4th European Micro-UAV Meeting Sept , 2004

Slides:



Advertisements
Similar presentations
OpenCV Introduction Hang Xiao Oct 26, History  1999 Jan : lanched by Intel, real time machine vision library for UI, optimized code for intel 
Advertisements

Joshua Fabian Tyler Young James C. Peyton Jones Garrett M. Clayton Integrating the Microsoft Kinect With Simulink: Real-Time Object Tracking Example (
Learning Techniques for Video Shot Detection Under the guidance of Prof. Sharat Chandran by M. Nithya.
Automated Shot Boundary Detection in VIRS DJ Park Computer Science Department The University of Iowa.
Activity Recognition Aneeq Zia. Agenda What is activity recognition Typical methods used for action recognition “Evaluation of local spatio-temporal features.
F ACE TRACKING EE 7700 Name: Jing Chen Shaoming Chen.
InteractIVe Summer School, July 6 th, 2012 Grid based SLAM & DATMO Olivier Aycard University of Grenoble 1 (UJF), FRANCE
Chapter 8. Basic Image Process The visual information can be recorded by a TV camera or a 2D array of CCD sensors. A digital image is formed.
Computer and Robot Vision I
Computer Vision REU Week 2 Adam Kavanaugh. Video Canny Put canny into a loop in order to process multiple frames of a video sequence Put canny into a.
Vehicle-Infrastructure-Driver Interactions Research Unit
IEEE TCSVT 2011 Wonjun Kim Chanho Jung Changick Kim
ICME 2008 Huiying Liu, Shuqiang Jiang, Qingming Huang, Changsheng Xu.
3. Introduction to Digital Image Analysis
CS 561, Sessions 27 1 Towards intelligent machines Thanks to CSCI561, we now know how to… - Search (and play games) - Build a knowledge base using FOL.
Vision Computing An Introduction. Visual Perception Sight is our most impressive sense. It gives us, without conscious effort, detailed information about.
On the Use of Computable Features for Film Classification Zeeshan Rasheed,Yaser Sheikh Mubarak Shah IEEE TRANSCATION ON CIRCUITS AND SYSTEMS FOR VIDEO.
SWE 423: Multimedia Systems Chapter 5: Video Technology (1)
Computer Vision for Interactive Computer Graphics Mrudang Rawal.
Using spatio-temporal probabilistic framework for object tracking By: Guy Koren-Blumstein Supervisor: Dr. Hayit Greenspan Emphasis on Face Detection &
A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE.
1 Motion in 2D image sequences Definitely used in human vision Object detection and tracking Navigation and obstacle avoidance Analysis of actions or.
GENERIC VISUAL PERCEPTION PROCESSOR
1 Debris flow velocity estimation: A comparison between gradient- based method and cross- correlation method Image Processing: Algorithms and Systems (Proceedings.
CMUcam Tom Kneeland. CMUcam – What is it? Digital Camera with an onboard microcontroller Track a blob based on programmable color thresholds Calculate.
Ahmed Abdel-Fattah Jerry Chang Derrick Culver Matt Zenthoefer.
Real Time Abnormal Motion Detection in Surveillance Video Nahum Kiryati Tammy Riklin Raviv Yan Ivanchenko Shay Rochel Vision and Image Analysis Laboratory.
Prepared by: - Mr. T.R.Shah, Lect., ME/MC Dept., U. V. Patel College of Engineering. Ganpat Vidyanagar. Digital Image Processing & Machine Vision – An.
Computer Science Department, Duke UniversityPhD Defense TalkMay 4, 2005 Fast Extraction of Feature Salience Maps for Rapid Video Data Analysis Nikos P.
JPEG 2000 Image Type Image width and height: 1 to 2 32 – 1 Component depth: 1 to 32 bits Number of components: 1 to 255 Each component can have a different.
ECE 472/572 - Digital Image Processing Lecture 4 - Image Enhancement - Spatial Filter 09/06/11.
CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young.
L29:Lower Power Embedded Architecture Design 성균관대학교 조 준 동 교수,
A Brief Overview of Computer Vision Jinxiang Chai.
Image Processing Lecture 2 - Gaurav Gupta - Shobhit Niranjan.
Video Classification By: Maryam S. Mirian
Fast Approximate Energy Minimization via Graph Cuts
Vision-based parking assistance system for leaving perpendicular and angle parking lots 2013/12/17 指導教授 : 張元翔 老師 研究生 : 林柏維 通訊碩一
SPIE'01CIRL-JHU1 Dynamic Composition of Tracking Primitives for Interactive Vision-Guided Navigation D. Burschka and G. Hager Computational Interaction.
Dr A VENGADARAJAN, Sc ‘F’, LRDE
CIS 601 Fall 2003 Introduction to Computer Vision Longin Jan Latecki Based on the lectures of Rolf Lakaemper and David Young.
CSC 461: Lecture 3 1 CSC461 Lecture 3: Models and Architectures  Objectives –Learn the basic design of a graphics system –Introduce pipeline architecture.
Introduction EE 520: Image Analysis & Computer Vision.
1 Introduction to Computer Graphics with WebGL Ed Angel Professor Emeritus of Computer Science Founding Director, Arts, Research, Technology and Science.
1Computer Graphics Lecture 4 - Models and Architectures John Shearer Culture Lab – space 2
Recognizing Action at a Distance Alexei A. Efros, Alexander C. Berg, Greg Mori, Jitendra Malik Computer Science Division, UC Berkeley Presented by Pundik.
Advances in digital image compression techniques Guojun Lu, Computer Communications, Vol. 16, No. 4, Apr, 1993, pp
1 Research Question  Can a vision-based mobile robot  with limited computation and memory,  and rapidly varying camera positions,  operate autonomously.
Chapter 5 Multi-Cue 3D Model- Based Object Tracking Geoffrey Taylor Lindsay Kleeman Intelligent Robotics Research Centre (IRRC) Department of Electrical.
Choosing the Appropriate Camera “Resolving” the Application.
Visual Computing Computer Vision 2 INFO410 & INFO350 S2 2015
Video Tracking G. Medioni, Q. Yu Edwin Lei Maria Pavlovskaia.
1 Machine Vision. 2 VISION the most powerful sense.
Motion Detection Frame 1Frame 2 Anomalous activity.
Presenter: Jae Sung Park
Submitted To: Submitted By: Seminar On 8086 Microprocessors.
Tobias Kohoutek Institute of Geodesy and Photogrammetry Geodetic Metrology and Engineering Geodesy ANALYSIS AND PROCESSING OF 3D-IMAGE-DATA FOR ROBOT MONITORING.
Image Perception ‘Let there be light! ‘. “Let there be light”
Digital Video Library - Jacky Ma.
Automatic Video Shot Detection from MPEG Bit Stream
A Forest of Sensors: Using adaptive tracking to classify and monitor activities in a site Eric Grimson AI Lab, Massachusetts Institute of Technology
Human Vision Nov Wu Pei.
Outline Image formats and basic operations Image representation
Eric Grimson, Chris Stauffer,
Introduction to Game Development
Image processing and computer vision
Estimation of Skin Color Range Using Achromatic Features
Image segmentation Grey scale image Binary image
Problem Image and Volume Segmentation:
Lark Kwon Choi, Alan Conrad Bovik
Presentation transcript:

4th European Micro-UAV Meeting Sept. 15-17, 2004 Generic Visual Perception Processor GVPP www.gvpp.org

Topic Generic Visual Perception Processor Real time processing CAMERA Action 4 adaptive properties Real time processing Detect persons, objects and events by temporal coincidence with unsupervised collective decision Track persons and objects in the image with anticipation of their motions Learning by example.

Understanding Introduction Perception GVPP Imaging processing Action Imaging processing Perception Understanding Action Power IP GVPP Nb. frames/seconds

Method - 1 Method - 1

Method - 2

Method - 3

Method - 4

Histogram Registers RMAX RMAX/2 NBPTS MIN POSMOY POSRMX MAX

A generic Spatio-Temporal Neuron STN block API REG Registers API Bus par. Time-Coincidences Bus PARAM Reg. FoG D F: automatic Classification G: Anticipation

Self Action STN MVT STN X-Y FoG Z NBPTS Initial ROI Final ROI TEMPORAL DOMAIN SPATIAL DOMAIN WHAT and WHERE* STN MVT STN X-Y FoG Z MOTION NBPTS Initial ROI Final ROI

Motion Perception

Self Organization - 1 Motion Perception

Self Organization - 2 Recruitment Color Analysis

Self Organization - 3 Main Color Found Inhibition No Main Color Analysis On the Main Area Tree generation For Labeling

Self Organization - 4 Improvement

Self Organization - 5 Face Organization Labeled and learned Perception/Synthesis

Eyes Tracking

Generic Visual Perception Processor

GVPP – System on a Chip

A LONG STORY 1986 2000 One statistic computation One System on Chip with 23 statistics computations

2004 GVPP7-B

ANTICIPATION

Lines Perception

EDGE ORIENTATION FLOW

CURVES FLOW

Horizon Perception

STABILIZATION

Automotive Application

Game on TV

GVPP7-B

PRELIMINARY INFORMATION Array Format (max): 800Hx600V max Frame Rate: 0-100 VGA frames per second progressive-scan Interface Mode: Master/Slave Data Rate (max): 40 mega pixel per second Dynamic Range: 10-bits Parameters: Luminance, Hue, Saturation, Motion (orientation, velocity), Spatial lines orientation,curves,corners Computation: 64 STN blocks Multi-scales possibilities Internal OS C language 0.5 Watt 3.3 Volts @ 13.5MHz Interface: PCI, I2C, RS232

GVPP road map

The Robotic Future

www.gvpp.org Thanks you for your attention