KR20170086799A - Apparatus and method for determing 3d object using rotation of laser - Google Patents
Apparatus and method for determing 3d object using rotation of laser Download PDFInfo
- Publication number
- KR20170086799A KR20170086799A KR1020160006252A KR20160006252A KR20170086799A KR 20170086799 A KR20170086799 A KR 20170086799A KR 1020160006252 A KR1020160006252 A KR 1020160006252A KR 20160006252 A KR20160006252 A KR 20160006252A KR 20170086799 A KR20170086799 A KR 20170086799A
- Authority
- KR
- South Korea
- Prior art keywords
- moving object
- information
- laser scanner
- dimensional
- rotation
- Prior art date
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
- 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
- G01S7/4817—Constructional features, e.g. arrangements of optical elements relating to scanning
-
- 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
Abstract
An apparatus and method for determining a three-dimensional object using laser rotation are disclosed. The three-dimensional object discriminating apparatus includes an information collecting unit for collecting three-dimensional point cloud of a moving object by scanning a moving object in space using a laser scanner, an information collecting unit for rotating the laser scanner vertically and horizontally Dimensional mesh information to mesh information, and a mesh control unit for matching the mesh information converted from the database storing the three-dimensional mesh information of each of the plurality of moving objects collected in advance And an object determining unit for determining a moving object to be moved.
Description
Embodiments of the present invention relate to an apparatus and method for obtaining a three-dimensional shape of a moving object using a fixed laser distance measurement module and determining the type of object based on the obtained three-dimensional shape.
The object recognition method using computer vision has a large variation in accuracy depending on the shooting time of the image information used for object recognition and the shooting environment such as weather. A complicated algorithm is used to improve the object recognition rate according to the shooting environment. However, when the algorithm is used, the calculation complexity increases and the time required for object recognition becomes very long. As described above, since the time required for object recognition increases, the power consumption increases, and real-time processing is difficult.
Particularly, when the object is far away from the measuring device that recognizes the object, there is a difficulty in obtaining the depth information of the object when acquiring the three-dimensional shape using the equipment for photographing the eye. That is, there is a difficulty in generating a three-dimensional shape from the depth information of the object measured due to the resolution limit.
Korean Patent Registration No. 10-1188584 describes a technique for discriminating an object in front of a vehicle using a camera and a laser scanner.
The present invention relates to a technique of scanning a moving object by rotating a stationary laser distance measuring device in the horizontal and vertical directions and determining the type of the object by implementing the three-dimensional shape using the depth information of the moving object from the scanned moving object .
The three-dimensional object discriminating apparatus includes an information collecting unit for collecting three-dimensional point cloud of a moving object by scanning a moving object in space using a laser scanner, an information collecting unit for rotating the laser scanner vertically and horizontally Dimensional mesh information to mesh information, and a mesh control unit for matching the mesh information converted from the database storing the three-dimensional mesh information of each of the plurality of moving objects collected in advance And an object determining unit for determining a moving object to be moved.
According to an aspect of the present invention, the rotation control unit may control the laser scanner to rotate in an " e " shape.
According to another aspect, the information collecting unit may control the laser scanner to scan the background when there is no moving object on the space, and store depth information of the scanned background in the auxiliary storage device. At this time, the rotation control unit determines a rotation start position for rotating the laser scanner based on the depth information of the background and the depth information of the moving object being measured, and controls the rotation of the laser scanner .
According to another aspect of the present invention, the rotation control unit controls the horizontal direction rotation of the laser scanner to be switched to the vertical direction rotation as the depth information of the background coincides with the depth information of the moving object within a predetermined error range can do.
The three-dimensional object discriminating method includes the steps of: collecting three-dimensional point cloud of a moving object by scanning a moving object in space using a laser scanner; controlling the laser scanner to rotate in the up and down and left and right directions Dimensional point information to mesh information, and determining a moving object that matches the mesh information converted from the database in which the three-dimensional mesh information of each of the plurality of moving objects collected in advance is stored .
By moving the stationary laser distance measuring device horizontally and vertically, the moving object is scanned irrespective of the width and length of the moving object. Based on the depth information of the moving object obtained through the scanning, By implementing the dimensional shape, image processing can obtain depth information of a hard object and more accurately determine the type of object.
FIG. 1 is a block diagram showing an internal configuration of a three-dimensional object discrimination apparatus according to an embodiment of the present invention.
FIG. 2 is a flowchart illustrating a method of determining a three-dimensional object by rotating a laser according to an embodiment of the present invention.
3 is a view for explaining a coordinate system sensed by a laser in an embodiment of the present invention.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
In particular, the present invention relates to a technique for recognizing an object using a laser scanner, in particular, a fixed laser scanner used for object recognition is rotated using a rotation module, And a technique for determining the type of moving object based on depth information of the moving object obtained by scanning the moving object.
In the present embodiments, the moving object may be an object to be scanned or photographed through a laser scanner, and may be a moving object such as a person, an animal, a vehicle, or the like. For example, the laser scanner may be mounted on a road or a pillar of an alley located in the vicinity of an area where a moving object is to be recognized, and the three-dimensional object discriminating apparatus may be configured to detect, based on moving object related information scanned through the laser scanner, Can be determined. For example, the three-dimensional object discriminating apparatus can be mounted on a laser scanner or separately from the laser scanner, and can control rotation of the laser scanner, information collection, and the like.
In this specification, the height of the moving object can be determined by moving the laser scanner up and down and scanning the moving object. For example, as the laser scanner scans the moving object while moving in the vertical direction, the height of the moving object can be determined according to the vertical moving size. Then, the vertical height of the moving object can be measured using an encoder, and Z-axis coordinates indicating the vertical height can be generated. As the laser scanner scans the moving object while moving in the lateral direction, the moving object can be scanned regardless of the width and the length of the moving object. Then, coordinates of the X-axis can be generated by measuring the rotation of the left and right using the encoder. The distance information from the laser scanner to the moving object can be generated as the depth information of the moving object as the laser scanner scans the moving object while moving in the vertical or horizontal direction and the depth information of the moving object is the Y- Lt; / RTI > Then, the three-dimensional object discrimination apparatus can determine the type of the scanned moving object by three-dimensionally mapping the moving object based on the generated X, Y, and Z axis coordinates. At this time, 3D rendering can be performed using the X, Y and Z axis coordinates and the depth information which is the distance from the laser scanner to the moving object. For example, in the case of rendering while moving up and down along the left and right rotation axes, the XZ value is determined using an encoder, and the Y value can be determined based on depth information, which is the distance from the laser scanner to the moving object. Then, by applying the XZ value and the Y value to a predefined rendering algorithm, a three-dimensional graphic rendering can be performed.
In this specification, only when the laser distance measurement module rotates and scans in the horizontal direction, the depth information, which is the distance information of the background and moving object, is obtained when the laser distance measurement module rotates in a ' And it is assumed that depth information is not obtained in the vertical direction rotation.
FIG. 1 is a block diagram illustrating an internal configuration of a three-dimensional object discrimination apparatus according to an embodiment of the present invention. FIG. 2 is a diagram illustrating a method of discriminating a three-dimensional object by rotating a laser according to an embodiment of the present invention Fig.
Referring to FIG. 1, the three-dimensional object
Although the laser scanner is not shown in FIG. 1, the laser scanner may be mounted on the three-dimensional object
In
For example, a laser scanner can scan a moving object or background moving in the surrounding space by emitting in a peripheral space where a near-infrared laser scanner with a low-power output, which is set to an extent that is harmless to the human body, is installed. At this time, when a moving object exists, the laser scanner senses the movement of the moving object by emitting the near-infrared rays in space, and can detect the presence of the moving object. When there is no moving object, the laser scanner can detect that there is no moving object due to no movement change on the space in which the near-infrared ray is radiated.
For example, the laser scanner can detect a moving object at a predetermined predetermined time interval (several μs to ms), and transmit the detection result (for example, moving object detection or moving object) to the three-dimensional object discrimination device.
In step 220, when the moving object does not exist, the laser scanner scans the background corresponding to the space in which the near-infrared rays are radiated, and transmits the depth information of the scanned background to the three-dimensional object discrimination device.
Then, the
If it is detected in step 230 that the moving object is present, that is, if the detection result collected by the
For example, the
At this time, in controlling the rotation of the laser scanner, the
In
In step 250, the
Here, the 3D mesh information of each of a plurality of objects collected in advance may be stored together with the object related information and stored and managed. For example, when the object is an eye, the three-dimensional mesh information of the child and the key and age of the child may be associated with each other and stored in the database. If the object is a vehicle, , Light vehicle, medium size, large size, etc.), model name, vehicle name, etc., may be associated and stored in the database.
Then, the
On the other hand, when the matching rate between the converted 3D mesh information and each of the 3D mesh information previously stored in the database is equal to or greater than the predetermined matching reference value, that is, when the matching rate is equal to or larger than the error range, the
3 is a view for explaining a coordinate system sensed by a laser in an embodiment of the present invention.
3, the depth information of the background and the depth information of the moving object stored in the auxiliary memory device are stored in the coordinate display method of the spherical coordinate system
, And the laser scanner may include a laser distance measurement module and a rotation module. Here, r represents the distance from the laser scanner, specifically, the laser distance measurement module to the measurement object (for example, background, moving object) Assuming that a virtual straight line passing through the ceiling from the rotation module rotating the laser distance measurement module is the z-axis, a virtual vector connecting the z-axis and the measurement object and the laser distance measurement module This may correspond to the smaller of the two. And, From a rotation module to a point on a predetermined horizon line, And the angle formed by projecting the light onto the plane of the horizon.As described above, the depth information of the background corresponding to the moving object and the depth information of the moving object
TheAt this time, the laser distance measuring module can perform only horizontal or vertical rotation at any moment during the rotation. That is, when the laser scanner rotates, the rotational direction can be switched in the vertical direction during the rotation in the horizontal direction. For example, the
In this case, when the laser distance measurement module rotates in the horizontal direction and the scanning is performed, the depth information which is the distance information of the background and the moving object can be obtained And depth information may not be obtained in the vertical direction rotation. The horizontal resolution corresponding to the distance information measured through the scanning in the laser distance measuring module is inversely proportional to the rotational speed of the rotating module and can be directly proportional to the sampling frequency of the laser distance measuring module. The vertical resolution corresponding to the distance information measured through the scanning in the laser distance measurement module may be inversely proportional to the rotation angle of the rotation module in the vertical direction once.
When the process of calculating the depth information of the moving object is completed while rotating the laser scanner to the 'r' character, the
Since the depth information of the moving object calculated according to Equation (1) does not have the same measurement time of each point, when the depth information is visualized, a distortion phenomenon in which the lower portion is deviated toward one side may occur. The faster the moving speed of the moving object, the more the distortion can be. Accordingly, the
Referring again to Equation (1), the three-dimensional point orthogonal coordinate information converted into the rectangular coordinates may represent one side of the moving object to be measured. Here, the three-dimensional point orthogonal coordinate information is transferred to the first octal space of the three-dimensional orthogonal coordinate system using the linear coordinate transformation as the three-dimensional mesh information, and is applied to the object recognition algorithm based on the three-dimensional point information, It can be used for kind discrimination.
For example, it is possible to compare three-dimensional mesh information of a plurality of persons built in a database and three-dimensional mesh information (three-dimensional point orthogonal coordinate information) of a moving object with each other, The type and identity of the moving object can be determined based on the information.
As described above, the laser distance measurement module is rotated using the rotation module, and the distance from the laser scanner to the moving object is measured through the laser distance measurement module to obtain the depth information of the moving object. Accordingly, it is possible to determine the moving object more accurately without using a computer vision having a large deviation in recognition accuracy. That is, the accuracy of object recognition can be improved.
The method according to an embodiment may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions to be recorded on the medium may be those specially designed and configured for the embodiments or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.
While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. For example, it is to be understood that the techniques described may be performed in a different order than the described methods, and / or that components of the described systems, structures, devices, circuits, Lt; / RTI > or equivalents, even if it is replaced or replaced.
Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.
Claims (5)
A rotation control unit for controlling the laser scanner to rotate in the vertical and horizontal directions;
A mesh conversion unit for converting the three-dimensional point information into mesh information; And
An object determining unit that determines a moving object matching with the converted mesh information from a database storing three-dimensional mesh information of each of a plurality of moving objects collected in advance,
Dimensional object discriminating device.
The rotation control unit includes:
To control the laser scanner to rotate in an " e " shape
Dimensional object discriminating apparatus.
The information collecting unit,
Controlling the laser scanner to scan the background when there is no moving object on the space, storing depth information of the scanned background in the auxiliary storage device,
The rotation control unit includes:
Determining a rotation start position for rotating the laser scanner based on depth information of the background and depth information of the moving object being measured, and controlling the laser scanner to rotate in accordance with a predefined rotation direction
Dimensional object discriminating apparatus.
The rotation control unit includes:
And controlling so that the horizontal rotation of the laser scanner is switched to the vertical rotation as the depth information of the background coincides with the depth information of the moving object within a predetermined error range
Dimensional object discriminating apparatus.
Controlling the laser scanner to rotate in the vertical and horizontal directions;
Converting the three-dimensional point information into mesh information; And
Determining a moving object matching with the converted mesh information from a database storing three-dimensional mesh information of each of a plurality of moving objects collected in advance
Dimensional object.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020160006252A KR101784584B1 (en) | 2016-01-19 | 2016-01-19 | Apparatus and method for determing 3d object using rotation of laser |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020160006252A KR101784584B1 (en) | 2016-01-19 | 2016-01-19 | Apparatus and method for determing 3d object using rotation of laser |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20170086799A true KR20170086799A (en) | 2017-07-27 |
KR101784584B1 KR101784584B1 (en) | 2017-10-12 |
Family
ID=59427779
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020160006252A KR101784584B1 (en) | 2016-01-19 | 2016-01-19 | Apparatus and method for determing 3d object using rotation of laser |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR101784584B1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10726612B2 (en) | 2018-06-22 | 2020-07-28 | Electronics And Telecommunications Research Institute | Method and apparatus for reconstructing three-dimensional model of object |
WO2020218683A1 (en) * | 2019-04-23 | 2020-10-29 | 이지스로직 주식회사 | Three-dimensional image acquisition system using lidar |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005070840A (en) | 2003-08-25 | 2005-03-17 | East Japan Railway Co | Three dimensional model preparing device, three dimensional model preparing method and three dimensional model preparing program |
-
2016
- 2016-01-19 KR KR1020160006252A patent/KR101784584B1/en active IP Right Grant
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10726612B2 (en) | 2018-06-22 | 2020-07-28 | Electronics And Telecommunications Research Institute | Method and apparatus for reconstructing three-dimensional model of object |
WO2020218683A1 (en) * | 2019-04-23 | 2020-10-29 | 이지스로직 주식회사 | Three-dimensional image acquisition system using lidar |
Also Published As
Publication number | Publication date |
---|---|
KR101784584B1 (en) | 2017-10-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102109941B1 (en) | Method and Apparatus for Vehicle Detection Using Lidar Sensor and Camera | |
JP5822255B2 (en) | Object identification device and program | |
CA2950791C (en) | Binocular visual navigation system and method based on power robot | |
JP4233723B2 (en) | Obstacle detection device, obstacle detection method, and recording medium recording an obstacle detection program | |
JP5303873B2 (en) | Vehicle shape measuring method and apparatus | |
KR102029850B1 (en) | Object detecting apparatus using camera and lidar sensor and method thereof | |
JP2015057690A (en) | Image processor, recognition object detection method, recognition object detection program, and traveling body control system | |
JP6597795B2 (en) | Image processing apparatus, object recognition apparatus, device control system, image processing method and program | |
JP5775965B2 (en) | Stereo camera system and moving body | |
CN111178295A (en) | Parking space detection and model training method and device, vehicle, equipment and storage medium | |
KR20210090384A (en) | Method and Apparatus for Detecting 3D Object Using Camera and Lidar Sensor | |
WO2017094300A1 (en) | Image processing device, object recognition device, device conrol system, image processing method, and program | |
JP6547841B2 (en) | Image processing apparatus, object recognition apparatus, device control system, image processing method and program | |
CN109240291B (en) | Robot motion line planning method and system based on remote control | |
JP6572696B2 (en) | Image processing apparatus, object recognition apparatus, device control system, image processing method and program | |
CN109886064A (en) | Determination can driving space boundary method | |
KR101784584B1 (en) | Apparatus and method for determing 3d object using rotation of laser | |
JP2010079639A (en) | Pedestrian detecting device for vehicle | |
KR20160125803A (en) | Apparatus for defining an area in interest, apparatus for detecting object in an area in interest and method for defining an area in interest | |
JP2007233440A (en) | On-vehicle image processor | |
JP3465531B2 (en) | Object recognition method and apparatus | |
JP3969984B2 (en) | Recognition method for moving objects | |
JP2019179289A (en) | Processing device and program | |
JP3475700B2 (en) | Object recognition method, object recognition device, and vehicle recognition device | |
JP4475060B2 (en) | Human detection device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
E902 | Notification of reason for refusal | ||
E701 | Decision to grant or registration of patent right | ||
GRNT | Written decision to grant |