Channel: PyData

Category: Science & Technology

Tags: pythonlearn to codeeducationsoftwarepydatalearncodinghow to programjuliaopensourcescientific programmingnumfocuspython 3tutorial

Description: Speaker: Dr. Jagadeeswaran Rathinavel, Wi-Tronix LLC Trespassing and grade crossing are the two leading causes of railroad fatalities. Federal Railroad Administration (FRA) regulations require maintenance and inspections of active highway-rail grade crossings, which are invaluable and necessary, but very time-consuming and costly tasks. Wi-Tronix has the global vision of saving lives and ensuring the most efficient and reliable movement of goods and people throughout the world’s railroad networks by applications of computer vision. We design our system so that as locomotives pass through crossings, videos are recorded by forward-facing cameras installed on lead locomotives. Based on the locomotives’ locations and other conditions, videos are continuously uploaded to our cloud storage. Our system augments human inspectors by analyzing those videos and provides almost real-time intelligence to railroad operators. Recent innovations in deep convolutional neural networks for object detection and tracking make them a potential candidate for automated railroad monitor. Deep neural networks are trained using the data gathered and continuously improved as the fleets and seasons change. This talk will provide an overview of our system and lay out the challenges in building such a system. We will provide a brief demonstration of using an object detector and tracker neural network. Bio: Jagadeeswaran Rathinavel is an applied mathematician and data scientist with more than 10 years of experience in building software and systems. In his current role at Wi-Tronix Llc, Jags develops deep-learning computer-vision systems and algorithms for railroad safety and operations. He also works with researchers at IIT-Chicago in developing open-source quasi-Monte Carlo software (QMCPy). pydata.org PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome! 00:10 Help us add time stamps or captions to this video! See the description for details. Want to help add timestamps to our YouTube videos to help with discoverability? Find out more here: github.com/numfocus/YouTubeVideoTimestamps