Research Repository

Pixelwise annotation of coral reef substrates

Wright, Jessica and Palosanu, Ioana-Lia and Clift, Louis and Garcia Seco De Herrera, Alba and Chamberlain, Jon (2021) Pixelwise annotation of coral reef substrates. In: CLEF 2021 – Conference and Labs of the Evaluation Forum, 2021-09-21 - 2021-09-24, Bucharest, Romania.

[img]
Preview
Text
ImageCLEF_paper-119.pdf - Published Version
Available under License Creative Commons Attribution.

Download (4MB) | Preview

Abstract

Coral reef substrate composition is regularly surveyed for ecosystem health monitoring. The current method of visual assessment is slow and limited in scale. ImageCLEFcoral aims to identify reef areas of interest and annotate them appropriately. We present an adaptation of a submission to the 2019 ImageCLEFcoral task that uses a semantic segmentation model, DeepLabV3, with a ResNet-101 backbone. We implemented pre-training image colour enhancement and supplemented the available training data with that of NOAA NCEI for specific runs. Our runs had no overall improvement from the 2019 code, though did predict submassive corals and table corals with greater accuracy (+3.022% and +0.353%). Though none of our model runs had the highest precision or accuracy, we did best predict submassive corals (3.022%), boulder corals (12.787%), table corals (0.353%), foliose corals (0.097%), gorgonian soft corals (0.002%) and algae (0.027%) across 3 of our 4 runs. Image colour enhancement benefited the prediction accuracy of boulder corals (+1.209−5.026%), encrusting corals (+1.7−2.578%) and algae (+0.027%), most likely by making them more distinct from their surroundings. Adding NOAA data enhanced the precision of encrusting coral, soft coral and gorgonian predictions despite only providing additional annotations for encrusting and foliose corals. Our results suggest that a more balanced approach to data augmentation combined with image-specific colour improvements may provide a more desirable outcome, particularly when paired with a model that is fine-tuned to the data set used.

Item Type: Conference or Workshop Item (Paper)
Divisions: Faculty of Science and Health
Faculty of Science and Health > Computer Science and Electronic Engineering, School of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 27 Sep 2022 13:02
Last Modified: 27 Sep 2022 13:02
URI: http://repository.essex.ac.uk/id/eprint/32073

Actions (login required)

View Item View Item