Siamese Network Training Using Artificial Triplets By Sampling and Image Transformation

TL;DR

This paper presents a CNN-based approach for real-time object detection and tracking over water surfaces using thermal cameras, aiming to improve autonomous obstacle avoidance in challenging conditions like night or fog.

Contribution

It introduces a novel training method for Siamese networks using artificial triplets through sampling and image transformation techniques.

Findings

Effective object tracking in water environments demonstrated

High accuracy in obstacle identification and trajectory prediction

Real-time deployment validated on test boat platform

Abstract

The device used in this work detects the objects over the surface of the water using two thermal cameras which aid the users to detect and avoid the objects in scenarios where the human eyes cannot (night, fog, etc.). To avoid the obstacle collision autonomously, it is required to track the objects in real-time and assign a specific identity to each object to determine its dynamics (trajectory, velocity, etc.) for making estimated collision predictions. In the following work, a Machine Learning (ML) approach for Computer Vision (CV) called Convolutional Neural Network (CNN) was used using TensorFlow as the high-level programming environment in Python. To validate the algorithm a test set was generated using an annotation tool that was created during the work for proper evaluation. Once validated, the algorithm was deployed on the platform and tested with the sequence generated by the test boat.