We present a deep learning, computer vision algorithm constructed for the purposes of identifying and classifying charged particles in camera image sensors. We apply our algorithm to data collected by the Distributed Electronic Cosmic-ray Observatory (DECO), a global network of smartphones that monitors camera image sensors for the signatures of cosmic rays and other energetic particles, such as those produced by radioactive decays. The algorithm, whose core component is a convolutional neural network, achieves classification performance comparable to human quality across four distinct DECO event topologies. We apply our model to the entire DECO data set and determine a selection that achieves ≥ 90% purity for all event types. In particular, we estimate a purity of 95% when applied to cosmic-ray muons. The automated classification is run on the public DECO data set in real time in order to provide classified particle interaction images to users of the app and other interested members of the public.
The total area of silicon in cell phone camera sensors worldwide surpasses that in any experiment to date. Based on semiconductor technology similar to that found in modern astronomical telescopes and particle detectors, these sensors can detect ionizing radiation in addition to photons. The Distributed Electronic Cosmic-ray Observatory (DECO) uses the global network of active cell phones in order to detect cosmic rays and other energetic particles such as those produced by radioactive decays. DECO consists of an Android application, database, and public data browser available to citizen scientists around the world (https://wipac.wisc.edu/deco). Candidate cosmicray events have been detected on all seven continents and can be categorized by the morphology of their corresponding images. We present the DECO project, a novel particle detector with wide applications in public outreach and education.
Some robotic localization methods, such as ultra wideband localization and lighthouse localization, require external localization infrastructure in order to operate. However, there are situations where this localization infrastructure does not exist in the field, such as robotic exploration tasks. Deploying low power wireless sensor networks (WSNs) as localization infrastructure can potentially solve this problem. In this work, we demonstrate the use of an OpenWSN network of miniaturized low power sensor nodes as localization infrastructure. We demonstrate a quadrotor performing laser-based relative bearing measurements of stationary wireless sensor nodes with known locations and using these measurements to localize itself. These laser-based measurements require little computation on the WSN nodes, and are compatible with state-of-the-art 2 mm × 3 mm monolithic wireless system-on-chips (SoCs). These capabilities were demonstrated on a Crazyflie quadcopter using an Extended Kalman Filter and a network of motes running the OpenWSN wireless sensor network stack. The RMS error for X positioning was 0.57 m and the error for Y positioning was 0.39 m. This is the first use of an OpenWSN sensor network to support robotic localization. Furthermore, simulations show that these same measurements could be used for localizing sensor motes with unknown locations in the future.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.