Object Detection for Dummies Part 1: Gradient Vector, HOG, and SS
Lilian Weng
A beginner's guide post introduces foundational concepts in object detection for computer vision, covering gradient vectors, HOG (Histogram of Oriented Gradients), and image segmentation methods without using deep neural networks. The article promises subsequent parts will cover deep learning approaches to object detection in parts 2 and 3. This is primarily an educational explanation of classical computer vision techniques rather than reporting on new developments or research.
Why it matters
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. Nothing related to deep neural networks yet. Deep learning models for object detection and recognition will be discussed in Part 2 and Part 3.
