Hands-On Computer Vision: SLAM, 3d geometry, Calib, AR, Pose

Practical Computer Vision: 3D Geometry, Pose Estimation, and Augmented Reality

What you'll learn
- 3D Reconstruction via Stereo Triangulation from Two Views
- Monocular Visual Odometry Using Epipolar Geometry and Optical Flow on KITTI Dataset
- Real-Time 3D Pose Estimation and Augmented Reality Box Overlay from Video Using Feature Matching (Face Recognition)
- Epipolar Geometry Visualization Using Fundamental Matrix
- 2D Video Stabilization Using Feature Tracking and Homography
- Planar Image Stitching Using BRISK Feature Matching and Homography
- Object Localization and Height Estimation Using Monocular Camera Calibration and Grid Projection

Requirements
- python

Description
This hands-on course introduces students to3D computer visionusing monocular and stereo cameras. Through a series of real-world projects and coding exercises, learners will build a strong foundation incamera geometry,feature-based matching,pose estimation, and3D reconstruction targeted for research and industrial application in Autonomous vehicle, robotics, machine learning, 3d geometry and reconstruction.

You will begin by understandingcamera calibrationand how a single camera can be used forlocalization and height estimation. You'll then move on to more advanced topics likereal-time 3D pose estimation,augmented reality overlays,video stabilization, andvisual odometryon real datasets like KITTI.

This course is project-driven and emphasizes classical, interpretable methods giving you the tools to develop your own computer vision pipeline without requiring deep learning.

What You Will Learn:

Camera Calibration & Projection Geometry

Estimate intrinsic and extrinsic parameters of monocular cameras

Use projection grids for object height estimation

Object Localization & 3D Pose Estimation

Detect and track objects using feature matching

Estimate 3D object pose and overlay augmented content in real-time

Video Stabilization & Image Stitching

Implement 2D video stabilization using feature tracking and homographies

Perform planar image stitching using BRISK and homography transformation

Feature Detection and Matching

Use BRISK, ORB, and other descriptors for robust keypoint matching

Understand outlier rejection using RANSAC

Epipolar Geometry & Visual Odometry

Compute and visualize the fundamental matrix and epipolar lines

Apply monocular visual odometry using optical flow and epipolar constraints

3D Triangulation from Stereo Views

Reconstruct 3D point clouds from stereo image pairs

Understand triangulation using projection matrices

Skills You Will Gain:

Practical understanding ofcamera models and calibration

Hands-on experience withOpenCVfor vision pipelines

Real-time3D pose estimationand augmented reality overlay

Proficiency inhomography estimationandimage registration

Building basicvisual odometrysystems from scratch

Creating and visualizing3D reconstructionsusing triangulation

Working with real datasets likeKITTIfor visual SLAM foundations

Ideal For:

Engineering and CS students

Robotics and AR/VR enthusiasts

Developers interested in classical computer vision techniques

Anyone seeking a practical foundation before diving into deep learning

Who this course is for:
- All level python developers
More Info