Detection of 3D bounding boxes of vehicles using perspective transformation for accurate speed measurement
- PDF / 5,351,880 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 110 Downloads / 190 Views
ORIGINAL PAPER
Detection of 3D bounding boxes of vehicles using perspective transformation for accurate speed measurement Viktor Kocur1
· Milan Ftáˇcnik1
Received: 29 March 2020 / Revised: 4 August 2020 / Accepted: 20 August 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Detection and tracking of vehicles captured by traffic surveillance cameras is a key component of intelligent transportation systems. We present an improved version of our algorithm for detection of 3D bounding boxes of vehicles, their tracking and subsequent speed estimation. Our algorithm utilizes the known geometry of vanishing points in the surveilled scene to construct a perspective transformation. The transformation enables an intuitive simplification of the problem of detecting 3D bounding boxes to detection of 2D bounding boxes with one additional parameter using a standard 2D object detector. Main contribution of this paper is an improved construction of the perspective transformation which is more robust and fully automatic and an extended experimental evaluation of speed estimation. We test our algorithm on the speed estimation task of the BrnoCompSpeed dataset. We evaluate our approach with different configurations to gauge the relationship between accuracy and computational costs and benefits of 3D bounding box detection over 2D detection. All of the tested configurations run in real time and are fully automatic. Compared to other published state-of-the-art fully automatic results, our algorithm reduces the mean absolute speed measurement error by 32% (1.10 km/h to 0.75 km/h) and the absolute median error by 40% (0.97 km/h to 0.58 km/h). Keywords Traffic surveillance · 3D object detection · Deep learning · Perspective transformation
1 Introduction Recent development in commercially available cameras has increased the quality of recorded images and decreased the costs required to install cameras in traffic surveillance scenarios. Automatic traffic surveillance aims to provide information about the surveilled vehicles such as their speed, type and dimensions and as such is an important aspect of intelligent transportation system design. Automatic traffic surveillance system requires an accurate way of detecting the vehicles in the image and an accurate calibration of the recording equipment.
Electronic supplementary material The online version of this article (https://doi.org/10.1007/s00138-020-01117-x) contains supplementary material, which is available to authorized users.
B 1
Viktor Kocur [email protected] Department of Applied Informatics, Faculty of Mathematics, Physics and Informatics of Comenius University in Bratislava, Mlynská Dolina, 841 01Bratislava, Slovakia
Standard procedures of camera calibration require a calibration pattern or measurement of distances on the road plane. Dubská et al. [8] proposed a fully automated camera calibration for the traffic surveillance scenario. We use an improved version [33] of this method to obtain the camera calibration and focus on the accuracy
Data Loading...
