Abstract
Automobiles have increased urban mobility, but traffic accidents have also increased. Therefore, road safety is a significant concern involving academics and government. Transit studies are the main supply for studying road accidents, congestion, and flow traffic, allowing the understanding of traffic flow. They require special equipment (sensors) to measure the car’s speed. With technological advances, artificial intelligence, and videos, it is possible to estimate the speed in real-time without modifying the installed urban infrastructure. We need to employ public databases that provide reliable monocular videos to generate automated traffic studies. The problem of speed estimation with a monocular camera involves synchronizing data recording, tracking, and detecting the vehicles over the road considering the lanes and distance between cars. Usually, a set of constraints are considered, such as camera calibration, flat roads, including methods based on the homography and augmented intrusion lines, patterns or regions, or prior knowledge about the actual dimensions of some of the objects. In this paper, we present a system that generates a dataset from videos recorded from a highway—obtaining 532 samples; we separated the vehicle’s detection by lane, estimating its speed. We use this data set to compare five different statistical methods and three machine learning methods to evaluate their accuracy in estimating the cars’ speed in real-time. Our vehicle estimation requires a feature extraction process using YOLOv3 and Kalman filter to detect and track vehicles. The Linear Regression Model (LRM) yielded the best results obtaining a Mean Absolute Error (MAE) of 1.694 km/h for the center lane and 0.956 km/h for the last lane. The results were compared with several state-of-the-art works, having competitive performance. Hence, LRM is fast estimating speed in real time and does not require high computational resources allowing a future hardware implementation.
Highlights
We describe the method used to obtain the speed estimation, classified according to physical formulas, pixels proportion, or machine learning algorithms (e.g., YOLO v2, CNN)
We present the precision of each work, allowing us to observe the main differences and that the speed estimation is still an open problem to solve
The results of this work will show the realization of the dataset and the performance of the learning models used for speed estimation
Summary
Association for Safe International Road Travel (ASIRT), more than 1.3 million people die each year in traffic accidents. Between 20 and 50 million people are injured, or disabled [1]. In the event of an accident, the most significant responsibility falls on the driver of the car [2]. Among the main factors that cause traffic accidents are speeding, distracted driving, obstacles on the road, poor signaling, state of the road infrastructure, and lighting. Perspective Transform to obtein of distance traveled by the vehicle, calculate the speed with the distance and time. It uses the distance between 2 points and the time it takes for vehicles to cross those 2 points. Use the tracking algorithm to obtain the distance traveled by the vehicle and use the time
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
