Consumer Class Side Scanning Sonar Dataset for Human Detection

One of the leading problems for using modern deep neural networks with sonars is the lack of datasets, even rarer are datasets that are collected with consumer class sonars. This paper introduces a novel side scanning sonar dataset for humans under water. Data is collected with consumer class Garmin 8400 Xsv sonar with GT54UHD-TM transducer. Dataset is collected in shallow coastal water of the Baltic Sea, near Rauma Finland. The dataset contains 331 images of humans, and 364 images with other objects like tires and rocks. Dataset contains cropped images from objects, and full resolution images. Data is collected from two different locations, with different sonar settings. All images are from two rescue divers at the bottom of the sea. This Paper also introduces standard data split for collected dataset for training, validation, and test data for benchmarking different models with dataset, and the data collection system based on ROS.