NASA Logo, External Link
Facebook icon, External Link to NASA STI page on Facebook Twitter icon, External Link to NASA STI on Twitter YouTube icon, External Link to NASA STI Channel on YouTube RSS icon, External Link to New NASA STI RSS Feed AddThis share icon
 

Record Details

Record 1 of 1
A 3D Active Learning Application for NeMO-Net, the NASA Neural Multi-Modal Observation and Training Network for Global Coral Reef Assessment
NTRS Full-Text: Click to View  [PDF Size: 255 KB]
Author and Affiliation:
van den Bergh, Jarrett(Bay Area Environmental Research Inst., Moffett Field, CA, United States)
Schutz, Joey(Bay Area Environmental Research Inst., Moffett Field, CA, United States)
Li, Alan(Bay Area Environmental Research Inst., Moffett Field, CA, United States)
Chirayath, Ved(NASA Ames Research Center, Moffett Field, CA, United States)
Abstract: NeMO-Net, the NASA neural multi-modal observation and training network for global coral reef assessment, is an open-source deep convolutional neural network and interactive active learning training software aiming to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology as well as mapping of spatial distribution. We present an interactive video game prototype for tablet and mobile devices where users interactively label morphology classifications over mm-scale 3D coral reef imagery captured using fluid lensing to create a dataset that will be used to train NeMO-Nets convolutional neural network. The application currently allows for users to classify preselected regions of coral in the Pacific and will be expanded to include additional regions captured using our NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as lower-resolution airborne remote sensing data from the ongoing NASA CORAL campaign. Active learning applications present a novel methodology for efficiently training large-scale Neural Networks wherein variances in identification can be rapidly mitigated against control data. NeMO-Net periodically checks users input against pre-classified coral imagery to gauge their accuracy and utilize in-game mechanics to provide classification training. Users actively communicate with a server and are requested to classify areas of coral for which other users had conflicting classifications and contribute their input to a larger database for ranking. In partnering with Mission Blue and IUCN, NeMO-Net leverages an international consortium of subject matter experts to classify areas of confusion identified by NeMO-Net and generate additional labels crucial for identifying decision boundary locations in coral reef assessment.
Publication Date: Dec 14, 2017
Document ID:
20170012202
(Acquired Dec 19, 2017)
Subject Category: EARTH RESOURCES AND REMOTE SENSING
Report/Patent Number: ARC-E-DAA-TN46257
Document Type: Conference Paper
Meeting Information: AGU Fall Meeting; 11-15 Dec. 2017; New Orleans, LA; United States
Meeting Sponsor: American Geophysical Union; Washington, DC, United States
Contract/Grant/Task Num: NNX12AD05A
Financial Sponsor: NASA Ames Research Center; Moffett Field, CA, United States
Organization Source: NASA Ames Research Center; Moffett Field, CA, United States
Description: 1p; In English
Distribution Limits: Unclassified; Publicly available; Unlimited
Rights: Copyright; Public use permitted
NASA Terms: EDUCATION; NEURAL NETS; THREE DIMENSIONAL MODELS; CORAL REEFS; IMAGING TECHNIQUES; APPLICATIONS PROGRAMS (COMPUTERS); MORPHOLOGY; CLASSIFICATIONS; REMOTE SENSING; PROTOTYPES; AERIAL RECONNAISSANCE
Other Descriptors: 3D; LEARNING; NEMO=NET; NASA
Availability Notes: Abstract Only
› Back to Top
Find Similar Records
NASA Logo, External Link
NASA Official: Gerald Steeman
Site Curator: STI Program
Last Modified: December 19, 2017
Contact Us