The high growth of vehicular travel in urban areas, in particular, requires a traffic control system that optimizes traffic flow efficiency. Traffic congestion can also occur by large de-lays in Red Light etc. The delay in lighting is difficult to code and does not rely on real traffic density. It follows that traffic controls are simulated and configured to better meet this rising demand. So, in order to avoid the traffic control problem, the Adaptive Intelligent Traffic Light control system (AITLCS) has been proposed based on OpenCV and Image processing technique. The system proposed is designed to ensure smooth and efficient traffic flow for daily life as well as emergency and public transportation safety. Based on the road density instead of the levels set the proposed system provides the timing for the traffic light signal so that a highly loaded side switched on over long periods compared with the other lanes. It can also be used at an intersection with traffic signs, which controls the traffic light signal at the intersection. If timers are smart to predict the exact time, the system is more efficient because it reduces the time spent on unintended green signal significantly. With the help of OpenCV software, this paper aims to have a signal management SMART solution that will be cost-effective at the end. The system consists of a camera facing a lane taking pictures of the route we want to travel and then the density of the pedestrian and vehicle is taken and compared with each image employing image processing. Such images are processed effectively to learn the density of traffic.

中文翻译：

---

基于OpenCV图像处理技术的照明智能控制系统设计

尤其是城市地区车辆出行的高速增长，需要优化交通流量效率的交通控制系统。交通拥堵也可能因红灯等的大量延迟而发生。照明延迟难以编码并且不依赖于实际交通密度。因此，对交通控制进行了模拟和配置，以更好地满足这种不断增长的需求。因此，为了避免交通控制问题，提出了基于OpenCV和图像处理技术的自适应智能交通灯控制系统（AITLCS）。所提出的系统旨在确保日常生活的顺畅和高效的交通流量以及紧急和公共交通安全。基于道路密度而不是设置的水平，建议的系统为交通灯信号提供时间，以便与其他车道相比，高负载侧长时间开启。也可用于有交通标志的路口，控制路口的红绿灯信号。如果计时器能够智能地预测准确时间，则系统效率更高，因为它显着减少了花在意外绿色信号上的时间。在OpenCV软件的帮助下，本文旨在拥有一个最终具有成本效益的信号管理SMART解决方案。该系统由一个面向车道的摄像头组成，拍摄我们想要行驶的路线，然后拍摄行人和车辆的密度，并与采用图像处理的每个图像进行比较。