Journal
2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)
Volume -, Issue -, Pages 2635-2642Publisher
IEEE COMPUTER SOC
DOI: 10.1109/ICPR48806.2021.9412264
Keywords
Salt marsh monitoring; convolutional neural networks; network topology; attention mechanism; deep learning; ecological monitoring
Categories
Funding
- National Science Foundation [DBI-2016741]
- Georgia Coastal Ecosystems Long-Term Ecological Research program [OCE-1832178]
Ask authors/readers for more resources
Recent advancements in computer vision and machine learning, particularly deep convolutional neural networks (CNNs), are utilized to identify and localize various plant species in salt marsh images. Different approaches are explored to estimate abundance and spatial distribution at varying levels of granularity, with CNNs showing high precision and recall for more common plant species but reduced performance for less common ones. The study highlights a trade-off between CNN estimation quality and spatial resolution, offering insights for ecological applications of CNN-based approaches in automated plant identification and localization.
Recent advances in computer vision and machine learning, most notably deep convolutional neural networks (CNNs), are exploited to identify and localize various plant species in salt marsh images. Three different approaches are explored that provide estimations of abundance and spatial distribution at varying levels of granularity defined by spatial resolution. In the coarsest-grained approach, CNNs are tasked with identifying which of six plant species are present/absent in large patches within the salt marsh images. CNNs with diverse topological properties and attention mechanisms are shown capable of providing accurate estimations with > 90% precision and recall for the more abundant plant species and reduced performance for less common plant species. Estimation of percent cover of each plant species is performed at a finer spatial resolution, where smaller image patches are extracted and the CNNs tasked with identifying the plant species or substrate at the center of the image patch. For the percent cover estimation task, the CNNs are observed to exhibit a performance profile similar to that for the presence/absence estimation task, but with an approximate to 5%-10% reduction in precision and recall. Finally, fine-grained estimation of the spatial distribution of the various plant species is performed via semantic segmentation. The DeepLab-V3 semantic segmentation architecture is observed to provide very accurate estimations for abundant plant species, but with significant performance degradation for less abundant plant species; in extreme cases, rare plant classes are seen to be ignored entirely. Overall, a clear trade-off is observed between the CNN estimation quality and the spatial resolution of the underlying estimation thereby offering guidance for ecological applications of CNN-based approaches to automated plant identification and localization in salt marsh images.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available