Accurate Ulva prolifera regions extraction of UAV images with superpixel and CNNs for ocean environment monitoring

UAV (Unmanned Aerial Vehicle) monitoring mounted with high resolution camera is a rising way to monitor the ocean environment, and it can make up the shortages of low spatial and temporal resolutions of SAR images. How to get the accurate regions of Ulva prolifera in the very high-resolution images...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neurocomputing (Amsterdam) Jg. 348; S. 158 - 168
Hauptverfasser: Wang, Shengke, Liu, Lu, Qu, Liang, Yu, Changyin, Sun, Yujuan, Gao, Feng, Dong, Junyu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 05.07.2019
Schlagworte:
CNN
Pixel-level segmentation
Superpixel
Ulva prolifera
Superpixel
CNN
Pixel-level segmentation
Ulva prolifera
ISSN:0925-2312, 1872-8286
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:UAV (Unmanned Aerial Vehicle) monitoring mounted with high resolution camera is a rising way to monitor the ocean environment, and it can make up the shortages of low spatial and temporal resolutions of SAR images. How to get the accurate regions of Ulva prolifera in the very high-resolution images remains a lot of challenges. Due to the limitation of GPU memory, the popular pixel-level image segmentation methods cannot deal with the raw resolution images(Up to 6000*4000). In this paper, we propose a novel framework to get the Ulva prolifera regions, which incorporates both superpixel segmentation and CNN classification and can deal with raw resolution images. We first process the raw images with superpixel algorithm to generate local multi-scale patches. And then a binary classification CNN model can be trained with the labeled patches. With the result of superpixel segmentation and the classification of CNN model, a more detailed segmentation of Ulva prolifera can be obtained. Two datasets UlvaDB-1 and UlvaDB-2 are also proposed in this paper. The experiment results show that the proposed method can achieve state-of-the-art performance compared with the recent pixel-level segmentation and instance-aware semantic segmentation methods.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2018.06.088