One Small Step for a Man: Estimation of Gender, Age and Height from Recordings of One Step by a Single Inertial Sensor

Abstract

A number of previous works have shown that information about a subject is encoded in sparse kinematic information, such as the one revealed by so-called point light walkers. With the work at hand, we extend these results to classifications of soft biometrics from inertial sensor recordings at a single body location from a single step. We recorded accelerations and angular velocities of 26 subjects using integrated measurement units (IMUs) attached at four locations (chest, lower back, right wrist and left ankle) when performing standardized gait tasks. The collected data were segmented into individual walking steps. We trained random forest classifiers in order to estimate soft biometrics (gender, age and height). We applied two different validation methods to the process, 10-fold cross-validation and subject-wise cross-validation. For all three classification tasks, we achieve high accuracy values for all four sensor locations. From these results, we can conclude that the data of a single walking step (6D: accelerations and angular velocities) allow for a robust estimation of the gender, height and age of a person.

Motion-To-BMI: Using Motion Sensors to Predict the Body Mass Index of Smartphone Users

“…However, there was certainly room for future improvement. Riaz et al [11] recorded accelerations and angular velocities of 26 subjects using wearable motion sensors attached at four locations (chest, lower back, right wrist, and left ankle) when performing standardized gait tasks. They then trained random forest classifiers in order to estimate soft biometrics (gender, age, and height).…”

“…Data from motion sensors are also multi-dimensional with a special temporal-spatial structure for conventional feature-based approaches [10,11]. Furthermore, the design of a specific feature extractor that transforms raw data into feature vectors relies on heuristic hand-crafted feature engineering and considerable domain expertise.…”

“…(2) We define motion entropy (MEn), which is a measure of the regularity and complexity of the motion sensor, and propose a novel MEn-based filtering strategy to select parts of these sub-sequences for training the prediction model. (3) We evaluate the hybrid deep neural network model with the MEn-based filtering strategy using two public datasets in comparison with baseline conventional feature-based approaches that have been applied to infer simple human traits from gaits [10,11]. Experimental results show that the proposed model significantly outperforms the baseline methods.…”

Assessing Motor Fluctuations in Parkinson’s Disease Patients Based on a Single Inertial Sensor

“…The principles used to detect strides are based on Zijlstra et al work [64]. Although segmentation techniques can be employed to detect strides [65,66,67], we restrict to biomechanical properties of gait and the way they are observed in the acceleration signals to do so. More concretely, the beginning of the support phase of gait, that is when the heel touches the ground, can be detected by a local minimum in the front acceleration measured from the bottom of the trunk [64].…”

Age Estimation Robust to Optical and Motion Blurring by Deep Residual CNN

“…Human age estimation based on facial images is currently a hot research topic being applied in many areas, including demographic analysis, consumer analysis, visual surveillance, and aging process analysis [1,2]. To obtain an accurate age estimation, facial features containing age information need to be extracted from images captured by a camera.…”