Machine Learning and Robotic Vision
2 likes1,096 views
This document provides an overview of machine learning and robotic vision. It discusses what machine learning is, how it is used in areas like security, business and medicine. It also discusses what learning means and different machine learning techniques. For robotic vision, it discusses what a robot and vision are, the advantages of robots, how robotic vision works and examples of processing images. It provides an example of machine learning and discusses the development and future of robots.
Machine Learning and Robotic Vision
- 1. Machine Learning & robotic Visions Presented By: Nikesh Balami & Suraj Bohara
- 2. What is Machine Learning? “The goal of machine learning is to build computer systems that can adapt and learn from their experience.” Machine Learning is arguably the greatest export from computing to other scientific fields. Machine learning uses include: – Security (Pattern recognition, face recognition) – Business (Stocks, user behaviors) – Medical (Research)
- 3. What Is Learning? “Learning denotes changes in a system that ... enable a system to do the same task more efficiently the next time.” –Herbert Simon “Learning is constructing or modifying representations of what is being experienced.” –Ryszard Michalski “Learning is making useful changes in our minds.” –Marvin Minsky
- 5. Why Machine Learning Is Important? Relationships and correlations can be hidden within large amounts of data. Machine Learning/Data Mining may be able to find these relationships. Human designers often produce machines that do not work as well as desired in the environments in which they are used.
- 6. Why Machine Learning Is Important? Cont… The amount of knowledge available about certain tasks might be too large for explicit encoding by humans (e.g., medical diagnostic). New knowledge about tasks is constantly being discovered by humans. It may be difficult to continuously re-design systems “by hand”.
- 7. Some Success Stories Of Machine Learning Data Mining, Lerner in Web Analysis of astronomical data Human Speech Recognition Handwriting recognition Fraudulent Use of Credit Cards Drive Autonomous Vehicles Predict Stock Rates Robot Soccer
- 8. Machine Learning Techniques Decision tree learning Artificial neural networks Naive Bayes Bayesian Net structures Instance-based learning Reinforcement learning Genetic algorithms Support vector machines Explanation Based Learning Inductive logic programming
- 9. Designing a Learning System: An Example 1. Problem Description 2. Choosing the Training Experience 3. Choosing the Target Function 4. Choosing a Representation for the Target Function 5. Choosing a Function Approximation Algorithm 6. Final Design
- 10. Example Of Machine Learning
- 11. Finally!
- 12. Robotic Vision
- 13. What Is Vision? • Vision is our most powerful sense providing us with an enormous amount of information about our environment and enables us to interact intelligently with the environment • It is therefore not surprising that an enormous amount of effort has occurred to give machines a sense of vision • Vision is also our most complicated sense – Whilst we can reconstruct views with high resolution on photographic paper, understanding how the brain processes the information from our eyes is still in its infancy
- 14. Output Example:
- 15. What Is Robot? “A robot is a reprogrammable, multifunctional manipulator designed to move material, parts, tools, or specialized devices through variable programmed motions for the performance of a variety of tasks.” (Robot Institute of America) “A robot is a one-armed, blind idiot with limited memory and which cannot speak, see, or hear.”
- 16. What Is Robot? Cont… Robots are known to save costs, to improve quality and work conditions, and to minimize waste of resources. Robot-based production increases product quality, improves work conditions and leads to an optimized use of resources. Robots are expendable, so they can be deployed in disaster zones where it would be too dangerous for humans to go. They can be designed to cope with excessive heat, radiation and toxic chemicals.
- 18. Advantage Of Robots Ro bo ts may have be tte r pe rce ptio n se nso rs than humans. Using came ra, so nar or laser scanners, robots may be able to learn much more about their environment than a human ever could. Ro bo ts may be mo re mo bile than humans. Fo r e xample , sho e bo x-size d ro bo ts can fit into places where humans can not, or aerial robots can explore an environment from heights. Ro bo ts can be ve ry inte llig e nt. I llig e nt ag e nts and multi-ag e nt syste ms have become a very active nte area of research, and it is conceivable that robots will be able to make decisions faster and more intelligently than humans in the near future.
- 20. Forecast
- 21. Professional Use
- 22. Processing Pictures: Without the fluke board we can’t process pictures taken by the robot. However we can process regular .jpg files. Caution: Processing can take a long time so keep your pictures to 600 x 600 pixels. If you are just experimenting try to keep your pictures even smaller – 200x200 pixels.
- 23. Robot Vision The robot and our program don’t see purple, they each see a combination of red, green and blue. r,g,b = getColors(pixel) Colors with low values of red, green and blue are generally dark and with high values, generally light.
- 24. Fuzzy Logic
- 25. First Digital Cameras Photoelectric effect (Hertz 1887; Einstein 1905) Charge-coupled devices as storage (late 1960’s) Light sensing, pixel row readout (early 1970’s) First electronic CCD still- image camera (1975): Fairchild CCD element Resolution: 100 x 100 b&w Image capture time: 23 sec., mostly writing cassette tape Total weight: 8½ pounds
- 26. Modern Digital Cameras Now days, Certain amount of money can buys a camera with: – 640 x 480 pixel resolution at 30Hz – 1280 x 960 still image resolution – 24-bit RGB pixels (8 bits per channel) – Automatic gain control, color balancing – On-chip lossy compression algorithms – Uncompressed images if desired – Integrated microphone, USB interface – Limitations • Narrow dynamic range • Narrow FOV, with fixed spatial resolution • No motion / active vision capabilities
- 27. Any Question? ?
- 28. Thank you