Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Monocular vision mileage measuring method and odometer based on image characteristics

A monocular vision and image feature technology, applied in the field of image processing, can solve the problem that the accuracy of triangulation reconstruction is not very high

Active Publication Date: 2019-07-23
宽衍(北京)科技发展有限公司
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Then the motion information between frames is the motion parameter fitting between two piles of 3D points; the disadvantage of binocular is that it is usually not very wide due to the fixed baseline and the limitation of the carrier size.
Therefore, the accuracy of triangulation reconstruction is generally not very high.

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
  • Monocular vision mileage measuring method and odometer based on image characteristics
  • Monocular vision mileage measuring method and odometer based on image characteristics
  • Monocular vision mileage measuring method and odometer based on image characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] Embodiment 1: The method for measuring mileage based on monocular vision based on image features is applied in vehicle-mounted tunnel detection equipment, and specifically includes the following steps:

[0051] (1) First, the camera is calibrated to obtain the parameters of the camera;

[0052] (2) Calculate the 2D feature points of the two frames before and after in the forward direction of the vehicle;

[0053] (3) matching the 2D feature points to find the corresponding feature points;

[0054] (4) Calculate the 3D coordinates of the feature points, and calculate the attitude according to the 3D coordinates and 2D coordinates of the feature points, and obtain the relative displacement;

[0055] (5) Take the same method for subsequent measured frames in turn, calculate the displacement of the camera relative to the previous frame when shooting each frame, and finally accumulate all the displacements to obtain the mileage;

[0056] Such as figure 1 As shown, the che...

Embodiment 2

[0080] Embodiment 2: the method for the monocular vision measurement mileage based on image features, specifically comprises the following steps:

[0081] 1) According to the checkerboard calibration algorithm, the camera is calibrated to obtain the internal parameters of the camera;

[0082] 2) Calculate the image features for the two frames before and after: first construct the image pyramid, and on each layer, extract the pixel point with a larger difference with the pixel point in the surrounding area as the key point; select point pairs around the key point, and pass Compare pixel values ​​to generate descriptors; adjust the descriptor according to the angle between the key point and the gray centroid, so that the descriptor has rotation invariance; finally obtain the descriptor of the image feature;

[0083] 3) Match the feature points on the two frames before and after to obtain the corresponding feature points: build a k-d tree for the feature point set on the image: s...

Embodiment 3

[0112] Embodiment 3: the method for the monocular vision measurement mileage based on image features, specifically comprises the following steps:

[0113] 1) According to the checkerboard calibration algorithm, the camera is calibrated to obtain the internal parameters of the camera;

[0114] 2) Calculate the image features for the two frames before and after: first construct the image pyramid, and on each layer, extract the pixel point with a larger difference with the pixel point in the surrounding area as the key point; select point pairs around the key point, and pass Compare pixel values ​​to generate descriptors; adjust the descriptor according to the angle between the key point and the gray centroid, so that the descriptor has rotation invariance; finally obtain the descriptor of the image feature;

[0115] 3) Match the feature points on the two frames before and after to obtain the corresponding feature points: build a k-d tree for the feature point set on the image: s...

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 monocular vision mileage measuring method and an odometer based on image characteristics. The method comprises the following steps: (1) calibrating a camera; (2) calculating 2D characteristic points of two adjacent frames of images along the advancing direction; (3) matching the 2D characteristic points to find corresponding characteristic points in the two frames of images; (4) calculating the 3D coordinates of the corresponding characteristic points in the two frames of images, and calculating the pose of the camera according to the 3D coordinates and the 2D coordinates of the corresponding characteristic points to obtain the relative displacement of the camera; and (5) performing the same operation on the subsequent frame, and finally accumulating all the displacements to obtain the mileage. Compared with a binocular vision-based method, the method for measuring the mileage by monocular vision is simple in equipment and low in cost; and compared with a method based on sift and Harris angular points, the method has the advantages that the image characteristic calculation speed is higher, and the rotation scale invariance and the real-time processing can be realized.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for measuring mileage based on monocular vision based on image features and an odometer. Background technique [0002] During the operation of the subway, apparent defects such as water leakage, cracks, and spalling of the tunnel structure mainly made of concrete materials, as well as deformation of the tunnel section, are unavoidable disease phenomena, and the long-term development of the disease has serious consequences for the safety of the tunnel. irreversible negative effects. Therefore, the maintenance of the tunnel structure in the subway operation is a necessary means to ensure the long-term safe operation of the tunnel. The position control of the sensor in the detection process directly affects the validity of the detection data collection. At present, most of the sensor positions for defect detection in subway tunnels are set in advance. For differe...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G01C22/00
CPCG01C22/00
Inventor 樊晓东孟俊华王飞唐文平高成
Owner 宽衍(北京)科技发展有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com