Traffic surveillance is an important issue for Intelligent Transportation Systems (ITS) that helps detect incidents automatically, such as wrong-way drivers, still-standing vehicles and jams. Sometimes these systems require a fast and short-term deployment of video cameras. In these cases, ad-hoc networks could be a low-cost and feasible option, but they have poor performance for video delivery. Thus, we propose a smart live video adaptive streaming technique in order to transport video streams from the cameras to the external road traffic monitoring servers. To achieve this goal, these networks need a thorough study in order to analyze video quality under their inherent constraints, given by their specific topologies (once deployed), video streaming protocol, nodes’ performance and routing protocols. From our results both in simulated and real scenarios, we demonstrate the feasibility of our proposal in these specific scenarios, validated with several performance metrics in terms of Quality of Service and video quality.

交通监控是智能交通系统（ITS）的重要问题，它有助于自动检测错误的事件，例如错误的驾驶员，静止的车辆和堵塞。有时，这些系统需要快速且短期地部署摄像机。在这些情况下，ad-hoc网络可能是一种低成本且可行的选择，但它们在视频传递方面的性能较差。因此，我们提出了一种智能的实时视频自适应流技术，以便将视频流从摄像机传输到外部道路交通监控服务器。为了实现此目标，这些网络需要进行深入研究，以在其固有约束下分析视频质量，这些固有条件由其特定拓扑（一旦部署），视频流协议，节点性能和路由协议给定。