Artificial Intelligence

    

LeGuess – Predicting or Guessing the Next Scene Using Image Sequences for Accelerating Autonomous Capabilities.

Authors: Ranjan Akarsh

This paper depicts a network called LeGuess (LeG) which, using computer vision, is able to precisely predict the future scenes given sequence of images. The network is able to automatically learn the features and representations of the objects present in the sequence of images fed as input. Furthermore, this network learns the movements of the objects and predicts very well. The network is mainly designed for the domain of Autonomous Vehicles, which contains plenty of applications alone. Taking this in note, LeG can be applied to predict the steering angles, predicting the future positions of cars, trucks, cyclists, etc., ready a generative model to generate images along with steering angles, which could be used to train vehicles to drive, as well as generate images of road with/without lane to train segmentation for better autonomous driving. The network is designed to make predictions (local) of up to given number of time-steps ahead.

Comments: 9 Pages. Kindly reach out to me for any queries. I'd be happy comply.

Download: PDF

Submission history

[v1] 2020-01-04 09:21:59

Unique-IP document downloads: 202 times

Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus