Timezone: »

xView3-SAR: Detecting Dark Fishing Activity Using Synthetic Aperture Radar Imagery
Fernando Paolo · Tsu-ting Tim Lin · Ritwik Gupta · Bryce Goodman · Nirav Patel · Daniel Kuster · David Kroodsma · Jared Dunnmon

Tue Nov 29 09:00 AM -- 11:00 AM (PST) @ Hall J #1018

Unsustainable fishing practices worldwide pose a major threat to marine resources and ecosystems. Identifying vessels that do not show up in conventional monitoring systems---known as ``dark vessels''---is key to managing and securing the health of marine environments. With the rise of satellite-based synthetic aperture radar (SAR) imaging and modern machine learning (ML), it is now possible to automate detection of dark vessels day or night, under all-weather conditions. SAR images, however, require a domain-specific treatment and are not widely accessible to the ML community. Maritime objects (vessels and offshore infrastructure) are relatively small and sparse, challenging traditional computer vision approaches. We present the largest labeled dataset for training ML models to detect and characterize vessels and ocean structures in SAR imagery. xView3-SAR consists of nearly 1,000 analysis-ready SAR images from the Sentinel-1 mission that are, on average, 29,400-by-24,400 pixels each. The images are annotated using a combination of automated and manual analysis. Co-located bathymetry and wind state rasters accompany every SAR image. We also provide an overview of the xView3 Computer Vision Challenge, an international competition using xView3-SAR for ship detection and characterization at large scale. We release the data (\href{https://iuu.xview.us/}{https://iuu.xview.us/}) and code (\href{https://github.com/DIUx-xView}{https://github.com/DIUx-xView}) to support ongoing development and evaluation of ML approaches for this important application.

Author Information

Fernando Paolo
Tsu-ting Tim Lin (Cambrio)
Ritwik Gupta (University of California, Berkeley)
Bryce Goodman
Nirav Patel (Defense Innovation Unit)
Daniel Kuster (Cambrio)

CEO, Cambrio

David Kroodsma
Jared Dunnmon (Stanford University)

-- Postdoctoral scholar with Prof. Chris Re at Stanford University -- Foci include multi-modal weak supervision and data augmentation

More from the Same Authors