Panoptic Segmentation of Environmental UAV Images : Litter Beach

TL;DR

This paper presents a panoptic segmentation approach for environmental UAV images to effectively identify and categorize marine litter on heterogeneous beaches, addressing challenges posed by complex backgrounds.

Contribution

It introduces a novel combination of instance and panoptic segmentation models tailored for UAV images of beaches with diverse textures and objects.

Findings

Achieved high accuracy with limited training samples.

Demonstrated robustness against heterogeneous beach backgrounds.

Improved litter detection compared to traditional CNN methods.

Abstract

Convolutional neural networks (CNN) have been used efficiently in several fields, including environmental challenges. In fact, CNN can help with the monitoring of marine litter, which has become a worldwide problem. UAVs have higher resolution and are more adaptable in local areas than satellite images, making it easier to find and count trash. Since the sand is heterogeneous, a basic CNN model encounters plenty of inferences caused by reflections of sand color, human footsteps, shadows, algae present, dunes, holes, and tire tracks. For these types of images, other CNN models, such as CNN-based segmentation methods, may be more appropriate. In this paper, we use an instance-based segmentation method and a panoptic segmentation method that show good accuracy with just a few samples. The model is more robust and less