Weight estimation from frame sequences using computational intelligence techniques

Abstract

Soft biometric techniques can perform a fast and unobtrusive identification within a limited number of users, be used as a preliminary screening filter, or combined in order to increase the recognition accuracy of biometric systems. The weight is a soft biometric trait which offers a good compromise between distinctiveness and permanence, and is frequently used in forensic applications. However, traditional weight measurement techniques are time-consuming and have a low user acceptability. In this paper, we propose a method for a contactless, low-cost, unobtrusive, and unconstrained weight estimation from frame sequences representing a walking person. The method uses image processing techniques to extract a set of features from a pair of frame sequences captured by two cameras. Then, the features are processed using a computational intelligence approach, in order to learn the relations between the extracted characteristics and the weight of the person. We tested the proposed method using frame sequences describing eight different walking directions, and captured in uncontrolled light conditions. The obtained results show that the proposed method is feasible and can achieve a view-independent weight estimation, also without the need of computing a complex model of the body parts.

What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics

“…This work proceeded also to evaluate -based on the same measurements -the subjects' height and gender, using realtime reduced-complexity 3D model fitting. A related work for weight estimation by Labati et al [134] studied frame sequences representing walking subjects, where different walking directions and lighting conditions were used to challenge the algorithms. Features such as body height, body volume (estimated by ellipses passing through the silhouettes), body shape and walking direction were extracted to train a neural network towards body weight estimation.…”

Show me your face and I will tell you your height, weight and body mass index

“…In addition, an automated and Kinect based weight estimation [15] from full-body shots obtained weight estimation error of 4% in a small dataset of 15 subjects. Furthermore a related work for weight estimation by Labati et al [16] studied frame sequences representing walking subjects. Under specific video acquisition from calibrated cameras, body height, body volume (estimated by ellipses passing through the silhouettes), body shape and walking direction were extracted, to train a neural network towards body weight estimation.…”

“…This is marginally larger than the weight estimation, given several precise body-measurements [14], which constituted in reportedly less than 10% in 93% of the cases. Kinectaided weight estimation based on body images has shown though a significantly better performance [15], [16]. The associated human accuracy is though rather imprecise too, with 47% of estimates at least 10% different and 19% of estimates at least 20% different from the measured values [17].…”

Body Weight Estimation for Dose-Finding and Health Monitoring of Lying, Standing and Walking Patients Based on RGB-D Data

“…Beside the body weight estimation from a single frame, it is also possible to estimate it by a sequence of sensor data. Labati et al [ 27 ] developed a body weight estimation suitable for walking persons. The focus was set on a contact-less and low-cost method.…”