Map movement using hand gestures by machine learning

The goal of this project is to enhance Google Maps navigation via the implementation of gestures using machine learning and Python programming. Our method is an interdisciplinary interface that combines gesture detection and hand position estimation, with a collaborative learning algorithm to increase overall accuracy. It is based on current advancements and approaches detailed in the relevant papers. With the technology, users can effortlessly navigate Google Maps left-right, up-and-down, and zoom in and out using gestures. The use of gentle hand movements enhances the ship’s organic sailing sensation, particularly when the ship is in its vertical and horizontal postures. Using a shape-based gesture to zoom in and out is simple. A user-friendly experience is offered via an application for Google Maps that is smoothly linked with the platform. Applications such as continuous hand gesture recognition, Manipuri traditional dance gesture recognition, and teleoperation control of a mobile robot with a mechanum-wheel serve as sources of inspiration. ADDAT supports a complicated system and provides accuracy, speed, and user-friendly navigation. Our solution tackles the difficulties of unclear gestures while moving by fusing machine learning with Python, offering a more organic and effective method of adoption so that people can interact. It is anticipated that the suggested methodology would provide viable approaches to enhance human-computer interaction in transportation planning and other associated domains.