caa a22 4500 60554106X CHVBK 20210128100914.0 cr unu---uuuuu 210128e20150601xx s 000 0 eng 10.1007/s00371-015-1092-0 doi (NATIONALLICENCE)springer-10.1007/s00371-015-1092-0 DTW-based kernel and rank-level fusion for 3D gait recognition using Kinect [Elektronische Daten] [Faisal Ahmed, Padma Paul, Marina Gavrilova] This paper presents a new 3D gait recognition method that utilizes the kinect skeleton data for representing the gait signature. We propose to use two new features, namely joint relative distance (JRD) and joint relative angle (JRA), which are robust against view and pose variations. The relevance of each JRD and JRA sequence in representing human gait is evaluated using a genetic algorithm. We also introduce a dynamic time warping-based kernel that takes a collection of JRD or JRA sequences as parameters and computes a dissimilarity measure between the training and the unknown sample. The proposed kernel can effectively handle variable walking speed without any need of extra pre-processing. In addition, we propose a rank-level fusion of JRD and JRA features that can boost the overall recognition performance greatly. The effectiveness of the proposed method is evaluated using a 3D skeletal gait database captured with a Kinect v2 sensor. In our experiments, rank level fusion of joint relative distance (JRD) and joint relative angle (JRA) achieves promising results, as compared against only JRD and only JRA-based gait recognition. Springer-Verlag Berlin Heidelberg, 2015 Gait recognition nationallicence Kinect v2 sensor nationallicence Joint relative distance nationallicence Joint relative angle nationallicence DTW-kernel nationallicence 3D skeleton nationallicence Ahmed Faisal Department of Computer Science, University of Calgary, Calgary, AB, Canada aut Paul Padma Department of Computer Science, University of Calgary, Calgary, AB, Canada aut Gavrilova Marina Department of Computer Science, University of Calgary, Calgary, AB, Canada aut The Visual Computer Springer Berlin Heidelberg 31/6-8(2015-06-01), 915-924 0178-2789 31:6-8<915 2015 31 371 https://doi.org/10.1007/s00371-015-1092-0 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00371-015-1092-0 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Ahmed Faisal Department of Computer Science, University of Calgary, Calgary, AB, Canada aut NATIONALLICENCE 700 1- Paul Padma Department of Computer Science, University of Calgary, Calgary, AB, Canada aut NATIONALLICENCE 700 1- Gavrilova Marina Department of Computer Science, University of Calgary, Calgary, AB, Canada aut NATIONALLICENCE 773 0- The Visual Computer Springer Berlin Heidelberg 31/6-8(2015-06-01), 915-924 0178-2789 31:6-8<915 2015 31 371