Unlock instant, AI-driven research and patent intelligence for your innovation.

Three-dimensional reconstruction system and method based on unmanned trolley

A 3D reconstruction and unmanned car technology, applied in the field of 3D reconstruction, can solve the problem of re-acquisition of unmissable positions and achieve low cost and better economic performance

Pending Publication Date: 2021-03-30
SUN YAT SEN UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the shortcomings that the existing 3D reconstruction system cannot automatically re-acquire the missing position in a targeted manner, and needs to manually complete the missing analysis and then collect, and provide a 3D reconstruction system based on an unmanned car

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Three-dimensional reconstruction system and method based on unmanned trolley
  • Three-dimensional reconstruction system and method based on unmanned trolley

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Such as figure 1 Shown is an embodiment of a 3D reconstruction system based on an unmanned car of the present invention. A 3D reconstruction system based on an unmanned car, which includes Raspberry Pi, PC terminal, binocular camera module, RGB camera module, control steering gear and IO expansion control board. The binocular camera module communicates with the Raspberry Pi through USB, the RGB camera module communicates with the Raspberry Pi through USB, the Raspberry Pi communicates with the PC through WIFI two-way, and the Raspberry Pi communicates with the IO expansion control board through GPIO. The extended control board controls the connected wheel drive motor and the movement of the steering gear through PWM, and the RGB camera module is located on the steering gear.

[0045] In this embodiment, the Raspberry Pi: collects the data information of the binocular camera module, the RGB camera module, and the PC terminal, and sends a movement command to the IO expan...

Embodiment 2

[0048] Such as figure 2Shown is an embodiment of a 3D reconstruction method based on an unmanned car in the present invention. A three-dimensional reconstruction method based on an unmanned car, which includes the following specific steps:

[0049] Step 1. Input the position of the target to be collected and the maximum external range on the PC.

[0050] Step 2. The PC end divides the input space into a planar grid in the form of a top view, removes the grid where the modeling object is located, and generates the initial path for driving and collecting data.

[0051] Step 3. Use the binocular camera and IMU to obtain the current pose information.

[0052] Step 4. The IO expansion control board uses PID to control the movement of the unmanned car according to the pose information and the set path. When it runs to the position of the data point, the pose and image color are collected through the binocular camera module and the RGB camera module. .

[0053] Step 5. Input the...

Embodiment 3

[0059] An embodiment of a three-dimensional reconstruction method based on an unmanned car. A three-dimensional reconstruction method based on an unmanned car, including the following specific steps:

[0060] Step 1. First input the location of the target to be collected and the maximum external range on the PC. The user needs to set the maximum range W×L and the modeling granularity d in it. The map will be divided and numbered from the upper left corner to the lower right corner It is a grid G ​​with side length d={g 1 , g 2 , g 3 ,Kg i}.

[0061] Step 2. Set an initial no-go zone (X f ,Y f ,W f , K f ), respectively represent the coordinates and length and width of the progress area. Then the above grid G ​​will be traversed. If the center point of the grid is within this range, the grid will be deleted to prevent the unmanned car from entering the restricted area.

[0062] Step 3. Next, the unmanned car will move in sequence in the aforementioned processed grid G...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a three-dimensional reconstruction system based on an unmanned trolley. The system comprises a Raspberry Pi, a PC terminal, a binocular camera module, an RGB camera module, a control steering engine and an IO expansion control panel. The binocular camera module is in communication connection with the Raspberry Pi through a USB, the RGB camera module is in communication connection with the Raspberry Pi through a USB, the Raspberry Pi is in bidirectional communication with the PC through WIFI, the Raspberry Pi is in communication connection with the IO expansion control panel through GPIO, the IO expansion control panel controls a wheel driving motor and a control steering engine connected with the IO expansion control panel through PWM, and the RGB camera module is located on the control steering engine. The invention further provides a three-dimensional reconstruction method based on the unmanned trolley. The missing position of the three-dimensional model can beautomatically analyzed, the driving path of the unmanned trolley is re-planned according to the missing position, shooting is carried out again according to the driving path, and three-dimensional reconstruction is completed.

Description

technical field [0001] The present invention relates to the technical field of three-dimensional reconstruction, and more specifically, relates to a three-dimensional reconstruction system and method based on an unmanned trolley. Background technique [0002] The existing 3D reconstruction methods are mainly divided into two types: one is real-time mapping or SLAM, and the other is offline mapping. The commonly used method is SfM. These two methods are generally performed manually, and a camera needs to be manually used to collect images or video data of an object to be reconstructed, and then perform a reconstruction step. [0003] Real-time mapping will distinguish between a key frame and subsequent data frames of the image, and the pixels in the key frame will be initialized with a probability and an initial position will be established. Subsequent images are used as data frames for pose matching with the current keyframe. Then match the pixels on the image and calculat...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06T17/20
CPCG06T17/20G06V20/56
Inventor 顾家宝杨然
Owner SUN YAT SEN UNIV