Object Detection for Dummies Part 1: Gradient Vector, HOG, and SS | Lil'Log

I’ve never worked in the field of computer vision and has no idea how the magic could work when an autonomous car is configured to tell apart a stop sign from a pedestrian in a red hat. To motivate myself to look into the maths behind object recognition and detection algorithms, I’m writing a few posts on this topic “Object Detection for Dummies”. This post, part 1, starts with super rudimentary concepts in image processing and a few methods for image segmentation.

Table of Contents Image Gradient Vector Common Image Processing Kernels Example: Manu in 2004 Histogram of Oriented Gradients (HOG) How HOG works Example: Manu in 2004 Image Segmentation (Felzenszwalb's Algorithm) Graph Construction Key Concepts How Image Segmentation Works Example: Manu in 2013 Selective Search How Selective Search Works Configuration Variations References I've never worked in the field of computer vision and has no idea how the magic could work when an autonomous car is configured to tell apart a stop sign from a pedestrian in a red hat. To motivate myself to look into the m

related reading

• Object Detection for Dummies Part 3: R-CNN Family | Lil'Loglilianweng.github.io
• Policy Gradient Algorithms | Lil'Loglilianweng.github.io
• The Little Book of Deep Learningfleuret.org
• Part 3: Intro to Policy Optimization - Spinning Up documentationspinningup.openai.com
• Differentiable Programming from Scratchthenumb.at
• 3D Object Detection via 2D Segmentation-Based Computational Integral Imaging Applied to a Real Videoncbi.nlm.nih.gov
• CS231n Deep Learning for Computer Visioncs231n.github.io
• Deep Reinforcement Learning: Pong from Pixelskarpathy.github.io
• CS231n Deep Learning for Computer Visioncs231n.github.io
• Understanding Image Gradients | TheAILearnertheailearner.com
• How to build a self-driving car in one month | by Max Deutsch | Mediummedium.com
• Understanding Convolutions on Graphsdistill.pub