Image projection method for vehicle speed estimation model in video system

Abstract

Recent developments in Information and Communication Technology have facilitated a new concept of Smart City to the world. The Smart City concept is driven by technology intervention in every aspect of city life, including the most dynamic and unpredictable transport management. Intelligent transport management system (ITMS) is the most essential component of a Smart City ecosystem. The primary function is to ensure smooth and accident-free transport on the city roads. ITMS can prompt drivers of possible traffic jams; ITMS can be used to detect speed violations of vehicles. One of the primary inputs to ITMS is fed from closed circuit television (CCTV) installations on the roads. The main objective of the paper is to detect vehicles violating traffic rules especially over-speeding. The detection of over-speeding of a vehicle involves detection of vehicle, calculation and calibration of the distance traveled by the vehicle both on an image plane and real world. To calibrate the distance traveled by the vehicle, the geometric plane of the real world is projected onto the image plane. The projection onto the image plane helps in determining the actual distance traveled by the vehicle in the real world. After calibration of the distance traveled by the vehicle, speed calculation is performed. The accuracy of the algorithm to speed detection is 90.8%.

Vehicle dynamics prediction via adaptive robust unscented particle filter

“…Zheng et al 4 proposed and performed a piecewise linear frequency domain identification method relying on finite impulse response models to tackle the nonlinearity issue in the signal estimation problems. Anandhalli et al 5 proposed a method to detect vehicles violating traffic rules especially over-speeding. Herlambang et al 6 designed a H-infinity method for the state estimation of vehicle position.…”