The Effect of Physics-Based Corrections and Data Augmentation on Transfer Learning for Segmentation of Benthic Imagery
Autor: | Blair Thornton, Takaki Yamada, Jenny Walker, Adam Prügel-Bennett |
---|---|
Rok vydání: | 2019 |
Předmět: |
0303 health sciences
0209 industrial biotechnology Artificial neural network business.industry 02 engineering and technology Image segmentation Remotely operated underwater vehicle Automation Metadata 03 medical and health sciences 020901 industrial engineering & automation Segmentation Computer vision Artificial intelligence Underwater Transfer of learning business 030304 developmental biology |
Zdroj: | 2019 IEEE Underwater Technology (UT). |
Popis: | Ocean observation has been greatly improved by the use of Autonomous Underwater Vehicles and Remotely Operated Vehicles, and the high quality and high quantity of imagery they produce. This quantity of images collected on research cruises has, however, become intractable using traditional manual image analysis methods. There is a growing need for automation of this process, using methods such as deep learning to analyse and summarise the information present, yet research into how to improve their performance for underwater images is currently limited. This paper presents a study into the effect of using physics-based corrections and data augmentation to aid the performance of DeepLabV3, a state of the art image segmentation system. Using metadata about the physical environment the images were taken in, particularly the altitude of the vehicle for each image, and the known wavelength dependent light attenuation over distance through water, reduces the generalisation error of the DeepLabV3 system. |
Databáze: | OpenAIRE |
Externí odkaz: |