Traffic surveillance camera calibration by 3D model bounding box alignment for accurate vehicle speed measurement

• Published in: Computer vision and image understanding Vol. 161; pp. 87 - 98
• Main Authors: Sochor, Jakub, Juránek, Roman, Herout, Adam
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.08.2017
• Subjects: Bounding box alignment; Camera calibration; Fully automatic; Speed measurement; Traffic surveillance; Vanishing point detection; Speed measurement; Fully automatic; Traffic surveillance; Camera calibration; Bounding box alignment; Vanishing point detection
• ISSN: 1077-3142; 1090-235X
• DOI: 10.1016/j.cviu.2017.05.015

•Improved traffic camera calibration method based on vanishing points detection.•Automatic scene scale inference by alignment of 3D model bounding box.•Extensive experiments on a recent speed measurement dataset BrnoCompSpeed.•Results show that our method outpeforms manual camera calibration.•Mean speed measurement error of the method is 1.10 km/h. [Display omitted] In this paper, we focus on fully automatic traffic surveillance camera calibration, which we use for speed measurement of passing vehicles. We improve over a recent state-of-the-art camera calibration method for traffic surveillance based on two detected vanishing points. More importantly, we propose a novel automatic scene scale inference method. The method is based on matching bounding boxes of rendered 3D models of vehicles with detected bounding boxes in the image. The proposed method can be used from arbitrary viewpoints, since it has no constraints on camera placement. We evaluate our method on the recent comprehensive dataset for speed measurement BrnoCompSpeed. Experiments show that our automatic camera calibration method by detection of two vanishing points reduces error by 50% (mean distance ratio error reduced from 0.18 to 0.09) compared to the previous state-of-the-art method. We also show that our scene scale inference method is more precise, outperforming both state-of-the-art automatic calibration method for speed measurement (error reduction by 86 % – 7.98 km/h to 1.10 km/h) and manual calibration (error reduction by 19 % – 1.35 km/h to 1.10 km/h). We also present qualitative results of the proposed automatic camera calibration method on video sequences obtained from real surveillance cameras in various places, and under different lighting conditions (night, dawn, day).