Habitat mapping using deep neural networks

  • PDF / 2,003,856 Bytes
  • 12 Pages / 595.276 x 790.866 pts Page_size
  • 113 Downloads / 310 Views

DOWNLOAD

REPORT


SPECIAL ISSUE PAPER

Habitat mapping using deep neural networks Muhammad Yasir1 · Arif Ur Rahman1   · Moneeb Gohar1

© Springer-Verlag GmbH Germany, part of Springer Nature 2020

Abstract Habitat mapping is an important and challenging task that helps in monitoring, managing, and preserving ecosystems. It becomes more challenging when marine habitats are mapped, as it is difficult to get quality images in an underwater environment. Moreover, achieving good location accuracy in underwater environments is an additional issue. Sonar imagery has good quality but is hard to be analyzed. Therefore, camera imagery is used for research purposes. Our research targets marine habitats - more specifically, coral reef marine habitats. Recognition of coral reef in underwater images poses a significant difficulty due to the nature of the data. Many species of coral reef have similar characteristics, i.e. higher inter-class similarity and lower intra-class similarity. Spatial borders between coral reef classes are hard to separate, as they tend to appear together in groups. For these reasons, the classification of coral reef species requires aid from marine biologists. This research work presents a technique for accurate coral reef classification using deep convolutional neural networks. The proposed approach has been validated on Moorea Labeled Corals (MLC), an imbalanced dataset, which is a subset of Moorea Coral Reef Long Term Ecological Research (MCR LTER) packaged for computer vision research. A custom valid patch dataset is extracted using the annotation files provided with the dataset. Two image enhancement algorithms and datadriven feature extraction techniques are employed using several pre-trained deep convolutional neural networks as feature extractors. Local-SPP technique is combined with feature extractors and followed by 2-layers multi-layer perceptron (MLP) classifier to achieve high classification rates. Keywords  Habitat mapping · Coral reef · Color channel stretching · CLAHE · Convolutional neural networks · Feature extraction

1 Introduction A habitat is a natural environment in which an organism (species) lives or the physical environment that encompasses, impacts and is used by species populace. For instance, a forest or a swamp is a habitat. Habitats exist in two forms, namely Land and Marine. Habitats and biological communities throughout the world face high risks of elimination because of atmosphere changes, defilement, meddling species and overexploitation [1]. To see, how human-conduct destroys these frequently delicate habitats, one needs to assess them through habitat mapping. Habitat mapping shows the geographic distribution of different habitats within a particular area. Various types of images can be used for mapping habitats. Depending * Arif Ur Rahman [email protected] 1



Department of Computer Science, Bahria University, Islamabad, Pakistan

on the form of habitat to be mapped, different data types exist, for instance, sonar imagery and satellite imagery. Two continuous habitat maps of the sam