U.C. sAN DIEGO

ENGINEERS FOR EXPLORATION, A NATIONAL GEOGRAPHIC & NSF FUNDED PROGRAM

MACHINE LEARNING FOR MANGROVES PROJECT

The purpose of the project I worked was to monitor mangroves by using drones, advanced imaging sensors, and machine learning. I worked specifically with deep learning methods (convolutional neural networks) to perform Mangrove species classification.

why mangroves?

Mangroves are a coastal ecosystem that provides extremely valuable services: they sequester 2-4 times more carbon than tropical rainforests, protect coastlines from storm systems, and provide excellent fisheries. Unfortunately, mangroves are at risk due to human encroachment and the government lacks adequate information to provide effective enforcement to protect these sanctuaries.

international collaboration

Gulf of California Marine Program, Octavio Aburto Lab at Scripps Institute of Oceanography, and Engineers for Exploration traveled to La Paz, Mexico California Baja Sur to collect on-the-ground data with unmanned aerial vehicles. In addition to this, we performed field work to compare our data concerning the biomass of the three different Mangrove Species.

why machine learning?

The biggest advantages of utilizing machine learning methods versus traditional classification methods is time and cost. Convolutional Neural Networks (CNN's) are most commonly applied to analyzing visual imagery. The CNN that I primarily worked with were YOLOv3 and OpenCV.

work pipeline

data ACQUISITION

Our automated data collection plan was performing lawn mower flights, selecting low altitude photos for high quality, and randomly distributed low altitude photo collection. In addition to this, we performed calibration processes such as georeferencing control, color Calibration, and multispectral calibration.

Data Processing

Using Agisoft, I created an Orthomosaic of our 5,000+ drone image tiles

machine learning

We created and online labeling tool in Python to work with over a million image samples. I used this data to train my ML algorithms in OpenCV an YoloV3 frameworks.

Back to home page