This presents a methodology to employ two 360 cameras to perceive obstacles all around the autonomous vehicle using stereo vision. Using vertical, rather than horizontal, camera displacement allows the computation of depth information in all viewing directions, except zenith and nadir which have the least useful information about the obstacles. The Key idea for obstacle detection is to classify points in the 3D space based on height, width and traversable slope relative to the neighbouring points. The detected obstacle points can be mapped onto convenient projection planes for motion planning.

This algorithm that automatically reads license plate from videos that has taken from personal devices. Unlike commonly used license plate reader in toll payment or road control system, video from personal devices usually has more variation in viewing angle, resolution, shutter speed and so on. This work read single frame from video first, then extract the license plate by detecting high-density vertical edge areas and filtered by color and boundary features.

It consists of an adaptive image contrast based document image binarization technique that is tolerant to different type of document degradation such as uneven illumination document smear involving smudging of text, seeping of ink to the other side of page, degradation of paper ink due to aging

Lane Departure Detection will Detect the Lane and Detect Departure of Vehicle from the Lane.

Object Detection Using Stereo Vision Camera will Detect the Object by Depth Detection.

License Plate Detection will Detect License Plate and Character by OCR