MATLAB & Simulink


Computer Vision with MATLAB

Course Highlights

This two-day course provides hands-on experience with performing computer vision tasks. Examples and exercises demonstrate the use of appropriate MATLAB® and Computer Vision System Toolbox functionality.

Topics include:

  • Importing, displaying and annotating images and videos

  • Detecting, extracting and matching object features

  • Automatically aligning images using geometric transformations

  • Detecting objects in images and videos

  • Tracking objects and estimating their motion in a video

  • Removing lens distortion from images

  • Measuring planar objects 

  • Working with point clouds

  • Reconstructing a 3D scene from two or multiple images


Upcoming Program

Techsource Systems is
Mathworks Sole and Authorised Distributor and Training Partner


  • MATLAB, Image Processing Toolbox and Computer Vision System Toolbox


  • Attended Comprehensive MATLAB or equivalent experience using MATLAB.

  • Basic knowledge of image processing and computer vision concepts

Course Outline

Day 1 of 2

Importing, Visualizing and Annotating Videos


Objective: Import videos into MATLAB, as well as annotate and visualize them. The focus is on using System Objects for performing iterative computations on video frames.

-Importing and displaying video files

-Highlighting objects by drawing markers and shapes like rectangles

-Combining and overlaying two images

-Performing iterative computations on video frames 


Detecting, Extracting and Matching Image Features

Objective: Use corner and blob detectors to detect local features in images. Extract and match features from two images. Use matched features to automatically align and stitch images.

-Detecting and extracting features in an image

-Matching features between two input feature sets

-Estimating geometric transformation between images

-Aligning and stitching images 


Object Detection 


Objective: Train a detector for flexible object detection. Detect moving objects by using a foreground detector.

- Marking objects of interest in training images

- Training and using the cascaded object detector

- Using foreground detection to detect objects 


Motion Estimation


Objective: Estimate direction and strength of motion in a video sequence.

- Understanding motion perception in images

- Estimating motion using block matcher

- Estimating motion using optical flow methods

Day 2 of 2



Objective: Track single and multiple objects and estimate their trajectory. Handle occlusion by predicting object position.

- Tracking objects using histogram of pixel values

- Tracking points using a point tracker

- Predicting object position using the Kalman filter

- Tracking multiple objects


Camera Calibration

Objective: Remove lens distortion from images. Measure size of planar objects.

- Estimating intrinsic, extrinsic, and lens distortion parameters of a camera
- Visualizing the calibration error
- Removing lens distortion
- Measuring planar objects in real-world units 


Point Clouds

Objective: Work with data points stored as point clouds. Import, visualize, and process point clouds.


- Importing and visualizing point clouds
- Removing outliers from point clouds
- Registering multiple point clouds
- Fitting a geometric shape into a point cloud 


3D Reconstruction

Objective: Create a 3D reconstruction of a scene using stereo cameras or a series of images taken by a moving camera.


- Reconstructing a scene using two or multiple images
- Reconstructing a scene using calibrated stereo cameras
- Extracting depth information from stereo images