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

Plant image real-time splicing method based on L-ORB algorithm

An image and algorithm technology, which is applied in the field of agricultural plant image acquisition and image mosaic, can solve the problems of high error matching rate, scale invariance and inferior to SIFT, etc.

Pending Publication Date: 2020-09-04
JIANGSU UNIV
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The main advantage of ORB (Oriented FAST and Rotated BRIEF) algorithm is that its operating speed is about 100 times that of SIFT and 10 times that of SURF, which can meet the real-time requirements, but the scale is not as deformed as SIFT, and the error matching rate is 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
  • Plant image real-time splicing method based on L-ORB algorithm
  • Plant image real-time splicing method based on L-ORB algorithm
  • Plant image real-time splicing method based on L-ORB algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention.

[0052] figure 1 It is the overall flowchart of the plant image real-time splicing method based on the L-ORB algorithm, and the steps of the specific implementation are as follows:

[0053] Step 1: First fix the RealSense D435 sensor on the trolley, move the trolley at a constant speed, collect the depth information and color information of the plants, and then perform range limitation according to the obtained depth information to reacquire multiple sets of color images, and then use the improved Mean -shift algorithm extracts the effective plant rectangular area in the color image;

[0054] The main process of the improved Mean-shift algorithm is as follows:

[0055] 1) Iterative space construction. Taking any pixel point P0 on the input color image as the center, establis...

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 plant image real-time splicing method based on an L-ORB algorithm, and belongs to the field of computer vision and image splicing. The method comprises the following steps: firstly, collecting color and depth information of a plant through a Real Sense D435 sensor, and combining an improved Mean-shift algorithm with the plant depth information to obtain an effective plantarea in a color image; adopting an L-ORB algorithm to perform feature point extraction on a plant area, and the algorithm optimizes the feature detection area of a segmented image and simplifies thesupport of the ORB algorithm for scale and rotation non-deformation; performing feature point matching by using a Multi-Probe LSH (Local Sensitive Hash) algorithm, so that the operation rate of feature matching is improved; and finally, eliminating mismatching by using a PROSAC (Progressive Sample Consensus, improved sample consistency) algorithm, and splicing the images by using a multi-resolution fusion algorithm of an optimal suture line. The research provides a new method for realizing real-time splicing of the images, and lays a foundation for promoting agricultural intellectualization.

Description

technical field [0001] The invention mainly relates to the fields of computer vision and image splicing, and specifically relates to the field of agricultural plant image collection and image splicing methods. Background technique [0002] In recent years, with the development of information science technology and computer graphics, image mosaic has gradually become a hot issue in the research of analog computer vision, image processing, virtual reality and automobile fields, and is widely used in military, aviation, geology, medicine, etc. , communications and many other fields. With the further development of agricultural intelligence, image stitching plays an important role in the detection of agricultural fruit plants, field management, and agricultural robot navigation, which improves the management efficiency of farmland and reduces the burden on staff. Real-time image stitching can Real-time image acquisition, real-time stitching and output of images play an importan...

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): G06K9/46G06K9/62G06T3/40G06T5/50G06T7/90
CPCG06T7/90G06T5/50G06T3/4038G06V10/462G06V10/757G06F18/23
Inventor 沈跃庄珍珍刘慧姜建滨
Owner JIANGSU 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