Applied Artificial Intelligence
Article in Press
This paper presents GlidarPoly, an efficacious pipeline of 3D gait recognition for flash lidar data based on pose estimation and robust correction of erroneous and missing joint measurements. A flash lidar can provide new opportunities for gait recognition through a fast acquisition of depth and intensity data over an extended range of distance. However, the flash lidar data are plagued by artifacts, outliers, noise, and sometimes missing measurements, which negatively affects the performance of existing analytics solutions. We present a filtering mechanism that corrects noisy and missing skeleton joint measurements to improve gait recognition. Furthermore, robust statistics are integrated with conventional feature moments to encode the dynamics of the motion. As a comparison, length-based and vector-based features extracted from the noisy skeletons are investigated for outlier removal. Experimental results illustrate the superiority of the proposed methodology in improving gait recognition given noisy, low-resolution flash lidar data.
Original Publication Citation
Sadeghzadehyazdi, N., Batabyal, T., Glandon, A., Dhar, N., Familoni, B., Iftekharuddin, K., & Acton, S. T. (2022). Using skeleton correction to improve flash lidar-based gait recognition. Applied Artificial Intelligence, 1-33. https://doi.org/10.1080/08839514.2022.2043525
Sadeghzadehyazdi, Nasrin; Batabyal, Tamal; Glandon, Alexander; Dhar, Nibir; Familoni, Babajide; Iftekharuddin, Khan; and Acton, Scott T., "Using Skeleton Correction to Improve Flash Lidar-Based Gait Recognition" (2022). Electrical & Computer Engineering Faculty Publications. 324.