Trajectory tracking in a wide field using two fixed cameras and neural network

Authors

Maria Isabel Saludares ⋅ PH National Institute of Physics, University of the Philippines Diliman
Phoebe Gallanosa ⋅ PH National Institute of Physics, University of the Philippines Diliman
Alix Jean Santos ⋅ PH National Institute of Physics, University of the Philippines Diliman
Maricor Soriano ⋅ PH National Institute of Physics, University of the Philippines Diliman

Abstract

A low-cost method consisting of two fixed cameras was utilized to demonstrate a way of tracking objects in a wide field. The cameras were placed and positioned in an angle where there exist overlapping views such that the tracking of a moving object continues as it disappears from the view of one of the cameras. With the dimensions of the field known, pre- determined points from the image can be used to train a neural network that can then automatically convert a player’s position in image coordinates to actual world coordinates.

Downloads

Issue

2012: Proceedings of the 30th Samahang Pisika ng Pilipinas Physics Congress

Article ID

SPP2012-PA-32

Section

Poster Session PA

Published

2012-10-22

How to Cite

[1]

MI Saludares, P Gallanosa, AJ Santos, and M Soriano, Trajectory tracking in a wide field using two fixed cameras and neural network, Proceedings of the Samahang Pisika ng Pilipinas 30, SPP2012-PA-32 (2012). URL: https://proceedings.spp-online.org/article/view/SPP2012-PA-32.