A Secure Traffic Police Remote Sensing Approach via a Deep Learning-Based Low-Altitude Vehicle Speed Detector through UAVs in Smart Cites: Algorithm, Implementation and Evaluation

Abstract

Nowadays, the unmanned aerial vehicle (UAV) has a wide application in transportation. For instance, by leveraging it, we are able to perform accurate and real-time vehicle speed detection in an IoT-based smart city. Although numerous vehicle speed estimation methods exist, most of them lack real-time detection in different situations and scenarios. To fill the gap, this paper introduces a novel low-altitude vehicle speed detector system using UAVs for remote sensing applications of smart cities, forging to increase traffic safety and security. To this aim, (1) we have found the best possible Raspberry PI’s field of view (FOV) camera in indoor and outdoor scenarios by changing its height and degree. Then, (2) Mobile Net-SSD deep learning model parameters have been embedded in the PI4B processor of a physical car at different speeds. Finally, we implemented it in a real environment at the JXUST university intersection by changing the height (0.7 to 3 m) and the camera angle on the UAV. Specifically, this paper proposed an intelligent speed control system without the presence of real police that has been implemented on the edge node with the configuration of a PI4B and an Intel Neural Computing 2, along with the PI camera, which is armed with a Mobile Net-SSD deep learning model for the smart detection of vehicles and their speeds. The main purpose of this article is to propose the use of drones as a tool to detect the speeds of vehicles, especially in areas where it is not easy to access or install a fixed camera, in the context of future smart city traffic management and control. The experimental results have proven the superior performance of the proposed low-altitude UAV system rather than current studies for detecting and estimating the vehicles’ speeds in highly dynamic situations and different speeds. As the results showed, our solution is highly effective on crowded roads, such as junctions near schools, hospitals, and with unsteady vehicles from the speed level point of view.

Collaborative algorithm of workpiece scheduling and AGV operation in flexible workshop

“…For the path planning problem of AGV group, Dingding Yu et al (2021) first used an A Ã algorithm with penalty factor to generate a single path and then proposed a control method based on resource locking to avoid path conflicts between AGVs. Jahangir Moshayedi et al (2023) carried a field of view camera on unmanned aerial vehicles (UAVs) and trained single shot multiBox detector (SSD) deep learning networks with different vehicle speed models to achieve vehicle speed detection and estimation. For the multi-AGV path planning problem, Han et al (2017) designed a new three-point crossover method to generate offspring with the optimization goal of minimizing the total path length and minimizing the single path length and based on the genetic algorithm.…”

A Tube Model Predictive Control Method for Autonomous Lateral Vehicle Control Based on Sliding Mode Control

“…Under ideal conditions with no internal or external interference, the nominal system of the AV is given by Equation (11):…”

“…The effectiveness and rapidity of the method were verified on five different paths, making it valuable for researchers in the field of service robots. In a later study, they extended remote sensing applications to calibrate drone cameras accurately, ensuring precise detection of vehicle speed to enhance the operating efficiency of vehicles in congested road environments, thereby improving intelligent city services based on the Internet of Things [11]. Chu et al [12] proposed a trajectory-tracking framework based on the PID feedback method, with a steady-state error close to zero when finally tracking the curve.…”

Integrating Virtual Reality and Robotic Operation System (ROS) for AGV Navigation

“…Unity has recently gained widespread popularity in robotics simulation due to its user-friendly interface, real-time rendering capabilities, and robust support for 3D environments [3]. Conversely, ROS has become the industry-standard robotic software development platform, offering various functionalities such as real-time communication, perception, and control [4]. The integration of these two tools can enable researchers and engineers to construct highly realistic and sophisticated simulations that accurately represent their robots' real-world behavior [5,6].…”