Intelligent traffic monitoring using video data mining

使用视频数据挖掘的智能交通监控

• 批准号: 566707-2021
• 负责人: Azim, Akramul
• 金额: $ 1.5万
• 依托单位: University of Ontario Institute of Technology
• 依托单位国家: 加拿大
• 项目类别: Alliance Grants
• 财政年份: 2021
• 资助国家: 加拿大
• 起止时间: 2021-01-01 至 2022-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=723629
• 关键词: Intelligent; traffic; monitoring; using; video

Intelligent traffic monitoring systems need to provide continuous service with appropriate adaptation in various dynamic situations. To ensure performance guarantees, we need to have sufficient knowledge of the system and its properties. A transportation system needs to have sufficient knowledge of its situations and its subsequent changes, which can be obtained from video streams. It is necessary for the system to have a prior knowledge of its interactions with various objects of the environment involving different timing constraints to ensure safe and correct operations. It is also essential for the system to extract timing properties by mining video data, and understand the flow of execution through creating a knowledge base. Our aim is to create a knowledge base called VideoMine from the monitored video stream containing traffic information of various objects. Our objectives also include that accessing information from VideoMine will consume significantly less memory, allow faster information processing, and help to identify, analyze and validate safety aspects.

智能交通监控系统需要在各种动态情况下提供适当适应的连续服务。为了确保性能保证，我们需要对系统及其属性有足够的了解。运输系统需要对其情况及其后续更改有足够的了解，这可以从视频流中获得。系统有必要对其与涉及不同正时约束的环境的各种对象的相互作用进行事先了解，以确保安全和正确的操作。对于系统而言，通过挖掘视频数据来提取正时属性，并通过创建知识库来理解执行流也至关重要。我们的目的是从包含各种对象的流量信息的受监视视频流中创建一个称为视频的知识库。我们的目标还包括从视频中访问信息将消耗大大减少内存，允许更快的信息处理，并帮助识别，分析和验证安全方面。