Human Cardboard Cutout Recognition

Human Cardboard Cutout Recognition

Authors

Presenter(s)

Vijay Kumar Varma Ganaraju

Comments

Presentation: 11:20 a.m.-11:40 a.m., Kennedy Union 211

This project reflects research conducted as part of a course project designed to give students experience in the research process.

Course: CPS 595

Files

Description

As we are reaching the higher levels in autonomous driving, we are moving away from LiDAR and RADAR and towards Vision-only based prediction. And there are a lot of challenges with it. One of the important ones is predicting the objects when the vehicle is idle. Vision-only based systems predict using 3D reconstruction of the environment by moving over the space and triangulating the objects around it using multiple cameras. By NOT moving over the space, the 3D reconstruction is handicapped and it has to rely on 2D models. Therefore, the challenge is if a truck/bus is in front of the autonomous vehicle, it does not know if the human is real or just a poster on the truck/bus and could make grave mistakes. The goal of this research is to resolve this issue by creating a AI model which can classify real humans and fake humans (Cardboard cutouts) by analyzing the light patterns and variance.

Publication Date

4-20-2022

Project Designation

Course Project

Primary Advisor

Van Tam Nguyen

Primary Advisor's Department

Computer Science

Keywords

Stander Symposium project, College of Arts and Sciences

United Nations Sustainable Development Goals

Industry, Innovation, and Infrastructure

Human Cardboard Cutout Recognition

Share

COinS