A Glimpse Into GRASP Research: Computer Vision

Computer vision – “Computer Vision, often abbreviated as CV, is defined as a field of study that seeks to develop techniques to help computers “see” and understand the content of digital images such as photographs and videos.” – What is Computer Vision

Event camera (neuromorphic camera) – “Event cameras do not capture images using a shutter as conventional cameras do. Instead, each pixel inside an event camera operates independently and asynchronously, reporting changes in brightness as they occur, and staying silent otherwise.” – Wiki on event cameras

• Introduction to event based vision by Nabil Madali  (HS & advanced)
• From Pixels to Pictures, a description of how pixels contribute to the resolution of an image (MS & HS)
• Frames per second explanation (MS &HS)

Image credit: Nabil Madali

1/10th scale Traxxas car – This radio controlled (RC) racing car is commonly used by roboticists to study autonomous driving at a smaller scale (specifically at 1/10th the size of a real car). This smaller scale allows roboticists to test technology in real world scenarios without the costs and risks of using full sized vehicles. 

• Traxxas website
• More information about Traxxas (Advanced)

Brushless motor – “Direct current (DC) motors are a type of electric motor that provides efficient constant rotation. This is in contrast with servo motors that offer precise positional control with limited range of motion. DC motors use the interaction of magnetic fields and conductors to convert electrical energy to mechanical energy for rotation.” – Seeed Studio

Embedded computing board (example: Nvidia tx2) – An embedded computing board is a small computer that often functions within a larger mechanical or electrical system. These computer systems are more capable than microcontrollers.

• Nvidia website

Neural Networks – “Neural nets are a means of doing machine learning, in which a computer learns to perform some task by analyzing training examples. Usually, the examples have been hand-labeled in advance. An object recognition system, for instance, might be fed thousands of labeled images of cars, houses, coffee cups, and so on, and it would find visual patterns in the images that consistently correlate with particular labels. Modeled loosely on the human brain, a neural net consists of thousands or even millions of simple processing nodes that are densely interconnected.” – Larry Hardesty

• Understanding Neural Networks by Ashay Parikh (HS and Advanced)
• An Introduction to Neural Networks by Victor Zhou (Advanced)
• Simple introduction to Neural Networks from Physics World (Middle and HS)

Hough line transform– “Hough transform is a way of finding edge points in an image that lie along a straight line” – Auroshis Ray

K-means clustering – “A K-means clustering algorithm tries to group similar items in the form of clusters. The number of groups is represented by K.” – DescriptionBeginner’s guide to K-means clustering by Amal Nair