IBURD: Image Blending for Underwater Robotic Detection

TL;DR

IBURD is a novel image blending pipeline that generates realistic synthetic underwater images with annotations to improve deep learning detection of marine debris for autonomous underwater vehicles.

Contribution

The paper introduces IBURD, a new method for creating realistic synthetic underwater images with annotations, enhancing training data for marine debris detection.

Findings

Synthetic images improve detection accuracy.

IBURD effectively blends transparent objects into backgrounds.

Enhanced training data aids underwater robotic detection.

Abstract

We present an image blending pipeline, \textit{IBURD}, that creates realistic synthetic images to assist in the training of deep detectors for use on underwater autonomous vehicles (AUVs) for marine debris detection tasks. Specifically, IBURD generates both images of underwater debris and their pixel-level annotations, using source images of debris objects, their annotations, and target background images of marine environments. With Poisson editing and style transfer techniques, IBURD is even able to robustly blend transparent objects into arbitrary backgrounds and automatically adjust the style of blended images using the blurriness metric of target background images. These generated images of marine debris in actual underwater backgrounds address the data scarcity and data variety problems faced by deep-learned vision algorithms in challenging underwater conditions, and can enable the use of AUVs for environmental cleanup missions. Both quantitative and robotic evaluations of IBURD demonstrate the efficacy of the proposed approach for robotic detection of marine debris.