THE TECHNICAL VISION SYSTEM FOR DIAGNOSIS OF THE HARVESTING UNIT OF THE ROBOT FOR GATHERING WILD PLANTS A.I. Kuznetsov, A.V. Tyryshkin National Research.

Slides:



Advertisements
Similar presentations
Introduction to Machine Learning BITS C464/BITS F464
Advertisements

By: Mani Baghaei Fard.  During recent years number of moving vehicles in roads and highways has been considerably increased.
QR Code Recognition Based On Image Processing
The optical sensor of the robot Phoenix-1 Aleksey Dmitriev.
Stability of computer network for the set delay Jolanta Tańcula.
Face Recognition and Biometric Systems 2005/2006 Filters.
Ping Gallivan Xiang Gao Eric Heinen Akarsh Sakalaspur Automated Coin Grader.
1 Building a Dictionary of Image Fragments Zicheng Liao Ali Farhadi Yang Wang Ian Endres David Forsyth Department of Computer Science, University of Illinois.
Imaging Science Fundamentals Chester F. Carlson Center for Imaging Science The Properties of Images and Imaging Devices Group II of the Imaging Chain.
Virtual Dart: An Augmented Reality Game on Mobile Device Supervisor: Professor Michael R. Lyu Prepared by: Lai Chung Sum Siu Ho Tung.
Noman Haleem B.E. in Textile Engineering from National Textile University Specialization in Yarn Manufacturing Topic “Determination of Twist per Inch.
Tracking a moving object with real-time obstacle avoidance Chung-Hao Chen, Chang Cheng, David Page, Andreas Koschan and Mongi Abidi Imaging, Robotics and.
On the Construction of Energy- Efficient Broadcast Tree with Hitch-hiking in Wireless Networks Source: 2004 International Performance Computing and Communications.
Distinguishing Photographic Images and Photorealistic Computer Graphics Using Visual Vocabulary on Local Image Edges Rong Zhang,Rand-Ding Wang, and Tian-Tsong.
Image Forgery Detection by Gamma Correction Differences.
8-1 Quality Improvement and Statistics Definitions of Quality Quality means fitness for use - quality of design - quality of conformance Quality is.
CS 223B Assignment 1 Help Session Dan Maynes-Aminzade.
Object Recognition Using Geometric Hashing
Smart Traveller with Visual Translator for OCR and Face Recognition LYU0203 FYP.
CSE 803 Fall 2008 Stockman1 Veggie Vision by IBM Ideas about a practical system to make more efficient the selling and inventory of produce in a grocery.
Almost all diagnosis of diseases made by medical professionals can not be approved without blood analysis. In medical world the rapid.
Digital Photography White Balance RAW vs. JPEG Resolution & Megapixels Camera Settings.
Restricted © Siemens AG 2013 All rights reserved.siemens.co.uk/education Topic 4: I can see clearly now Siemens Education.
Computer Vision Spring ,-685 Instructor: S. Narasimhan Wean Hall 5409 T-R 10:30am – 11:50am.
September 10, 2012Introduction to Artificial Intelligence Lecture 2: Perception & Action 1 Boundary-following Robot Rules 1  2  3  4  5.
Costs of Ancillary Services & Congestion Management Fedor Opadchiy Deputy Chairman of the Board.
G52IIP, School of Computer Science, University of Nottingham What we will learn … Topics relate to the use of computer to Acquire/generate Process/manipulate/store.
Perception Introduction Pattern Recognition Image Formation
MISD Architecture of Specialized Processors in FPGA Structures for a Real-Time Video Data Pre-processing Kazimierz Wiatr Institute of Electronics, AGH.
Video Based Palmprint Recognition Chhaya Methani and Anoop M. Namboodiri Center for Visual Information Technology International Institute of Information.
Reconstructing shredded documents through feature matching Authors: Edson Justino, Luiz S. Oliveira, Cinthia Freitas Source: Forensic Science International.
An Efficient Search Strategy for Block Motion Estimation Using Image Features Digital Video Processing 1 Term Project Feng Li Michael Su Xiaofeng Fan.
CS654: Digital Image Analysis Lecture 25: Hough Transform Slide credits: Guillermo Sapiro, Mubarak Shah, Derek Hoiem.
GMDH Application for autonomous mobile robot’s control system construction A.V. Tyryshkin, A.A. Andrakhanov, A.A. Orlov Tomsk State University of Control.
CONTENTS INTRODUCTION TO A.I. WORKING OF A.I. APPLICATIONS OF A.I. CONCLUSIONS ON A.I.
COMP322/S2000/L171 Robot Vision System Major Phases in Robot Vision Systems: A. Data (image) acquisition –Illumination, i.e. lighting consideration –Lenses,
Computing Simulation in Orders Based Transparent Parallelizing Pavlenko Vitaliy Danilovich, Odessa National Polytechnic University Burdeinyi Viktor Viktorovych,
Logarithmic Image Processing (LIP) By Ben Weisenbeck Oiki Wong.
Artificial Intelligence, Expert Systems, and Neural Networks Group 10 Cameron Kinard Leaundre Zeno Heath Carley Megan Wiedmaier.
: TiM551 – Ranging Laser Scanner Incredibly good at detection - absolutely accurate at measuring Aaron Rothmeyer.
Counting windows Project participants (in alphabetical order): Akif Durdu Middle East Technical University, Turkiye Viktor Jónás Budapest Polytechnic,
Danish Institute of Agricultural Sciences Henning T. Søgaard Dept of Agricultural Engineering A New Project Build and.
Robodog Frontal Facial Recognition AUTHORS GROUP 5: Jing Hu EE ’05 Jessica Pannequin EE ‘05 Chanatip Kitwiwattanachai EE’ 05 DEMO TIMES: Thursday, April.
TECHNOLOGY OF ELECTRONIC EMERGENCY INSTRUCTION CREATION Agafonov D.V. Institute of Nuclear Energy (branch of Saint-Petersburg State Polytechnic University)
The article written by Boyarshinova Vera Scientific adviser: Eltyshev Denis THE USE OF NEURO-FUZZY MODELS FOR INTEGRATED ASSESSMENT OF THE CONDITIONS OF.
Shadow Detection in Remotely Sensed Images Based on Self-Adaptive Feature Selection Jiahang Liu, Tao Fang, and Deren Li IEEE TRANSACTIONS ON GEOSCIENCE.
Tobias Kohoutek Institute of Geodesy and Photogrammetry Geodetic Metrology and Engineering Geodesy ANALYSIS AND PROCESSING OF 3D-IMAGE-DATA FOR ROBOT MONITORING.
1. 2 What is Digital Image Processing? The term image refers to a two-dimensional light intensity function f(x,y), where x and y denote spatial(plane)
Coin Recognition Using MATLAB - Emad Zaben - Bakir Hasanein - Mohammed Omar.
IMAGE PROCESSING is the use of computer algorithms to perform image process on digital images   It is used for filtering the image and editing the digital.
Visual Information Processing. Human Perception V.S. Machine Perception  Human perception: pictorial information improvement for human interpretation.
7 Design of Work Systems.
Heechul Han and Kwanghoon Sohn
Automatic Speed Control Using Distance Measurement By Single Camera
Introduction to Methods Engineering
«Crowdsourcing and the Effectiveness of C2G Interaction in Russia»
FINGER PRINT RECOGNITION USING MINUTIAE EXTRACTION FOR BANK LOCKER SECURITY Presented by J.VENKATA SUMAN ECE DEPARTMENT GMRIT, RAJAM.
Comparing NARF and SIFT Key Point Extraction Algorithms
Submitted by: Ala Berawi Sujod Makhlof Samah Hanani Supervisor:
Digital image self-adaptive acquisition in medical x-ray imaging
Global Market Insights, Inc.
Common Classification Tasks
New horizons in the artificial vision
4.2 Data Input-Output Representation
Presenter by : Mourad RAHALI
Automatic analysis of biological images
Soft Computing for Customer Service
An Infant Facial Expression Recognition System Based on Moment Feature Extraction C. Y. Fang, H. W. Lin, S. W. Chen Department of Computer Science and.
Grey Level Enhancement
Sampling Techniques Statistics.
Presentation transcript:

THE TECHNICAL VISION SYSTEM FOR DIAGNOSIS OF THE HARVESTING UNIT OF THE ROBOT FOR GATHERING WILD PLANTS A.I. Kuznetsov, A.V. Tyryshkin National Research Tomsk Polytechnic University Department of Control Systems and Mechatronics Tomsk, Russia kuznteh@gmail.com 2017

Topicality Advantages of using robots in agriculture: productivity increase; cost reduction; reduction of labor intensity of service; improving the quality of products.

Fig.1. Prognosis of dynamics of the market of agricultural robots Topicality Fig.1. Prognosis of dynamics of the market of agricultural robots

Topicality Reserves of cranberry marshes of Tomsk region more 10 million tons Manually collects no more than 15% of the entire crop. The use of robots promises increased collection efficiency.

Topicality The collection unit can often fail. In the event of a malfunction, the robot will continue to move, but the cranberries will not be collected. The diagnostic system will prevent the work from being "idle".

Review of existing solutions Fig.2.AGROBOT HUELVA SW6010 Fig.3. Octinion Fig.4. Shibuya Seiki Fig.5. BoniRob All existing systems are designed to work in artificial conditions.

Goals and objectives Main idea: create diagnosis system for solving problem controlling the operation of harvesting unit. Function: diagnosis of the harvesting unit determination of the efficiency of berry picking; increase the convenience of servicing the robot; improving the robot's economy. Goals: choose of the principle of the system; choose of the realization method; development of the work algorithm; realization of the algorithm; debugging and adjustment.

Choose of the principle of the system Monitoring the details Control of the main function Benefits: simplicity of the diagnostic algorithm; completeness of information about the state of the parts of the node. Benefits: tolerance to various design options; the possibility of collecting statistical data; lack of direct contact with responsible details; ease of installation and transfer of the system.

Choose of the realization method Main function of harvesting unit is – decrease in the number of berries

Figure of the proposed solution Computer Harvesting unit Autonomous platform Camera №1 Camera №2 Fig.6. Harvesting robot

Development of the work algorithm Main functions: determination of the malfunction of the harvesting unit; determining the efficiency of the harvesting unit; control zones without berries; setting the parameters of the recognized berries; setting options for displaying error messages.

Algorithm Fig.7. Block diagram

Development of the function of recognition and counting of berries One of the main distinctive features of cranberries is the color.

Development of the function of recognition and counting of berries Fig.8. Dependence of the color of the berries on different lighting conditions

Setting cranberry options Select a sample of the berries from the photo. Select a color sample from the tone ruler.

Development of the function of recognition and counting of berries Fig.9. Recognition results for a given color

Development of the function of recognition and counting of berries Fig.10. The graph of the dependence of the amount of the recognized berries on the size of the color range of the berries

Development of the function of recognition and counting of berries

Development of the function of recognition and counting of berries Noises: presence of parasitic objects of similar color; complex lighting conditions that require a larger range of berry color.

Development of the function of recognition and counting of berries A contour is a line that delimits an object and characterizes its shape. Border - the place of sharp changes in color, brightness or other color coordinates.

Development of the function of recognition and counting of berries Выделение границ с использованием контрастности Fig.11. Searching for borders on image with transformation by the Laplace operator

Methods of preprocessing Fig.12. Contrast Fig.13. Sharpness

Methods of preprocessing Fig.14. Searching for borders with contrast preprocessing Fig.15. Searching for borders with sharpness preprocessing

Development of the function of recognition and counting of berries To determine the conformity of the form, the Hafa transformation method is used.

Development of the function of recognition and counting of berries

Service information The average efficiency factor is used. Finding zones without berries. Fig.16. Service information

Advantages Simplify the maintenance of the robot. Increase the working time. Access to statistical indicators. Savings of money due to the lack of a permanent operator.

Conclusion A system for diagnosing of the harvesting unit of the robot for gathering wild plants was developed. Algorithms for detecting and counting cranberries in the image are created. Complex external conditions are taken into account. The output of service information

THANK YOU FOR ATTENTION A.I. Kuznetsov, A.V. Tyryshkin National Research Tomsk Polytechnic University Department of Control Systems and Mechatronics Tomsk, Russia kuznteh@gmail.com 2017