Distance Estimation in Video using Machine Learning

Abstract

In a video, distance estimate refers to calculating the distance between an object and the camera. The camera records the live video of a person walking in front of it. Live video is collected when a human stands in front of the camera and begins to walk in front of it. A sequence of video frames is derived from the collected live footage. These frames are handled separately. Each frame is subjected to a face detection method. The detected face is surrounded by a rectangle. The rectangle created around the detected face is used to calculate height and breadth. This is known as the perspective width. The focal length is calculated using the perspective width. The proposed system is using the focal length to determine distance once it has been calculated. The user can now walk in front of the system, which is now ready for distance estimation. The basic goal is to recognize a moving face and calculate its distance from the camera. In the realm of research, distance estimate is useful. For execution, the initiative makes use of cutting-edge technologies such as machine learning.