Event Control through Motion Detection

Abstract

Computer Vision is the study of machines that extract information from an image and perform some processing on the captured images to extract necessary data
to solve some task. As a scientic discipline, the study of computer vision is concerned with the theories behind articial systems that extract information from images. The image data could in several dierent forms and formats, such as video sequences, views from multiple cameras, or multi-dimensional data acquired from a medical scanner. As a technological discipline, computer vision intends to
apply its theories and models to the construction and design of computer vision systems
The role of computer vison in robots is providing detailed information about the environment. A robust vision system should be able to detect and identify objects reliably and provide an accurate representation of the environment to
higher level processes. The vision system should also be highly ecient, allowing a resource limited agent to respond quickly to a changing environment. Each frame acquired by a digital camera must be processed in a small, usually xed,
amount of time. Algorithmic complexity is therefore constrained, introducing a tradeo between processing time and the quality of the information acquired. In most robotic applications, the vision system is the main perception device and autonomous robots must be capable of using it in order to self-localize and locate the objects that they have to manipulate.
The objective of the project was to build a computer controlled bot which could collect and deposit balls rolling down a ramp with the help of overhead/onboard
camera.The ojective was achieved with the use of Motion History Image(MHI) based image processing algortihms and microcontroller based controling of motors.