DesPat: Smartphone-Based Object Detection for Citizen Science and Urban Surveys

نویسندگان

چکیده

Abstract Data acquisition is a central task in research and one of the largest opportunities for citizen science. Especially urban surveys investigating traffic people flows, extensive manual labor required, occasionally augmented by smartphones. We present DesPat, an app designed to turn wide range low-cost Android phones into privacy-respecting camera-based pedestrian tracking tool automatize data collection. This can then be used analyze patterns general, identify crowd hotspots bottlenecks, which are particularly relevant light recent COVID-19 pandemic. All image analysis done locally on device through convolutional neural network, thereby avoiding any privacy concerns or legal issues regarding video surveillance. show example heatmap visualizations from deployments our prototype areas compare performance variety discuss suitability on-device object detection usecase

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Smartphone-powered citizen science for bioacoustic monitoring

An initial classifier considers the main frequency component of the call, centered around 13.5 kHz and spanning mainly between 11 and 17 kHz. The ratio between this and a range where little noise is present (8–9 kHz) is a measure of the acoustic energy of the cicada call, as can be defined as: • Only cicada native to the UK • Only present in the New Forest • High pitched call at ~ 13.5 kHz • Di...

متن کامل

Safari Science: assessing the reliability of citizen science data for wildlife surveys

science data for wildlife surveys Cara Steger* , Bilal Butt and Mevin B. Hooten Natural Resource Ecology Lab, Department of Ecosystem Science and Sustainability, Colorado State University, Fort Collins, CO 80523-1499, USA; School for Environment and Sustainability, University of Michigan, Ann Arbor, MI 48103, USA; and U.S. Geological Survey, Colorado Cooperative Fish and Wildlife Research Unit,...

متن کامل

Lights, Camera…Citizen Science: Assessing the Effectiveness of Smartphone-Based Video Training in Invasive Plant Identification

The rapid growth and increasing popularity of smartphone technology is putting sophisticated data-collection tools in the hands of more and more citizens. This has exciting implications for the expanding field of citizen science. With smartphone-based applications (apps), it is now increasingly practical to remotely acquire high quality citizen-submitted data at a fraction of the cost of a trad...

متن کامل

Citizen Science for Citizen Access to Law

Over 2014, the Cornell University Legal Information Institute and the Australian National University worked with users of the Cornell LII site in a citizen science project to collect over 43,000 crowdsourced assessments of the readability of legal and other sentences. Readers (“citizen scientists”) on legislative pages of the LII site were asked to rate passages from the United States Code and ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: I-com

سال: 2021

ISSN: ['1618-162X', '2196-6826']

DOI: https://doi.org/10.1515/icom-2021-0012