Video Based Machine Learning for Traffic Intersections

Video Based Machine Learning for Traffic Intersections describes the development of computer vision and machine learning-based applications for Intelligent Transportation Systems (ITS) and the challenges encountered during their deployment. This book presents several novel approaches, including a two-stream convolutional network architecture for vehicle detection, tracking, and near-miss detection; an unsupervised approach to detect near-misses in fisheye intersection videos using a deep learning model combined with a camera calibration and spline-based mapping method; and algorithms that utilize video analysis and signal timing data to accurately detect and categorize events based on the phase and type of conflict in pedestrian-vehicle and vehicle-vehicle interactions.

The book makes use of a real-time trajectory prediction approach, combined with aligned Google Maps information, to estimate vehicle travel time across multiple intersections. Novel visualization software, designed by the authors to serve traffic practitioners, is used to analyze the efficiency and safety of intersections. The software offers two modes: a streaming mode and a historical mode, both of which are useful to traffic engineers who need to quickly analyze trajectories to better understand traffic behavior at an intersection.

Overall, this book presents a comprehensive overview of the application of computer vision and machine learning to solve transportation-related problems. Video Based Machine Learning for Traffic Intersections demonstrates how these techniques can be used to improve safety, efficiency, and traffic flow, as well as identify potential conflicts and issues before they occur. The range of novel approaches and techniques presented offers a glimpse of the exciting possibilities that lie ahead for ITS research and development.

Key Features:

• Describes the development and challenges associated with Intelligent Transportation Systems (ITS)
• Provides novel visualization software designed to serve traffic practitioners in analyzing the efficiency and safety of an intersection
• Has the potential to proactively identify potential conflict situations and develop an early warning system for real-time vehicle-vehicle and pedestrian-vehicle conflicts

「基於視頻的機器學習在交通路口的應用」描述了在智能交通系統（ITS）中開發基於計算機視覺和機器學習的應用程序以及在部署過程中遇到的挑戰。本書提出了幾種新穎的方法，包括一種用於車輛檢測、跟踪和近距離錯過檢測的雙流卷積網絡架構；一種無監督方法，使用深度學習模型結合相機校準和基於樣條的映射方法，在魚眼路口視頻中檢測近距離錯過；以及利用視頻分析和信號定時數據的算法，根據行人-車輛和車輛-車輛交互的階段和衝突類型準確檢測和分類事件。

本書利用實時軌跡預測方法結合對齊的Google Maps信息，估計多個路口的車輛行駛時間。作者設計的新穎可視化軟件用於交通從業人員分析路口的效率和安全性。該軟件提供兩種模式：流式模式和歷史模式，對於需要快速分析軌跡以更好地理解路口交通行為的交通工程師非常有用。

總的來說，本書全面介紹了計算機視覺和機器學習在解決交通相關問題中的應用。《基於視頻的機器學習在交通路口的應用》展示了這些技術如何用於提高安全性、效率和交通流量，以及在問題發生之前識別潛在衝突和問題的能力。所提出的新穎方法和技術範圍展示了ITS研究和開發的令人興奮的可能性。

主要特點：
- 描述了智能交通系統（ITS）的開發和相關挑戰
- 提供了專為交通從業人員設計的新穎可視化軟件，用於分析路口的效率和安全性
- 有潛力主動識別潛在衝突情況，並為實時車輛-車輛和行人-車輛衝突開發早期警報系統

Tania Banerjee, PhD, is a research assistant scientist in Computer and Information Science and Engineering at the University of Florida. She earned her PhD in Computer Science from the University of Florida in 2012. She completed her MSc in Mathematics from the Indian Institute of Technology, Kharagpur. Her research interests are video analytics, intelligent transportation, data compression, and high performance computing.

Xiaohui Huang, PhD, earned her PhD in the Department of Computer & Information Science & Engineering, University of Florida, Gainesville, Florida, in December, 2020. Her research interests include machine learning, computer vision, and intelligent transportation systems.

Aotian Wu is currently a PhD student in the Department of Computer & Information Science & Engineering, University of Florida, Gainesville, Florida. Her research interests are machine learning, computer vision, and intelligent transportation systems.

Ke Chen is currently a PhD student in the Department of Computer & Information Science & Engineering, University of Florida, Gainesville, Florida. His research interests are machine learning, computer architecture, operating systems and algorithms, and data structures.

Anand Rangarajan, PhD, is a Professor, Department of CISE, University of Florida. His research interests are machine learning, computer vision, medical and hyperspectral imaging, and the science of consciousness.

Sanjay Ranka, PhD, is a Distinguished Professor in the Department of Computer Information Science and Engineering at University of Florida. His current research interests are high performance computing and big data science with a focus on applications in CFD, healthcare and transportation. He has co-authored four books and 290+ journal and refereed conference articles. He is a Fellow of the IEEE and AAAS. He is an Associate Editor-in-Chief of the Journal of Parallel and Distributed Computing and an Associate Editor for ACM Computing Surveys, Applied Sciences, Applied Intelligence, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

Tania Banerjee, PhD，是佛羅里達大學計算機與資訊科學與工程系的研究助理科學家。她於2012年在佛羅里達大學獲得計算機科學博士學位。她在印度理工學院哈拉格普爾分校獲得數學碩士學位。她的研究興趣包括視頻分析、智能交通、數據壓縮和高性能計算。

Xiaohui Huang, PhD，於2020年12月在佛羅里達大學計算機與資訊科學與工程系獲得博士學位。她的研究興趣包括機器學習、計算機視覺和智能交通系統。

Aotian Wu目前是佛羅里達大學計算機與資訊科學與工程系的博士生。她的研究興趣包括機器學習、計算機視覺和智能交通系統。

Ke Chen目前是佛羅里達大學計算機與資訊科學與工程系的博士生。他的研究興趣包括機器學習、計算機架構、操作系統和算法以及數據結構。

Anand Rangarajan, PhD，是佛羅里達大學CISE系的教授。他的研究興趣包括機器學習、計算機視覺、醫學和高光譜成像以及意識科學。

Sanjay Ranka, PhD，是佛羅里達大學計算機資訊科學與工程系的傑出教授。他目前的研究興趣是高性能計算和大數據科學，專注於在流體力學、醫療保健和交通領域的應用。他共同撰寫了四本書和290多篇期刊和會議論文。他是IEEE和AAAS的會士。他是《並行與分佈式計算期刊》的副主編，也是《ACM Computing Surveys》、《Applied Sciences》、《Applied Intelligence》和《IEEE/ACM Transactions on Computational Biology and Bioinformatics》的副編輯。