Kursinnehåll

Computer Vision Course Outline

1. Introduction to Computer Vision

What is Computer Vision?Fundamentals of Image Processing Linear algebra for image manipulation

2. Image Processing with OpenCV

Basic Transformations Fourier Transform Low-pass and High-pass Filters Noise Reduction and Smoothing Histogram Equalization Super-Resolution Techniques Edge Detection Corner and Blob Detection

3. Convolutional Neural Networks

Introduction to Convolutional Neural Networks Convolution Layers Pooling Layers Flattening Activation Functions Overview of Popular CNN Models Challenge: Building a CNN

4. Object Detection

Object Localization Object Detection Bounding Box Predictions Intersection Over Union (IoU) and Evaluation Metrics Non-Max Suppression (NMS)Anchor Boxes YOLO Model Overview Challenge: Object Detection with Custom Model and YOLO

5. Advanced Topics Overview

Transfer Learning in Computer Vision Overview of Face Recognition Overview of Image Generation

Corner and Blob Detection

Corner Detection

Corner detection is used to identify sharp changes in intensity where two edges meet. It helps in feature matching, object tracking, and structure recognition.

Popular Methods:

Harris Corner Detector (cv2.cornerHarris) - Detects corners based on gradient changes.

Shi-Tomasi Corner Detector (cv2.goodFeaturesToTrack) - Selects the strongest corners in an image.

Blob Detection

Blob detection finds regions of similar intensity in an image, useful for object detection and tracking.

Popular Method:

SimpleBlobDetector (cv2.SimpleBlobDetector) - Detects keypoints representing blobs based on size, shape, and intensity.

Uppgift

Swipe to start coding

Your task is to perform corner detection by Harris, Shi-Tomasi methods on a factory image and blob detection by Simple Blob Detector on a sunflower image with the following conditions:

Harris Corner Detection:
- Block size: 2;
- Kernel size: 3;
- Harris detector free parameter (k): 0.04;
- Mark detected corners in blue [0, 0, 255].
Shi-Tomasi Corner Detection:
- Maximum corners quantity: 100;
- Quality level: 0.01;
- Minimum distance between corners: 10;
- Mark detected corners in green [255, 255, 0].
Blob Detection (SimpleBlobDetector):
- Maximal threshold: 127;
- Filter by area:
  - Minimal area: 100;
  - Maximal area: 500;
- Filter by circularity:
  - Minimal circularity: 0.02 (detects irregular shapes);
- Filter by convexity:
  - Minimal convexity: 0.5 (allows concave blobs);
- Filter by inertia:
  - Minimal inertia ratio: 0.001 (detects elongated blobs);
- Mark detected blobs in green [255, 0, 255] using cv2.drawKeypoints() with cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS flag.

Lösning

Byt till skrivbordet för praktisk övningFortsätt där du är med ett av alternativen nedan

Var allt tydligt?

Tack för dina kommentarer!

Avsnitt 2. Kapitel 8

Corner and Blob Detection

Corner Detection

Corner detection is used to identify sharp changes in intensity where two edges meet. It helps in feature matching, object tracking, and structure recognition.

Popular Methods:

Harris Corner Detector (cv2.cornerHarris) - Detects corners based on gradient changes.

Shi-Tomasi Corner Detector (cv2.goodFeaturesToTrack) - Selects the strongest corners in an image.

Blob Detection

Blob detection finds regions of similar intensity in an image, useful for object detection and tracking.

Popular Method:

SimpleBlobDetector (cv2.SimpleBlobDetector) - Detects keypoints representing blobs based on size, shape, and intensity.

Uppgift

Swipe to start coding

Your task is to perform corner detection by Harris, Shi-Tomasi methods on a factory image and blob detection by Simple Blob Detector on a sunflower image with the following conditions:

Harris Corner Detection:
- Block size: 2;
- Kernel size: 3;
- Harris detector free parameter (k): 0.04;
- Mark detected corners in blue [0, 0, 255].
Shi-Tomasi Corner Detection:
- Maximum corners quantity: 100;
- Quality level: 0.01;
- Minimum distance between corners: 10;
- Mark detected corners in green [255, 255, 0].
Blob Detection (SimpleBlobDetector):
- Maximal threshold: 127;
- Filter by area:
  - Minimal area: 100;
  - Maximal area: 500;
- Filter by circularity:
  - Minimal circularity: 0.02 (detects irregular shapes);
- Filter by convexity:
  - Minimal convexity: 0.5 (allows concave blobs);
- Filter by inertia:
  - Minimal inertia ratio: 0.001 (detects elongated blobs);
- Mark detected blobs in green [255, 0, 255] using cv2.drawKeypoints() with cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS flag.

Lösning

Byt till skrivbordet för praktisk övningFortsätt där du är med ett av alternativen nedan

Var allt tydligt?

Tack för dina kommentarer!

Avsnitt 2. Kapitel 8

Byt till skrivbordet för praktisk övningFortsätt där du är med ett av alternativen nedan