on ultrasonic wave auxiliary positioning |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210323 |