Austin McEver

Marine Applied Research and Exploration (MARE) has collected hundreds of hours of video using their unmanned underwater vehicles and annotated each video with species and habitat labels. We are adapting scene recognition algorithms to their video in order to predict habitat temporal spans, and, later, recognize and detect vertebrate and invertebrate species. See some preliminary results in the video to the left.

The Marine Science Institute at UCSB has worked to photograph the sea floor near the Channel Islands and annotate their data using point labels. We are adapting state of the art algorithms for segmenting natural images to work with their data. With this small amount of additional supervision, we can achieve impressive semantic segmentation results comparable with fully supervised methods by using convolutional neural networks to learn semantic affinity and localization cues.

BisQue is an open source platform for storing, visualizing, organizing, and analyzing images in the cloud, largely maintained by UCSB’s Vision Research Lab. My responsibilities include software engineering tasks such as integrating Keycloak user authentication, developing machine learning modules for public use, assisting with Docker issues, and advising undergraduate research students who participate in the project.

Superpixels refer to an over segmentation used to group pixels into homogenous regions based on some criteria. They have numerous applications, but describing them computationally is not as straightforward or powerful as it could be. I am working to adapt new convolutional neural networks (CNNs) that generate superpixels to simultaneously generate deep features for those superpixels.