Kinect-based people detection and tracking from small-footprint ground robots

Gritti, Armando Pesenti; Tarabini, Oscar; Guzzi, Jérôme; Di, Gianni A.; Caglioti, Vincenzo; Gambardella, Luca Maria; Giusti, Alessandro

doi:10.1109/iros.2014.6943139

Cited by 39 publications

(17 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We perform on-board detection and tracking using two different algorithms that we fuse with means of a Kalman filter to improve the existing person detection and tracking. The first detection and tracking algorithm used is the one by Pesenti Gritti et al [23] for small-footprint ground robots, which has proven to be robust for cluttered indoor environments. This tracker returns the position of the person relative to the robot and its approximate orientation.…”

Section: B Human Trackingmentioning

confidence: 99%

On-board human-aware navigation for indoor resource-constrained robots: A case-study with the ranger

Talebpour¹,

Navarro²,

Martinoli³

2015

2015 IEEE/SICE International Symposium on System Integration (SII)

View full text Add to dashboard Cite

Abstract-Introducing simple robotic platforms into domestic environments is faced with the challenge of social acceptability. Therefore human-aware navigation is a must for robots operating in environments shared with human users. In this work, we focus on the human-aware navigation problem in a structured environment for a robot with limited sensing and constrained maneuvering called Ranger. The Ranger is a simple domestic robotic platform designed for interacting with children. The system combines person detection and tracking -which is the result of fusing laser-scan and depth-image based detectors provided by an RGB-D camera-, basic autonomous navigation and the concept of personal space. We rely only on the on-board sensors for mapping, localization, human tracking, and navigation. Systematic experiments are carried out with a real robot in the presence of a human in order to compare our human-aware navigation with a non human-aware simple approach. The results show that human-aware navigation is able to achieve trajectories which are respecting the personal spaces of the human and are thus more acceptable for the users.

show abstract

Section: B Human Trackingmentioning

confidence: 99%

On-board human-aware navigation for indoor resource-constrained robots: A case-study with the ranger

Talebpour¹,

Navarro²,

Martinoli³

2015

2015 IEEE/SICE International Symposium on System Integration (SII)

View full text Add to dashboard Cite

show abstract

“…To track the target people across various complex environments, robots need to localize the target and discriminate him/her from other people. In this context, localizing and tracking a moving target become critical and challenging for many indoor and outdoor robotic applications [1]- [3].…”

Section: Introductionmentioning

confidence: 99%

“…Among them, visual tracking enjoys a good population. It is an extremely active research area in computer vision community and 1 obtains significant progress over the past decade [7]- [11]. However, a monocular camera sensor is limited in providing the 2-D position because it is insufficient to measure the range information from the robot to the target.…”

Section: Introductionmentioning

confidence: 99%

Real-time 3D human tracking for mobile robots with multisensors

Wang

Shi

et al. 2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Acquiring the accurate 3-D position of a target person around a robot provides fundamental and valuable information that is applicable to a wide range of robotic tasks, including home service, navigation and entertainment. This paper presents a real-time robotic 3-D human tracking system which combines a monocular camera with an ultrasonic sensor by the extended Kalman filter (EKF). The proposed system consists of three sub-modules: monocular camera sensor tracking model, ultrasonic sensor tracking model and multi-sensor fusion. An improved visual tracking algorithm is presented to provide partial location estimation (2-D). The algorithm is designed to overcome severe occlusions, scale variation, target missing and achieve robust re-detection. The scale accuracy is further enhanced by the estimated 3-D information. An ultrasonic sensor array is employed to provide the range information from the target person to the robot and Gaussian Process Regression is used for partial location estimation (2-D). EKF is adopted to sequentially process multiple, heterogeneous measurements arriving in an asynchronous order from the vision sensor and the ultrasonic sensor separately. In the experiments, the proposed tracking system is tested in both simulation platform and actual mobile robot for various indoor and outdoor scenes. The experimental results show the superior performance of the 3-D tracking system in terms of both the accuracy and robustness.

show abstract

“…The system measures the displacements and velocities of the feet and it requires the user to wear markers on the shoes for foot detection. Recently, RGB-D camera has been employed to measure a person’s walking postures and speeds [1, 2]. An RGB-D camera provides reliable depth data for lower limb detection.…”

Section: Introductionmentioning

confidence: 99%

“…An RGB-D camera provides reliable depth data for lower limb detection. Gritti, et al [1] propose a histogram based lower limb detection algorithm that extracts a person’s feet and legs from an RGB-D camera’s depth data and tracks the feet and legs over time. However, it does not measure the walking postures.…”

Section: Introductionmentioning

confidence: 99%

RGB-D camera based walking pattern recognition by support vector machines for a smart rollator

Zhang

2017

Int J Intell Robot Appl

View full text Add to dashboard Cite

This paper presents a walking pattern detection method for a smart rollator. The method detects the rollator user’s lower extremities from the depth data of an RGB-D camera. It then segments the 3D point data of the lower extremities into the leg and foot data points, from which a skeletal system with 6 skeletal points and 4 rods is extracted and used to represent a walking gait. A gait feature, comprising the parameters of the gait shape and gait motion, is then constructed to describe a walking state. K-means clustering is employed to cluster all gait features obtained from a number of walking videos into 6 key gait features. Using these key gait features, a walking video sequence is modeled as a Markov chain. The stationary distribution of the Markov chain represents the walking pattern. Three Support Vector Machines (SVMs) are trained for walking pattern detection. Each SVM detects one of the three walking patterns. Experimental results demonstrate that the proposed method has a better performance in detecting walking patterns than seven existing methods.

show abstract

Kinect-based people detection and tracking from small-footprint ground robots

Cited by 39 publications

References 31 publications

On-board human-aware navigation for indoor resource-constrained robots: A case-study with the ranger

On-board human-aware navigation for indoor resource-constrained robots: A case-study with the ranger

Real-time 3D human tracking for mobile robots with multisensors

RGB-D camera based walking pattern recognition by support vector machines for a smart rollator

Contact Info

Product

Resources

About