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

End-to-end semantic instant-positioning and graph building method based deep learning

A deep learning and semantic technology, applied in image enhancement, image analysis, image data processing, etc., can solve problems such as incomparable performance

Active Publication Date: 2018-10-16
ZHEJIANG UNIV
View PDF8 Cites 77 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method brings novel ideas, but the performance cannot be compared with the traditional method at present

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
  • End-to-end semantic instant-positioning and graph building method based deep learning
  • End-to-end semantic instant-positioning and graph building method based deep learning
  • End-to-end semantic instant-positioning and graph building method based deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0080] The present invention is further described below.

[0081] Embodiment implemented according to the inventive method and implementation process thereof are:

[0082] (1) The continuous original image sequence and the original 3D point cloud sequence corresponding to the image sequence are respectively collected by the color camera and the laser radar, and the total number of frames of the original image sequence and the original 3D point cloud sequence are the same;

[0083] (2) For each frame of image I t , by the current frame image I t Its adjacent frame images are constructed to form a continuous five-frame image sequencet-2 , I t-1 , I t , I t+1 , I t+2 >, with five consecutive frames of image sequence t-2 , I t-1 , I t , I t+1 , I t+2 >Divide the original image sequence and the original 3D point cloud sequence as the basic unit, and process to obtain a continuous five-frame image sequencet-2 , I t-1 , I t , I t+1 , I t+2 >Pose transformation informatio...

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 discloses an end-to-end semantic instant-positioning and graph building method based on deep learning. A continuous original image sequence and an original three-dimensional point cloudsequence corresponding to the image sequence are respectively collected and obtained through a color camera and lidar, and pose transformation information, depth information and semantic segmentationinformation of continuous five-image sequences are obtained by processing; and a multi-task deep neural network with branches is constructed, the sequences are input into the multi-task deep neural network, and the multi-task deep neural network is trained for obtaining parameters, and the trained multi-task deep neural network is adopted to process a consecutive to-be-tested five-image sequence to obtain pose transformation information, depth information and semantic segmentation information among images. Compared with a traditional ORB-SLAM algorithm and methods similarly based on deep learning, the method of the invention has better performance.

Description

technical field [0001] The invention relates to an image simultaneous positioning and mapping method, in particular to an end-to-end semantic real-time positioning and mapping method based on deep learning. Background technique [0002] Among the key technologies of unmanned platforms, the functions of environment perception and positioning itself are essential. At the same time, the positioning and mapping algorithm is the master of the algorithm to solve these problems. It uses various sensors to perceive the surrounding environment and estimate its own position, and is widely used in unmanned systems. [0003] At present, most of the simultaneous positioning and mapping algorithms provide the structural information of the environment and their own position information, lack of understanding of the scene, and are often not enough to meet the needs of unmanned platforms to perform tasks. In order to obtain richer environmental information, it is particularly urgent to add ...

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): G06T7/70G06T7/10G06T7/50G06N3/04
CPCG06T7/10G06T7/50G06T7/70G06T2207/10044G06T2207/10024G06T2207/20084G06N3/045
Inventor 严超华龚小谨
Owner ZHEJIANG UNIV
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