بینایی کامپیوتر

1.1. Syllabus

00:12′

2.1. Basic Definitions

00:20′

3.1. Motivations

00:18′

4.1. Conducted Research at IPL

00:18′

1.2. Brief Review on Signals & Systems

00:19′

2.2. Some Simple Image Processing Tasks & Convolution

00:18′

3.2. Fourier Transform 01

00:15′

4.2. Fourier Transform 02

00:09′

5.2. Fourier Transform 03

00:11′

6.2. Fourier Transform 04

00:06′

7.2. Image Filtering 01

00:16′

8.2. Image Filtering 02

00:11′

1.3. Review on Linear Algebra

00:18′

2.3. Parameterizing the Rotation Matrix

00:07′

3.3. Homogeneous Coordinates 01

00:19′

4.3. Homogeneous Coordinates 02

00:12′

5.3. Pinhole Camera Model 01

00:16′

6.3. Pinhole Camera Model 02

00:11′

1.4. Parallel projection 01

00:11′

2.4. Parallel projection 02

00:05′

3.4. Perspective projection

00:14′

4.4. Building simple image mosaics 01

00:09′

5.4. Building simple image mosaics 02

00:08′

6.4. External & internal camera parameters

00:14′

7.4. Homography map 01

00:10′

8.4. Homography map 02

00:20′

9.4. General camera translation

00:08′

1.5. Two calibrated cameras 01

00:19′

2.5. Two calibrated cameras 02

00:12′

3.5. Two calibrated cameras & Calibration using known 3D object

00:08′

4.5. Computing camera parameters from the projection matrix

00:14′

5.5. Computing the projection matrix from E 01

00:16′

6.5. Computing the projection matrix from E 02

00:21′

7.5. Uncalibrated cameras - The fundamental matrix (F) & Projective reconstruction

00:18′

8.5. Computing the projection matrices from F

00:16′

9.5. Rectification using metric information

00:14′

1.6. Surface reconstruction & rendering

00:17′

2.6. Voronoi cells & Delaunay triangulations

00:06′

3.6. Surface mappings, image-based rendering & Planar surfaces, linear mappings

00:15′

1.7. Multiple Cameras 01

00:18′

2.7. Multiple Cameras 02

00:17′

1.8. Some Basic Properties

00:15′

2.8. Derivatives 01

00:13′

3.8. Derivatives 02

00:05′

4.8. Keypoints 01

00:15′

5.8. Keypoints 02

00:11′

6.8. Keypoints 03

00:07′

7.8. Scale Selection

00:06′

8.8. SIFT

00:14′

9.8. HoG

00:10′

10.8. GIST

00:10′

1.9. Keypoint Matching

00:17′

2.9. Template Matching & Chamfer Matching

00:13′

3.9. KD- Tree Search

00:10′

1.10. Model Fitting

00:15′

2.10. M - estimator

00:06′

3.10. Robust Estimation

00:17′

1.11. Data grouping

00:18′

2.11. Learning Types

00:05′

3.11. K-Means clustering

00:12′

4.11. K-nearest neighbor classifier

00:12′

5.11. Expectation-Maximization

00:12′

6.11. Mean shift

00:17′

1.12. Introduction to Deep Learning

00:22′

2.12. Basic Machine Learning Concepts

00:12′

3.12. Deep Learning in Computer Vision

00:09′

4.12. Neural Network Models

00:17′

5.12. Neural Networks

00:14′

6.12. Convolutional Neural Networks

00:10′

7.12. Recurrent Neural Networks

00:09′

8.12. Transformer models

00:18′

9.12. Popular Networks in Computer Vision

00:17′

1.13. Opencv

00:27′

2.13. Edge

00:24′

3.13. Open3d

00:43′

4.13. Homography

00:31′

5.13. Surface Reconstruction

00:22′

6.13. Template Matching 01

00:26′

7.13. Template Matching 02

00:33′

8.13. Sift

00:26′

9.13. Feature Matching 01

00:23′

10.13. Feature Matching 02

00:13′

11.13. Comparison

00:37′

12.13. Scikit Image

00:22′

13.13. HoG

00:53′

14.13. Scikit-learn

00:07′

15.13. Clustering

00:42′

16.13. Pytorch-Introduction

00:20′

17.13. Pytorch-Torchvision

00:07′

18.13. Pytorch-Dataset

00:31′

19.13. Pytorch-Model

00:25′

20.13. Pytorch-Train Loop

00:30′

21.13. Pytorch-Inference

00:06′