Key points are not available for this paper at this time.
Rather than relying on public transportation, people are increasingly comfortable driving their automobiles to satisfy their mobility needs. Reasons for this include the automobiles' accessibility and the fact that they can be used whenever needed. Because of this, many cities around the world experience terrible traffic congestion and long wait periods at traffic signals. Smarter and more effective traffic management is possible through the integration of big data, the Internet of Things (IoT), and a cloud platform with a network of linked vehicles and sensors. The objective of this study is to estimate traffic conditions along a route and provide updates to the user. Initially, Deep Learning (DL) models such as YOLO (You Only Look Once) and SSD (Single-Shot Object Detection) are developed and tested to detect vehicles. YOLO produces outstanding performance in vehicle detection, with an 89.5% mean Average Precision (mAP) and an 83.98% Intersection over Union (IoU). This model is then pushed to the cloud. A Global Positioning System (GPS) module is used to determine the user's current location. Based on the user's location, the nearest camera is enabled, and the recorded video is sent to the cloud. The cloud-deployed YOLO model is used to detect and count vehicles. To improve the user experience, this study has created a mobile application. The software contains a navigation map function that allows users to specify the maximum number of vehicles expected along their route. The created system counts the number of vehicles on their path, and if the count exceeds the specified threshold, the mobile app notifies the user about traffic conditions.
Devi et al. (Wed,) studied this question.