Computer Vision for Mobile Robot Object Identification and Tracking - - PowerPoint PPT Presentation

▶

Sep 12, 2022 141 likes •389 views

Computer Vision for Mobile Robot Object Identification and Tracking Wael Abd-Almageed The Robotics, Artificial Intelligence, and Vision Laboratory Electrical and Computer Engineering Dept. University of New Mexico Albuquerque, New Mexico 87106

SLIDE 1

Computer Vision for Mobile Robot Object Identification and Tracking

Wael Abd-Almageed The Robotics, Artificial Intelligence, and Vision Laboratory Electrical and Computer Engineering Dept. University of New Mexico Albuquerque, New Mexico 87106 wamageed@eece.unm.edu

– p.1/23

SLIDE 2

In This Presentation

Overview.
Introduction.
Vision-Based Navigation.
Object Detection (or Segmentation)
Object Identification (or Classification.)

– p.2/23

SLIDE 3

Computer Vision Applications

Zip Code Recognition (USPS)
FBI Fingerprint Database
Image Stabilization
Autofocus

– p.3/23

SLIDE 4

Medical Imaging

Classification and Diagnosis
MRI Image Segmentation
Vision-Guided Surgery
Modeling and Visualization

– p.4/23

SLIDE 5

Material Handling

Sorting
Waste Management
Packing

– p.5/23

SLIDE 6

Industrial Applications

Printed Circuit Boards
Quality Assurance
Automobile Assembly

– p.6/23

SLIDE 7

Intelligent Transportation

Landmark recognition
Lane Following
Road Sign Reading

– p.7/23

SLIDE 8

Human-Computer Interaction

Eye Tracking
Lip Reading
Face Recognition
Gesture Recognition
Signature Recognition

– p.8/23

SLIDE 9

Navigation: Main Problems

Feature Correspondence
Structure From Motion
Obstacle Avoidance

– p.9/23

SLIDE 10

Feature Correspondence

Which corner feature is which (very difficult for

the computer)?

Need two Calibrated Cameras

Left Camera Right Camera

– p.10/23

SLIDE 11

Feature Correspondence

Sometimes it is even worse.

Left Camera

Right Camera

– p.11/23

SLIDE 12

Structure From Motion

Problem: Need to estimate the depth, z

xleft = R.xright + T (1)

R is a 3 × 3 rotation matrix
T is a 3 × 1 translation vectors
Need at least 6 matched feature points to solve

for R and T

– p.12/23

SLIDE 13

Object Detection

Some Famous Methods:

Background Subtraction
Thresholding
Statistical Methods
Snakes

– p.13/23

SLIDE 14

Background Subtraction

Subtract a well known background image from the current image frame Object = ImageCurrent − ImageBackground (2)

– p.14/23

SLIDE 15

Thresholding

All pixels with intensity greater than a certain

threshold are object pixels.

Or, all pixels with intensity in a certain range are
bject pixels.

– p.15/23

SLIDE 16

Thresholding

Original Image

Thresholding for the red object Thresholding for the green object

– p.16/23

SLIDE 17

Object Classification

After segmenting out the object, we need to

classify it (car, ball, dog, or what?)

Famous Methods
Neural Networks
String Matching
Texture Analysis

– p.17/23

SLIDE 18

Neural Networks

A simple scheme is to feed the network with the object colors and let it decide what object this is.

– p.18/23

SLIDE 19

String matching

The boundary of the object is treated as a string of an- gels and the similarity between the object’s string and the known string is measured. The object is classified to the class with which it gave maximum similarity.

– p.19/23

SLIDE 20

Texture Analysis

The texture of the object is analyzed using tools such as Fourier transform to detect certain patterns of fre-

quencies. The assumption is that different objects have

different frequency patterns.

– p.20/23

SLIDE 21

Object Tracking

The main problem is to locate the object from frame to another in the image sequence or the video. One famous method is Active Deformable Models, more commonly known as snakes.

– p.21/23

SLIDE 22

Object Tracking

Figure 1: Target Tracking

– p.22/23

SLIDE 23

Object Tracking

Figure 2: Target Tracking

– p.23/23