A simplified nonlinear regression method for human height estimation in video surveillance

Abstract

This paper presents a simple camera calibration method for estimating human height in video surveillance. Given that most cameras for video surveillance are installed in high positions at a slightly tilted angle, it is possible to retain only three calibration parameters in the original camera model, namely the focal length, the tilting angle and the camera height. These parameters can be directly estimated using a nonlinear regression model from the observed head and foot points of a walking human instead of estimating the vanishing line and point in the image, which is extremely sensitive to noise in practice. With only three unknown parameters, the nonlinear regression model can fit data efficiently. The experimental results show that the proposed method can predict the human height with a mean absolute error of only about 1.39 cm from ground truth data.

What Face and Body Shapes Can Tell Us About Height

“…The height of standing people can be estimated geometrically from a single image under some fairly mild assumptions. This can be done by finding head position and foot contact through triangulation when the camera height and orientation in relation to the ground plane is known [14,21,47], computing the vanishing point of the ground plane and the height of a reference object in the scene [15,18], or accounting for the height of multiple nearby reference objects [18,23]. However, the necessary knowledge about camera pose, ground plane, and feet contact points is often unavailable.…”

“…For example, comparisons to the average height have been used in [9] to infer people's sizes from group pictures. Similarly, height inference in images acquired with calibrated cameras and in which the location of the ground plane is given [14,18,21,47] or where objects of known height are visible [18,23] have been demonstrated. The method of [4] is the only one we know of that can operate on single uncalibrated RGB images and without prior knowledge.…”

Automatic Distortion Rectification of Wide-Angle Images Using Outlier Refinement for Streamlining Vision Tasks

“…The results clearly state that the method used in Li, Shengzhe et al [32] is manual in a manner with the intrinsic-based height estimation, which can be termed as manual distortion-rectification-guided intrinsic-based height estimation (DR-IE) has an effect due to pixel irregularities. This inconsistency in pixel locations and corresponding error in metric information increases with the increase in the distortion levels.…”

“…Both the quantitative and qualitative analyses were dealt with using experiments where the distortions were rectified and thereby the intrinsic estimation and height calculations were performed. This process was done for both cases-the distortion rectification process proposed in this study as well as the manual rectification following the approach of Li, Shengzhe et al [32]. The accuracy in height measurements was estimated with a straightforward method of retrieving errors between the estimated and available ground truth.…”

Gravity as a Reference for Estimating a Person’s Height From Video

“…Placing multiple references is cumbersome and has been overcome by relating a single reference to other points in the scene through vanishing points of the ground plane [5,14,30]. An alternative is to manually calibrate the camera height and orientation in relation to the ground plane [12,31,18]. Thereby, the height of standing people can be inferred by locating the head and foot position in a single image, triangulating the 3D foot position on the known ground plane, and scaling the head-foot distance to this 3D position.…”