Artificial Intelligence | Computer Vision

In a nutshell, I’ve taken the following steps to accomplish this: Correct for Camera Distortion Filter Lane Pixels Get the“Sky View” Fit the “Best-Fit” Curve Project the Lane back to the “Vehicle-View” Image 1. CAMERA CALIBRATION Because of the physical properties of a camera lens, the captured two-dimensional image isn’t perfect. There are image distortions that change the apparent size and shape of an object. More importantly it makes some objects appear closer or farther away than they actually are. Fortunately, we can measure this distortions and correct them. We can extract all the distortion information we need by having pictures of objects which we know where the certain points should be theoretically. Commonly used are chessboards on a flat surface because chessboards have regular high contrast patterns. It’s easy to imagine what an undistorted chessboard looks like. 2. PERSPECTIVE TRANSFORMATION After having the image corrected, we’d have an undistorted image of a road from th...

  The project idea was implemented using OpenCV-Python and aws.rekognition The aim was to predict the facial expression features of the image or frame in a video. Requirements:  Python3 library: opencv-python  https://pypi.org/project/opencv-python/ AWS account Step 1:            Sign up an aws account and create iam user service (amazon rekogmition and amazon bucket s3) enabled.          Once created iam user account download credential.csv file and copy the file to your folder location.( Note don't share your credential to anyone ) Step 2:            write a  python program to capture the video using webcam.                        Read the credential file to your program and read  aws_access_key_id  and  aws_secret_access_key. with open ( "new_user_credentials.csv" , 'r' ) as input: next (...