Duo: Towards a Wearable System that Learns about Everyday Objects and Actions Charles C. Kemp MIT CSAIL ● Goal: help machines learn an important form of.

Slides:



Advertisements
Similar presentations
SETTING UP A PROJECT Adobe Premiere Pro CS6. Getting started… Adobe Premiere Pro project file stores links to all the video and sound files-aka…clips.
Advertisements

Kien A. Hua Division of Computer Science University of Central Florida.
Analysis of Contour Motions Ce Liu William T. Freeman Edward H. Adelson Computer Science and Artificial Intelligence Laboratory Massachusetts Institute.
Real-time, low-resource corridor reconstruction using a single consumer grade RGB camera is a powerful tool for allowing a fast, inexpensive solution to.
Perception and Perspective in Robotics Paul Fitzpatrick MIT Computer Science and Artificial Intelligence Laboratory Humanoid Robotics Group Goal To build.
Tracking Learning Detection
Introduction To Tracking
3/5/2002Phillip Saltzman Video Motion Capture Christoph Bregler Jitendra Malik UC Berkley 1997.
Vision Based Control Motion Matt Baker Kevin VanDyke.
Real Time Motion Capture Using a Single Time-Of-Flight Camera
Introduction to Data-driven Animation Jinxiang Chai Computer Science and Engineering Texas A&M University.
Personal Driving Diary: Constructing a Video Archive of Everyday Driving Events IEEE workshop on Motion and Video Computing ( WMVC) 2011 IEEE Workshop.
Supervised by Prof. LYU, Rung Tsong Michael Department of Computer Science & Engineering The Chinese University of Hong Kong Prepared by: Chan Pik Wah,
LYU 0102 : XML for Interoperable Digital Video Library Recent years, rapid increase in the usage of multimedia information, Recent years, rapid increase.
Automatic Camera Calibration for Image Sequences of a Football Match Flávio Szenberg (PUC-Rio) Paulo Cezar P. Carvalho (IMPA) Marcelo Gattass (PUC-Rio)
WP -6: Human Tracking and Modelling Year–I Objectives: Simple upper-body models and articulated tracks from test videos. Year-I Achievements: Tracking.
I mage and M edia U nderstanding L aboratory for Performance Evaluation of Vision-based Real-time Motion Capture Naoto Date, Hiromasa Yoshimoto, Daisaku.
Carlo Tomasi, Computer Science. Human Vision Computer Vision?
1 7M836 Animation & Rendering Animation Jakob Beetz Joran Jessurun
RAGEEVGANDHI MEMORIAL COLLEGE OF ENGINEERING AND TECHNOLOGY
A Brief Overview of Computer Vision Jinxiang Chai.
Smartphone Overview iPhone 4 By Anthony Poland 6 Nov 2014.
CS 376b Introduction to Computer Vision 04 / 29 / 2008 Instructor: Michael Eckmann.
The Whole World in Your Hand: Active and Interactive Segmentation The Whole World in Your Hand: Active and Interactive Segmentation – Artur Arsenio, Paul.
PortableVision-based HCI A Hand Mouse System on Portable Devices 連矩鋒 (Burt C.F. Lien) Computer Science and Information Engineering Department National.
Presentation by: K.G.P.Srikanth. CONTENTS  Introduction  Components  Working  Applications.
Characterizing activity in video shots based on salient points Nicolas Moënne-Loccoz Viper group Computer vision & multimedia laboratory University of.
Speaker : Meng-Shun Su Adviser : Chih-Hung Lin Ten-Chuan Hsiao Ten-Chuan Hsiao Date : 2010/01/26 ©2010 STUT. CSIE. Multimedia and Information Security.
A General Framework for Tracking Multiple People from a Moving Camera
A Method for Hand Gesture Recognition Jaya Shukla Department of Computer Science Shiv Nadar University Gautam Budh Nagar, India Ashutosh Dwivedi.
Submitted by:- Vinay kr. Gupta Computer Sci. & Engg. 4 th year.
CSCE 5013 Computer Vision Fall 2011 Prof. John Gauch
Dynamic 3D Scene Analysis from a Moving Vehicle Young Ki Baik (CV Lab.) (Wed)
Towards real-time camera based logos detection Mathieu Delalandre Laboratory of Computer Science, RFAI group, Tours city, France Osaka Prefecture Partnership.
Visual Tracking on an Autonomous Self-contained Humanoid Robot Mauro Rodrigues, Filipe Silva, Vítor Santos University of Aveiro CLAWAR 2008 Eleventh International.
November 13, 2014Computer Vision Lecture 17: Object Recognition I 1 Today we will move on to… Object Recognition.
Trends in Embedded Computing The Ubiquitous Computing through Sensor Swarms.
Vision-based human motion analysis: An overview Computer Vision and Image Understanding(2007)
December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.
Natural Tasking of Robots Based on Human Interaction Cues Brian Scassellati, Bryan Adams, Aaron Edsinger, Matthew Marjanovic MIT Artificial Intelligence.
12/7/10 Looking Back, Moving Forward Computational Photography Derek Hoiem, University of Illinois Photo Credit Lee Cullivan.
Action and Gait Recognition From Recovered 3-D Human Joints IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS— PART B: CYBERNETICS, VOL. 40, NO. 4, AUGUST.
Efficient Visual Object Tracking with Online Nearest Neighbor Classifier Many slides adapt from Steve Gu.
Teleoperation In Mixed Initiative Systems. What is teleoperation? Remote operation of robots by humans Can be very difficult for human operator Possible.
Object Recognition in ROS Using Feature Extractors and Feature Matchers By Dolev Shapira.
CONTENT 1. Introduction to Kinect 2. Some Libraries for Kinect 3. Implement 4. Conclusion & Future works 1.
Workshop - November Toulouse (SoC toolKit for critical Embedded sysTems) Thales Use Case: Pedestrian tracking with smart cameras SoCKET Collaborative.
1 Machine Vision. 2 VISION the most powerful sense.
Semantic Extraction and Semantics-Based Annotation and Retrieval for Video Databases Authors: Yan Liu & Fei Li Department of Computer Science Columbia.
Target Tracking In a Scene By Saurabh Mahajan Supervisor Dr. R. Srivastava B.E. Project.
Alan Cleary ‘12, Kendric Evans ‘10, Michael Reed ‘12, Dr. John Peterson Who is Western State? Western State College of Colorado is a small college located.
Narration/dialogue: Camera motion: Video effect: Audio effect: Shot duration: Transition to next scene: Storyboard Panel #
Face Recognition Technology By Catherine jenni christy.M.sc.
3D Motion Classification Partial Image Retrieval and Download Multimedia Project Multimedia and Network Lab, Department of Computer Science.
AN ACTIVE VISION APPROACH TO OBJECT SEGMENTATION – Paul Fitzpatrick – MIT CSAIL.
ENTERFACE 08 Project 9 “ Tracking-dependent and interactive video projection ” Mid-term presentation August 19th, 2008.
CHAPTER 8 Sensors and Camera. Chapter objectives: Understand Motion Sensors, Environmental Sensors and Positional Sensors Learn how to acquire measurement.
Over the recent years, computer vision has started to play a significant role in the Human Computer Interaction (HCI). With efficient object tracking.
Manipulation in Human Environments
REAL-TIME DETECTOR FOR UNUSUAL BEHAVIOR
Visual Information Retrieval
Design and Implementation of versatile ebot using raspberry pi
Tracking parameter optimization
Manipulation in Human Environments
Detecting Room Occupancy with Pi Camera
Learning about Objects
M ND: Music Improvisation and Narrative Design
Data Science with Python
Progress Review.
Object Recognition Today we will move on to… April 12, 2018
Presentation transcript:

Duo: Towards a Wearable System that Learns about Everyday Objects and Actions Charles C. Kemp MIT CSAIL ● Goal: help machines learn an important form of commonsense in pursuit of better AI ● wearable first person video and motion capture ● segmentation based perception ● online and offline methods for processing and annotation

The Platform

● Hardware Infrastructure – four Intersense gyros provide absolute orientation information (they use acceleration, gravity, and earth's magnetic field) which is sufficient to model the kinematic chain from the camera to the hand – 8+ hours of battery life and hard disk space – firewire camera, standard laptop ● Software Infrastructure – Python with C++ and Swig ● interpreted high-level code for fast development ● C++/C for speed when necessary – GNU/Linux, Debian testing – SQLite 3.0 – Many Libre libraries (twisted, numarray, opencv, glade,...)

In our initial application, the human and the wearable cooperated to acquire segmentations of the objects with which the person interacted (see below). This approach used active illumination and cooperation, we are now working on more general methods, which we describe in this poster. (presented at Humanoids 2003)

The kinematic segmentation algorithm breaks actions at local minima of multi-scale smoothed hand speed estimates. These segments can serve as the units of search for detection, recognition and learning. They can also be used to summarize scenes for annotation and browsing, such as with this summarized 120 frame sequence.

The visual segmentation system initializes visual segments around the kinematically estimated hand location, tracks the segments, and filters them.

hand at rest hand reaching hand carrying Clustering performed on the hand positions at the detected transitions between action segments (local minima in hand speed), results in clusters that correspond with significant hand states.

Detect and track known visual segments

Annotation Software for visual segments for action segments for browsing the database