People Detection and Tracking Using LIDAR Sensors

Abstract

The tracking of people is an indispensable capacity in almost any robotic application. A relevant case is the @home robotic competitions, where the service robots have to demonstrate that they possess certain skills that allow them to interact with the environment and the people who occupy it; for example, receiving the people who knock at the door and attending them as appropriate. Many of these skills are based on the ability to detect and track a person. It is a challenging problem, particularly when implemented using low-definition sensors, such as Laser Imaging Detection and Ranging (LIDAR) sensors, in environments where there are several people interacting. This work describes a solution based on a single LIDAR sensor to maintain a continuous identification of a person in time and space. The system described is based on the People Tracker package, aka PeTra, which uses a convolutional neural network to identify person legs in complex environments. A new feature has been included within the system to correlate over time the people location estimates by using a Kalman filter. To validate the solution, a set of experiments have been carried out in a test environment certified by the European Robotic League.

Multiposture leg tracking for temporarily vision restricted environments based on fusion of laser and radar sensor data

“…Guerrero-Higueras et al (2019) propose the PeTra detection and tracking network based on the U-Net architecture (Ronneberger et al, 2015). They further propose an extension in Álvarez-Aparicio et al (2019). PeTra is better understood as a static background filter, which is applied to extract leg clusters.…”

A Semantic Classification Approach for Indoor Robot Navigation

“…For instance, the authors of [6] proposed a new approach for road obstacle classification using two different LiDAR sensors. Moreover, the works presented in [7,8] developed classification systems for forest environment characteristics, whereas in [9], the authors used a single LiDAR sensor to maintain the continuous identification of a person in a complex environment. The author of [10] developed a classification system using a LiDAR sensor, which was able to classify three different types of buildings: single-family houses, multiple-family houses, and non-residential buildings.…”

Monitoring Critical Infrastructure Using 3D LiDAR Point Clouds

“…Comprehensive survey on different types of Li-DAR [2], [3], [4] have been extensively studied by the researchers. Individual surveys on different applications of Li-DAR in road transportation [5], [6], [7], [8], [9], air transporta-tion [10], [11], [12], [13], railway [14], [15], electrical power transmission [16] and people tracking [17] are present in literature. Several LiDAR databases are also available for post processing applications [33]- [47].…”