Scribd
Upload
3 views

0. Computer Vision - Lecture Introduction

Uploaded by

hòa trịnh
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
3 views

0. Computer Vision - Lecture Introduction

Uploaded by

hòa trịnh
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 33

COMPUTER VISION

Le Thanh Ha, Ph.D


Assoc. Prof. at University of Engineering and Technology,
Vietnam National University
[email protected]; [email protected]; 0983 692 592
About myself
• Full name: Le Thanh Ha

• 2005-2010: Ph.D at Korea University, Korea


• 2010-now:
– Assoc. Prof. at University of Engineering and Technology (UET), VNUH
– Head of Human Machine Interaction Laboratory

• Expertise: Computer vision, Image/video processing and analysis,


Machine learning

2/6/2023 Le Thanh Ha, Lab of HMI 2


HMI Laboratory

Human Machine Interface

Interaction

Integration

Intelligence

2/6/2023 Le Thanh Ha, Lab of HMI 3


Workgroups

Computer
Computer
vision and
graphics
video analysis

https://hmiuet.wordpress.com

Video coding Natural


and language
communication processing

2/6/2023 Le Thanh Ha, Dr., Lab. of HMI 4


Digital Image Processing and Computer Vision
• Low-level process: Digital Image
• Inputs and outputs are images. Processing
• Noise reduction, contrast enhancement, …

• Mid-level process:
• Extract attributs from images.
• Segmentation, single object recog., …

• High-level process
• Perform cognitive functions Computer
Vision
2/6/2023 Le Thanh Ha, Lab of HMI 5
What is computer vision?
• Make computers understand images and video.

What kind of scene?

Where is the buffalo?

How far is the house?

2/6/2023 Le Thanh Ha, Dr., Lab. of HMI 6


What is computer vision?

• How many flowers?

• What is the pup thinking?

2/6/2023 Le Thanh Ha, Dr., Lab. of HMI 7


What is computer vision?
• Is there anyway to reconstruct the 3D
structure of this building?

2/6/2023 Le Thanh Ha, Dr., Lab. of HMI 8


Vision is really hard
• Vision is an amazing feat of natural intelligence

– Human receive more than 80% information coming from visual system

– More human brain devoted to vision than anything else


Computer vision topics
• Virtual & Augmented Reality
• Biometric
• Object detection
• Optical Character Recognition
• Image video segmentation
• Scene understanding
• Image generation
• …

2/6/2023 Le Thanh Ha, Lab of HMI 10


Computer vision matters

Safety Health Security

Comfort Fun Access


Two reasons for computer vision

Household Robots Assisted Driving


Let’s see

Real applications of computer vision

2/6/2023 Le Thanh Ha, Dr., Lab. of HMI 13


Earth viewers (3D modeling)

Image from Google Earth


3D from thousands of images

Building Rome in a Day: Agarwal et al. 2009


Optical character recognition (OCR)
Technology to convert scanned docs to text
• If you have a scanner, it probably came with OCR software

Digit recognition, AT&T labs License plate readers


http://www.research.att.com/~yann/ http://en.wikipedia.org/wiki/Automatic_number_plate_recognition
Face detection

• Many new digital cameras now detect faces


– Canon, Sony, Fuji, …
Smile detection?

Sony Cyber-shot® T70 Digital Still Camera


Object recognition (in supermarkets)

LaneHawk by EvolutionRobotics
“A smart camera is flush-mounted in the checkout lane, continuously watching
for items. When an item is detected and recognized, the cashier verifies the
quantity of items that were found under the basket, and continues to close the
transaction. The item can remain under the basket, and with LaneHawk,you are
assured to get paid for it… “
Vision-based biometrics

“How the Afghan Girl was Identified by Her Iris Patterns” Read the story
wikipedia
Login without a password…

Face recognition systems now beginning


Fingerprint scanners on
to appear more widely
many new laptops, http://www.sensiblevision.com/
other devices
Object recognition (in mobile phones)

Point & Find, Nokia


Google Goggles
Smart cars

• Mobileye
– Vision systems currently in many high-end
models
http://mobileye.com/technology/applications/vehicle-detection/forward-colision-warning/
http://mobileye.com/technology/applications/pedestrian-detection/pedestrian-collision-warning/
Google cars

Oct 9, 2010. "Google Cars Drive Themselves, in Traffic". The New York Times. John Markoff
June 24, 2011. "Nevada state law paves the way for driverless cars". Financial Post.
Christine Dobby
Aug 9, 2011, "Human error blamed after Google's driverless car sparks five-vehicle
crash". The Star (Toronto)
Interactive Games: Kinect
• Object Recognition: http://www.youtube.com/watch?feature=iv&v=fQ59dXOo63o
• Mario: http://www.youtube.com/watch?v=8CTJL5lUjHg
• 3D: http://www.youtube.com/watch?v=7QrnwoO1-8A
• Robot: http://www.youtube.com/watch?v=w8BmgtMKFbY
Vision in space

Landing Site Panorama, with the Heights of Mount Sharp, taken by Curiosity on August 27,
2012.

Vision systems (JPL) used for several tasks


• Panorama stitching
• 3D terrain modeling
• Obstacle detection, position tracking
Industrial robots

Vision-guided robots position nut runners on wheels


Mobile robots

NASA’s Mars Curiosity


http://mars.jpl.nasa.gov/msl/mission/overview/ http://www.robocup.org/

Saxena et al. 2008 http://www.youtube.com/w


STAIR at Stanford
atch?v=DF39Ygp53mQ
Medical imaging

Image guided surgery


3D imaging
Grimson et al., MIT
MRI, CT
Content
1. Human visual system
2. Image formation
3. Early vision: Just one image
4. Early vision: Multiple images
5. Middle-level vision
6. High-level vision
7. Application and topics

2/6/2023 Le Thanh Ha, Dr., Lab. of HMI 30


Course projects
- Small projects will be given to individual or a group.
- Our topics are mainly related with AI applications for surveillance
cameras
- Students have to do the given project and make a presentation:
+ PPT Slide and presentation
+ Making report
+ Implementation

2/6/2023 Le Thanh Ha, Dr., Lab. of HMI 31


Textbook
• Textbook: “Computer Vision: A Modern Approach”, Forsyth,
Ponce, 2011.

• Related book: “Digital Image Processing”, R. C. Gonzalez, R. E.


Woods, Third Edition.

2/6/2023 Le Thanh Ha, Dr., Lab. of HMI 32


Course Evaluation
• Assignment: 10%
• Attendance: Every lecture at the beginning
• Project: 30%
• Final exam: 60%

2/6/2023 Le Thanh Ha, Dr., Lab. of HMI 33

You might also like