3D people surveillance on range data sequences of a rotating Lidar

Abstract

In this paper, we propose an approach on real-time 3D people surveillance, with probabilistic foreground modeling, multiple person tracking and on-line re-identification. Our principal aim is to demonstrate the capabilities of a special range sensor, called rotating multi-beam (RMB) Lidar, as a future possible surveillance camera. We present methodological contributions in two key issues. First, we introduce a hybrid 2D-3D method for robust foreground-background classification of the recorded RMB-Lidar point clouds, with eliminating spurious effects resulted by quantification error of the discretized view angle, non-linear position corrections of sensor calibration, and background flickering, in particularly due to motion of vegetation. Second, we propose a real-time method for moving pedestrian detection and tracking in RMB-Lidar sequences of dense surveillance scenarios, with short-and long-term object assignment. We introduce a novel person re-identification algorithm based on solely the Lidar measurements, utilizing in parallel the range and the intensity channels of the sensor, which provide biometric features. Quantitative evaluation is performed on seven outdoor Lidar sequences containing various multi-target scenarios displaying challenging outdoor conditions with low point density and multiple occlusions.

Object-Oriented Logic Programming of 3d Intelligent Video Surveillance Systems: The Problem Statement

“…Nowadays, this term could be associated with using 3D/2.5D data acquisition equipment [6] like time-of-flight (ToF) cameras, structured light sensors, stereo cameras, laser scanners (LiDARs) [7], and Flash Ladars [8] in video surveillance. Availability of 3D data acquisition equipment leads to considerable progress in video surveillance related research areas such as background subtraction and tracking people [9], [10], person identification [11], [12], face recognition [13], posture recognition [14], [15], gesture recognition [16], people counting [17], human activity recognition [18], etc.…”

Gait Recognition with Compact Lidar Sensors

“…In such point clouds view invariance can be simulated with proper 3D transformations of the point cloud of each person (Benedek et al, 2016), while occlusion handling, background segmentation and people tracking can also be more efficiently implemented in the range image domain, than with optical images. (Benedek, 2014) showed that a 64-beam LiDAR (Velodne HDL-64E) is able track several people in realistic outdoor surveillance scenarios, and (Benedek et al, 2016) showed that the same sensor is also effective in the re-identification of people leaving and re-entering the field-of-view. However, the 64-beam sensor is too heavy and expensive for wide usage in surveillance systems.…”

Pedestrian Detection by Laser Scanning and Depth Imagery

“…(Fuerstenberg and Lages, 2003) and (Gidel et al, 2010) have implemented a system tested in passenger car using laser methods. (Lovas and Barsi, 2015) applied profile laser scanner, (Benedek, 2014) has used rotating multi-beam laser scanner to detect pedestrians. (Gate and Nashashibi, 2008) have improved the pedestrian classification accuracy by recursive estimation.…”