Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A loopback detection method based on a convolutional neural network and ORB features

A convolutional neural network and detection method technology, applied in the field of intelligent mobile robots, can solve the problems of slow detection speed, low detection discrimination of bag-of-words method, and affect the real-time performance and accuracy of SLAM algorithm, so as to reduce false matching Probability, the effect of increasing speed and accuracy

Active Publication Date: 2019-06-25
DALIAN UNIV OF TECH
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In the traditional SLAM algorithm, the bag-of-words method is often used for loop detection. The bag-of-words method needs to load a large dictionary before detection, and the detection discrimination of the bag-of-words method is not high, and the detection speed is relatively slow.
Therefore, it will greatly affect the overall real-time performance and accuracy of the SLAM algorithm.

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
  • A loopback detection method based on a convolutional neural network and ORB features
  • A loopback detection method based on a convolutional neural network and ORB features
  • A loopback detection method based on a convolutional neural network and ORB features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further described below by accompanying drawing. SqueezeNet was designed by UCBerkeley and Stanford researchers. Its original intention was not to achieve the best CNN recognition accuracy, but to simplify the network complexity while achieving the recognition accuracy of the public network. Therefore, this network is suitable for lightweight high-level computing devices, such as intelligent mobile robots. The network structure of SqueezeNet is as follows Figure 5 As shown, it has a total of 14 layers, which can finally convert a 224×224×3 image into a 1000-dimensional array.

[0040] SqueezeNet mainly reduces the number of parameters of the network by reducing the size of the convolution kernel, reducing the size of the pooling layer, and removing some fully connected layers, so as to increase the speed of extracting image features.

[0041] The specific operation process of this method is as follows: Figure 1-4 As shown, the new imag...

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 a loopback detection method based on a convolutional neural network and ORB features. The method comprises the following steps: adding a new image i into an image sequence; Extracting feature vectors of the image i and other images in the image sequence by using a convolutional neural network, and calculating the similarity of other chords; Carrying out ORB feature extraction on the image i and the image j of which the similarity is greater than a threshold value; And carrying out feature matching on the image i and the image j, and if the correct logarithm of the finally matched feature points of the two images is greater than a set threshold value, considering that loop-back occurs. Due to the fact that the convolutional neural network is used for replacing a traditional word bag method, the speed and accuracy of loopback detection are improved. According to the invention, the convolutional neural network and ORB features are combined, so that the mismatchingprobability is reduced.

Description

technical field [0001] The invention belongs to the field of intelligent mobile robots, in particular to a loop detection method based on convolutional neural network and ORB features. Background technique [0002] At this stage, autonomous driving technology is very hot, and people are looking forward to the arrival of the era of intelligent transportation. For the research of unmanned driving, the cost of direct real vehicle test is too high and the risk is relatively high. Therefore, major university-level scientific research institutions prefer to use low-cost wheeled mobile robots for scientific research, and then graft the research results to the real car. For an intelligent mobile robot, it mainly needs to have the following basic functions: [0003] Positioning: The robot must be able to accurately determine its own position information by relying on the sensors it carries; [0004] Navigation: The robot can smoothly reach the designated location from the starting...

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): G06T7/33G01C21/20
Inventor 郭烈王肖李琳辉赵一兵孙大川夏文旭王东兴
Owner DALIAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
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