Sorry, you need to enable JavaScript to visit this website.

Glidar3DJ: A VIEW-INVARIANT GAIT IDENTIFICATION VIA FLASH LIDAR DATA CORRECTION

Citation Author(s):
Nasrin Sadeghzadehyazdi, Tamal Batabyal†, A. Glandon, Nibir K. Dhar, B. O. Familoni, K. M. Iftekharuddin, Scott T. Acton
Submitted by:
Scott Acton
Last updated:
16 September 2019 - 4:16pm
Document Type:
Poster
Document Year:
2019
Event:
Presenters:
Scott Acton
Paper Code:
1259

Abstract

Gait recognition is a leading remote-based identification method, suitable for applications in forensic cases, surveillance, and medical studies. We present Glidar3DJ, a model-based gait recognition methodology, using a skeleton model extracted from sequences generated by a single flash lidar camera. Compared with Kinect, a flash lidar camera has a drastically extended range (> 1000 meters) and its performance is not affected in outdoor. However, the low resolution and noisy imaging process of lidar negatively affects the performance of state-of-the-art skeleton-based systems, generating a significant number of outlier skeletons. We propose a rule-based filtering mechanism that adopts robust statistics to correct for erroneous skeleton joint measurements.

up
0 users have voted:

Files

icip2019_Glidar3DJ sa.pdf

(206)