Paralysis is one of the biggest curses to mankind. In worst case paralysis the person could move only his eyes. The head movement or voice-based wheelchairs will not hold good in that situation. So, an eyeball movement based wheelchair would help the best for those people. This would be more accurate when compared to other automated wheelchairs. A method for eyeball localization is proposed for controlling wheelchair. An algorithm is furnished with various processing steps and develops an efficient system to reduce both the cost and the computational complexity. Primary goal was to detect eyes in real time and to keep track on it. The idea is to create an Eye Monitored System which allows movement of the patient ‘s wheelchair depending on the eye movements. A patient looks directly at the camera mounted on a head gear and is able to move in a direction just by looking in that direction.
A head mount camera detects the eye movement and wheelchair is moved accordingly. The head mount camera is connected to the laptop where a continuously running and script processes the image and gives command to the microcontroller to control the wheels of a Wheelchair. This system came as a boon for such people. But the constraint was that you had to carry your laptop every time along with the Wheelchair System. That was bulky and costly. To remove the bulkiness and costliness of the Eye Movement based Electronic Wheelchair System, which uses MATLAB, people came up with ideas of using Raspberry Pi to control the whole Wheelchair System. Since Raspberry Pi has its own OS and it is easily portable, people switched to using Raspberry Pi based Wheelchair System. Although in the existing Raspberry Pi based Wheelchair System, latency (delay in response) is the biggest issue. Hence we have come up with a system that uses efficient algorithms for image 2 processing using OpenCV and reduces the latency as much as possible. OpenCV processes the eye and by applying the two algorithms (Centroid and Threshold), movement of wheelchair is initiated. Python is used for programming the Raspberry Pi
