A new approach to obtain height measurements from video

Over the last few years computer based signal processing has become more prominent in forensic image analysis. Using the processing power of computers and the advances in mathematical algorithms it is now possible to generate a wealth of information from an image once it has been digitized. It has already been recognised that the image quality from many CCTV systems is generally too poor for facial recognition. However, there are other human characteristics which allow us to recognise individuals from a distance long before other aspects of their person become distinguishable. One of these parameters is a human's height. In this paper a new measurement algorithm is presented which generates height measurements and their associated errors from a single known physical measurement in an image. The method draws on results from projective geometry and computer vision. A height measurement is obtained from each frame of the video. A "stereo like" correspondence between images is not required. Nor is any explicit camera calibration. The accuracy of the algorithm is demonstrated by a number of examples where ground truth is known. Finally, the height measurements and their variation are described for a person in motion. We draw attention to the uncertainty in heights associated with humans in motion, and the limitations of using this description for identification.