Bio-inspired Active Vision System


Published on

Presentation of active vision system developed by Martin Peniak during his stay at NVIDIA research in 2012.

GPU Technology Conference 2013

Published in: Technology
1 Like
  • Be the first to comment

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Bio-inspired Active Vision System

  1. 1. Bio-inspired Active VisionMartin Peniak, Davide Marocco, Ron Babich and John Tran
  2. 2. Outline Introduction Classical vision vs. active vision Show few examples, e.g. template matching, face detection etc. Pros&Cons Explain what is active perception (use current + davides slides) Active Vision – many possibilities but we like GA+NN, why? Based on neural network and genetic algorithm What is neural network? What is genetic algorithm? Pros&Cons Little computation required due to neural network architecture, fast No external representation needed thanks to GA evolving nn weights Generality, invariance, and application in multiple domains Cons: need more research, so far applied in limited domains Previous research by Floreano, Davide, me (ESA) Show videos and pictures Describe work done at NVIDIA Future work: AXA grant 2
  3. 3. GPU Computing Lab
  4. 4. Traditional Computer Vision 4
  5. 5. Traditional Computer Vision“Teaching a computer to classify objects has proved much harder than was originally anticipated”Thomas Serre - Center for Biological and Computational Learning at MIT Specific template or computational representation is required to allow object recognition Must be flexible enough to account with all kinds of variations 5
  6. 6. Biological Vision“Researchers have been interested for years in trying to copy biological vision systems,simply because they are so good” ~ David Hogg - computer vision expert at Leeds University, UK Highly optimized over millions of years of evolution, developing complex neural structures to represent and process stimuli Superiority of biological vision systems is only partially understood Hardware architecture and the style of computation in nervous systems are fundamentally different 6
  7. 7. Biological Vision 7
  8. 8. Seeing is a way of acting 8
  9. 9. Active Vision Inspired by the vision systems of natural organisms that have been evolving for millions of years In contrast to standard computer vision systems, biological organisms actively interact with the world in order to make sense of it Humans and also other animals do not look at a scene in fixed steadiness. Instead, they actively explore interesting parts of the scene by rapid saccadic movements 9
  10. 10. Creating Active Vision SystemsEvolutionary Robotics Approach 10
  11. 11. Evolutionary Robotics New technique for the automatic creation of autonomous robots Inspired by the Darwinian principle of selective reproduction of the fittest Views robots as autonomous artificial organisms that develop their own skills in close interaction with the environment and without human intervention Drawing heavily on biology and ethology, it uses the tools of neural networks, genetic algorithms, dynamic systems, and biomorphic engineering 11
  12. 12. Genetic Algorithms (GAs) are adaptive heuristic search algorithm premised on the evolutionary ideas of natural selection and genetic. The basic concept of GAs is ... designed to simulate processes in natural system necessary for evolution. Population (Chromosomes) ... ... Genetic Evaluation operators (Fitness)Artificial neural networks (ANNs) are very powerful brain-inspired Selection (Mating Pool)computational models, which have been used in many different 12areas such as engineering, medicine, finance, and many others.
  13. 13. Related ResearchMars Rover obstacle avoidance (Peniak et al.) 13
  14. 14. Related ResearchKoala robot obstacle avoidance (Marocco et al.) 14
  15. 15. Related ResearchAutonomous driving car (Floreano et al.) 15
  16. 16. Related ResearchObject recognition (Floreano et al.) 16
  17. 17. Going FurtherDesigning active vision system for real-world object recognition 17
  18. 18. TaskDesign active vision system that can learn to recognize thefollowing objects 18
  19. 19. Method Evolution of the active vision system for real-world object recognition training the system in a parallel manner on multiple objects viewed from many different angles and under different lighting conditions Amsterdam Library of Object Images (ALOI) provides a color image collection of one-thousand small objects recorded for scientific purposes systematically varied viewing angle, illumination angle, and illumination color Active Vision Training trained on a set of objects from the ALOI library each genotype is evaluated during multiple trials with different randomly rotated objects and under varying lighting conditions evolutionary pressure provided by a fitness function that evaluates overall success or failure of the object classification trained on increasingly larger number of objects Active Vision Testing robustness and resiliency of recognition of the dataset generalization to previously unseen instances of the learned objects 19
  20. 20. Experimental Setup Recurrent Neural Network Inputs: 8x8 neurons for retina, 2 neurons for proprioception (x,y pos) No hidden neurons Outputs: 5 object recognition neurons, 2 neurons to move retina (16px max) Genetic Algorithm Generations: 10000 Number of individuals: 100 Number of trials: 36+16 (object rotations + varying lighting conditions) Mutation probability: 10% Reproduction: best 20% of individuals create new population Elitism used (best individual is preserved) 20
  21. 21. Experimental Setup Each individual (neural network) could freely move the retina and read the input from the source image (128x128) for 20 steps At each step, neural network controlled the behavior of the system (retina position) and provide recognition output The recognition output neuron with the highest activation was considered the network’s guess about what the object was Fitness function = number of correct answers / number of total steps 21
  22. 22. GPU Accelerating GA and ANN GPUs were used to accelerate: Evolutionary process – parallel execution of trials Neural Network – parallel calculation of neural activities 22
  23. 23. Results Fitness can not reach 1.0 since it takes few time-steps to recognize an object All objects are correctly classified at the end of the each test 0.9 0.8 0.7 0.6 0.5 fitness 0.4 0.3 0.2 0.1 0 0 1000 2000 3000 4000 5000 6000 7000 8000 9000 10000 generations best fitness average fitness 23
  24. 24. Evolved Behavior 24
  25. 25. Future Work 25
  26. 26. "Imagination is the highest form of research" Albert Einstein Thank you! 26