Stingray Detection of Aerial Images Using Augmented Training Images Generated by A Conditional Generative Model

TL;DR

This paper introduces a novel data augmentation technique using a conditional generative model to improve deep learning-based stingray detection in aerial UAV images, demonstrating enhanced detection performance.

Contribution

We develop a conditional GLO-based data augmentation method tailored for object detection, effectively increasing training data for better stingray detection in aerial imagery.

Findings

Enhanced detection accuracy with augmented data

Effective generation of training samples for object detection

Improved CNN training performance

Abstract

In this paper, we present an object detection method that tackles the stingray detection problem based on aerial images. In this problem, the images are aerially captured on a sea-surface area by using an Unmanned Aerial Vehicle (UAV), and the stingrays swimming under (but close to) the sea surface are the target we want to detect and locate. To this end, we use a deep object detection method, faster RCNN, to train a stingray detector based on a limited training set of images. To boost the performance, we develop a new generative approach, conditional GLO, to increase the training samples of stingray, which is an extension of the Generative Latent Optimization (GLO) approach. Unlike traditional data augmentation methods that generate new data only for image classification, our proposed method that mixes foreground and background together can generate new data for an object detection task, and thus improve the training efficacy of a CNN detector. Experimental results show that satisfiable performance can be obtained by using our approach on stingray detection in aerial images.