Index Catalog // Deep Blue Data

Start Over

Filtering by: Creator Skinner, Katherine A Discipline Engineering

Machine Learning for Shipwreck Segmentation from Side Scan Sonar Imagery: Dataset and Benchmark, AI4Shipwrecks Dataset

Creator:

Sheppard, Anja, Sethuraman, Advaith V, Bagoren, Onur, Pinnow, Christopher, Anderson, Jamey, Havens, Timothy C, and Skinner, Katherine A

Description:

The AI4Shipwrecks dataset contains sidescan sonar images of shipwrecks and corresponding binary labels collected during 2022 and 2023 at the NOAA Thunder Bay National Marine Sanctuary in Alpena, MI. The data collection platform was an Iver3 Autonomous Underwater Vehicle (AUV) equipped with an EdgeTech 2205 dual-frequency ultra-high resolution sidescan sonar and 3D bathymetric system. The labels were compiled from reference labels created by experts in marine archaeology. The intended use of this dataset is to encourage development of semantic segmentation, object detection, or anomaly detection algorithms in the computer vision field. Comparisons of state-of-the-art segmentation networks on our dataset are shown in the paper. , The file structure is organized as described in the README.txt file, where images in 'images' directories are the waterfall product of sidescan sonar surveys, and images in 'labels' directories are binary representations of expert labels. Images across the 'images' and 'labels' directories are correlated by having identical filenames. In the label images, a pixel value of '0' represents the non-shipwreck/other class and '1' represents the shipwreck class for the correspondingly named image (<wreck_name>_<##>.png) in the images directory. , and The project webpage can be found at: https://umfieldrobotics.github.io/ai4shipwrecks/

Keyword:

machine learning, computer vision, field robotics, marine robotics, underwater robotics, sidescan sonar, semantic segmentation, and object detection

Discipline:

Engineering
Novel Sensors for Autonomous Vehicle Perception
User Collection

Creator:

Skinner, Katherine A, Vasudevan, Ram, Ramanagopal, Manikandasriram S, Ravi, Radhika, Buchan, Austin D, and Carmichael, Spencer

Description:

The Novel Sensors for Autonomous Vehicle Perception Collection of datasets are sequences collected with an autonomous vehicle platform including data from novel sensors. The dataset collection platform is a Ford Fusion vehicle with a roof-mounted novel sensing suite, which specifically consists of forward-facing stereo uncooled thermal cameras (FLIR 40640U050-6PAAX), event cameras (iniVation DVXplorer), monochrome cameras (FLIR BFS-PGE-16S2M), and RGB cameras (FLIR BFS-PGE-50S5C) time synchronized with ground truth poses from a high precision navigation system. Sequences include ~8 km routes, driven repeatedly under varying lighting conditions and/or opposing viewpoints. Further information and resources are available on the project website: https://umautobots.github.io/nsavp

Keyword:

novel sensing, perception, autonomous vehicles, thermal sensing, neuromorphic imaging, and event cameras

Citation to related publication:

https://umautobots.github.io/nsavp, https://github.com/umautobots/nsavp_tools, and https://sites.google.com/umich.edu/novelsensors2023

Discipline:

Engineering

12Works

Machine Learning for Shipwreck Segmentation from Side Scan Sonar Imagery: Dataset and Benchmark, AI4Shipwrecks Dataset

Novel Sensors for Autonomous Vehicle Perception

Limit your search

Resource type

Creator

Discipline

Search Results

Search Constraints

Search Results

Machine Learning for Shipwreck Segmentation from Side Scan Sonar Imagery: Dataset and Benchmark, AI4Shipwrecks Dataset

Novel Sensors for Autonomous Vehicle Perception

Limit your search

Resource type

Creator

Discipline