Semiautomated Mapping of Benthic Habitats and Seagrass Species Using a Convolutional Neural Network Framework in Shallow Water Environments

Abstract

Benthic habitats are structurally complex and ecologically diverse ecosystems that are severely vulnerable to human stressors. Consequently, marine habitats must be mapped and monitored to provide the information necessary to understand ecological processes and lead management actions. In this study, we propose a semiautomated framework for the detection and mapping of benthic habitats and seagrass species using convolutional neural networks (CNNs). Benthic habitat field data from a geo-located towed camera and high-resolution satellite images were integrated to evaluate the proposed framework. Features extracted from pre-trained CNNs and a “bagging of features” (BOF) algorithm was used for benthic habitat and seagrass species detection. Furthermore, the resultant correctly detected images were used as ground truth samples for training and validating CNNs with simple architectures. These CNNs were evaluated for their accuracy in benthic habitat and seagrass species mapping using high-resolution satellite images. Two study areas, Shiraho and Fukido (located on Ishigaki Island, Japan), were used to evaluate the proposed model because seven benthic habitats were classified in the Shiraho area and four seagrass species were mapped in Fukido cove. Analysis showed that the overall accuracy of benthic habitat detection in Shiraho and seagrass species detection in Fukido was 91.5% (7 classes) and 90.4% (4 species), respectively, while the overall accuracy of benthic habitat and seagrass mapping in Shiraho and Fukido was 89.9% and 91.2%, respectively.

Regional High-Resolution Benthic Habitat Data from Planet Dove Imagery for Conservation Decision-Making and Marine Planning

“…Key challenges remain, including the development of more accurate satellite-derived bathymetry (SDB) models and the ability to sense at greater depths, dealing with turbid water, improving the accuracy of training and validation data integration, and making change detection systems more stable and accurate [22,27,33,36]. Techniques for mapping benthic habitats will also continue to improve with more powerful machine learning classifiers, such as Support Vector Machines and Convolution Neural Networks (CNN) [79,80]. Recent advances that will enhance benthic mapping in the future include the development of a spectral database for corals [20] and the deployment of large-scale operational mapping of live coral [66].…”

Classification of Lakebed Geologic Substrate in Autonomously Collected Benthic Imagery Using Machine Learning

“…It is notable that the parent material and glacial processes that formed the contemporary Great Lakes lakebed are very similar to those in other parts of the North American marine coast (i.e., the Gulf of Maine). Therefore, the trained models used here may be directly applicable to similar geographies outside the Great Lakes region or be useful for transfer learning applications [9].…”

“…to make them more visually interpretable, assignment of substrate classes to imagery, and supervised classification to produce predictive maps across continuous areas. The assignment of substrate classes to imagery at specific locations (i.e., image "annotation") can be particularly time consuming if it requires human observer(s) to evaluate each image or video clip to determine the substrate class(es) present [8,9]. Automation of class assignments using computational methods has potential to both accelerate the preparation of ground truth data and to increase the number of ground truth observations available for supervised classification [5,9,10].…”

“…The assignment of substrate classes to imagery at specific locations (i.e., image "annotation") can be particularly time consuming if it requires human observer(s) to evaluate each image or video clip to determine the substrate class(es) present [8,9]. Automation of class assignments using computational methods has potential to both accelerate the preparation of ground truth data and to increase the number of ground truth observations available for supervised classification [5,9,10]. Here, we focus on the challenge of automated image annotation for geologic substrate classes in still images gathered from AUVs.…”

UAV-Based Subsurface Data Collection Using a Low-Tech Ground-Truthing Payload System Enhances Shallow-Water Monitoring

“…A hexacopter model, such as the DJI ® Matrice 600, not only provides longer flight times of approximately 35 min, but also comes with a higher payload capacity. The latter would allow for the mount of more advanced camera systems, additional loggers (e.g., water quality measurement systems [36], temperature profiling systems [38] or water samplers [33,34,[58][59][60][61]), and a line spool, which would eliminate the need for lowering the UAV flight altitude in order to submerge the camera-logger cluster.…”