Computer Vision
CNNs, object detection, segmentation, and image augmentation techniques
Foundations
- Computer Vision
Image Classification
Given a fixed-size image, predict which class it belongs to from a predefined set — the task that launched the deep learning revolution when AlexNet cut the ImageNet error rate nearly in half in 2012.
- Computer Vision
Camera Calibration and Parameters
Camera calibration is the process of estimating a camera's internal characteristics and its physical position in the world, enabling us to mathematically map 3D world coordinates to 2D image pixels.
- Computer Vision
Color Spaces in Vision
Why raw RGB pixels are terrible for computer vision, and how transforming color into spaces like HSV or YCbCr unlocks robust image processing.
- Computer Vision
Epipolar Geometry & Stereo Matching
How two cameras see the same 3D point in the world and use their geometry to simplify finding matches.
- Computer Vision
Frequency Domain Image Processing
Instead of viewing an image as a grid of pixels, frequency domain processing treats it as a sum of 2D sine and cosine waves, allowing us to easily filter out noise or isolate specific patterns.
- Computer Vision
Image Formation and Camera Model
How a 3D physical world is mathematically projected into a 2D pixel array, forming the foundation of computer vision and multi-view geometry.
- Computer Vision
Image Transformations and Homography
Learn how linear algebra powers resizing, rotating, and skewing images in computer vision, and understand homography for perspective projection.
- Computer Vision
Morphological Image Operations
Morphological operations are simple, non-linear techniques that process images based on shapes, allowing you to remove noise, separate touching objects, or find edges using a small sliding template called a structuring element.
- Computer Vision
Structure from Motion
Reconstructing a 3D scene and the camera's path simultaneously from a moving video or a collection of images.
- Computer Vision
Visual SLAM
Visual SLAM allows a system to simultaneously map an unknown environment and track its own location within it using only camera input.
Detection And Localization
- Computer Vision
Object Detection
Object detection finds every instance of every object class in an image, returning a bounding box and class label for each — combining classification and localization in a single forward pass.
- Computer Vision
Anchor Boxes
This concept covers the fundamentals of anchor boxes within the broader context of Computer Vision.
- Computer Vision
Non Maximum Suppression
This concept covers the fundamentals of non maximum suppression within the broader context of Computer Vision.
- Computer Vision
Region Proposal Networks
This concept covers the fundamentals of region proposal networks within the broader context of Computer Vision.
- Computer Vision
Yolo Architecture
This concept covers the fundamentals of yolo architecture within the broader context of Computer Vision.
- Computer Vision
Feature Pyramid Networks
This concept covers the fundamentals of feature pyramid networks within the broader context of Computer Vision.
- Computer Vision
Classical Object Tracking
Classical object tracking algorithms follow moving objects across video frames using mathematical motion models and pixel matching, rather than deep neural networks.
- Computer Vision
Corner and Keypoint Detection
Corners and keypoints are distinct image regions that can be tracked across frames or matched between different views, acting as stable anchors for computer vision tasks.
- Computer Vision
Face Detection and Recognition
Face recognition works in two distinct steps: first locating the face in an image (detection), then mapping its unique geometry to identify who it belongs to (recognition).
- Computer Vision
HOG Features and Classical Detection
The Histogram of Oriented Gradients (HOG) is a classical technique that detects objects by analyzing the distribution of edge directions in an image.
Segmentation
- Computer Vision
Semantic Segmentation
Semantic segmentation assigns a class label to every single pixel in an image, producing a dense map where pixels belonging to the same object class share the same label — going beyond bounding boxes to pixel-precise understanding.
- Computer Vision
Instance Segmentation
Instance segmentation identifies and outlines each distinct object in an image, unlike semantic segmentation which groups all objects of the same class together.
- Computer Vision
Convolutional Layers
This concept covers the fundamentals of convolutional layers within the broader context of Computer Vision.
- Computer Vision
Pooling And Downsampling
This concept covers the fundamentals of pooling and downsampling within the broader context of Computer Vision.
- Computer Vision
Panoptic Segmentation
This concept covers the fundamentals of panoptic segmentation within the broader context of Computer Vision.
- Computer Vision
Pose Estimation
This concept covers the fundamentals of pose estimation within the broader context of Computer Vision.
- Computer Vision
Optical Flow
This concept covers the fundamentals of optical flow within the broader context of Computer Vision.
- Computer Vision
Stereo Vision
This concept covers the fundamentals of stereo vision within the broader context of Computer Vision.
- Computer Vision
Image Generation
This concept covers the fundamentals of image generation within the broader context of Computer Vision.
- Computer Vision
Video Understanding
This concept covers the fundamentals of video understanding within the broader context of Computer Vision.
- Computer Vision
Classical Image Segmentation
How traditional computer vision techniques separate foreground from background using pixel intensity, edges, and regions without deep learning.
- Computer Vision
Encoder-Decoder Segmentation Architectures
By pairing a downsampling encoder to capture deep semantic context with an upsampling decoder to recover spatial details, models like U-Net can classify every pixel in an image.
- Computer Vision
Medical Image Analysis
Medical imaging requires extremely precise pixel-level analysis to locate tumors or organs, often using specialized architectures like U-Net that preserve fine spatial details.
Training Techniques
- Computer Vision
Image Augmentation
Image augmentation artificially expands the training set by applying random label-preserving transformations — flips, crops, color jitter — teaching the model that these variations don't change the label and dramatically reducing overfitting.
- Computer Vision
Transfer Learning
This concept covers the fundamentals of transfer learning within the broader context of Computer Vision.
- Computer Vision
Feature Extraction
This concept covers the fundamentals of feature extraction within the broader context of Computer Vision.
- Computer Vision
Domain Adaptation for Vision
Domain adaptation bridges the gap between the distribution of training data and real-world test data to make models more robust.
- Computer Vision
Few-Shot and Zero-Shot Vision
Few-shot and zero-shot learning empower vision models to recognize new classes with extremely little or absolutely no training data.
Evaluation
Architecture
Generative Vision Audio Multimodal
- Computer Vision
Image Captioning
Image captioning models act as a bridge between vision and language, taking an image as input and generating a coherent textual description of its contents.
- Computer Vision
Image-to-Image GANs
Instead of generating an image from random noise, Image-to-Image GANs translate an input image from one domain into another, like turning a sketch into a photo.
- Computer Vision
Super-Resolution and Image Restoration
Discover how deep learning models recover lost details, remove noise, and upsample low-quality images into crisp, high-resolution outputs.
Representation Learning
- Computer Vision
Neural Radiance Fields
Instead of explicitly storing 3D shapes, NeRF trains a neural network to memorize a 3D scene and render new views from any angle.
- Computer Vision
Point Cloud Processing
Instead of converting 3D scans into bulky grids, point cloud processing works directly on unstructured sets of 3D coordinates.