Tilted Object Height Measurement via Angle and Ground Point Estimation in Single View Image

Extracting accurate information from video data in the surveillance system plays a key role in understanding the field situation and solving the problem. In this paper, a new method for estimating the height of a tilted object from a single image is proposed. The existing single view metrology method has the limitation that it can be applied only when the object is perpendicular to the ground. On the other hand, the proposed method is designed to be able to estimate the height even if the object is not perpendicular. The tilted angle of the object was estimated through gravity direction detection and the ground point was estimated by using the estimated angle and geometric characteristics. Using the estimated tilt and ground point, the actual tilted angle and vertical height of the distorted object in the image can be estimated, and finally the height of the tilted object can be accurately measured. As a result of the experiment, the proposed method achieved the average error 1.09 cm and the average error ratio 1.21% to the object, proving the accurate estimation performance close to the actual object height.