Three-dimensional Human Tracking of a Mobile Robot by Fusion of Tracking Results of Two Cameras

  title={Three-dimensional Human Tracking of a Mobile Robot by Fusion of Tracking Results of Two Cameras},
  author={Shinya Matsubara and Akihiko Honda and Yonghoon Ji and Kazunori Umeda},
  journal={2020 21st International Conference on Research and Education in Mechatronics (REM)},
  • S. Matsubara, Akihiko Honda, +1 author K. Umeda
  • Published 3 July 2020
  • Computer Science
  • 2020 21st International Conference on Research and Education in Mechatronics (REM)
This paper proposes a process that uses two cameras to obtain three-dimensional (3D) information of a target object for human tracking. Results of human detection and tracking from two cameras are integrated to obtain the 3D information. OpenPose is used for human detection. In the case of a general processing a stereo camera, a range image of the entire scene is acquired as precisely as possible, and then the range image is processed. However, there are problems such as incorrect matching and… 


Occlusion handling for a target-tracking robot with a stereo camera
An occlusion-handling method for a target-tracking robot with a stereo camera and a combination of both color and location features of the target and candidates and the identification of a target is presented.
A Robust Person Tracking and Following Approach for Mobile Robot
A novel vision-based tracking and following method for a mobile robot is proposed, which combines the clothes color features of the person's upper body and the contour of the head-shoulder to enable the robot to follow the targeted person.
Audiovisual Person Tracking with a Mobile Robot
A person tracking system for a mobile robot which enables the robot to track several people simultaneously and is based on a variety of input cues that are fused using a multi-modal anchoring framework.
People Tracking Using a Robot in Motion with Laser Range Finder
Resultant experiments and analysis showed that multiple walking people are tracked well from a mobile robot with the proposed method.
Hand Keypoint Detection in Single Images Using Multiview Bootstrapping
An approach that uses a multi-camera system to train fine-grained detectors for keypoints that are prone to occlusion, such as the joints of a hand, and derives a result analytically relating the minimum number of views to achieve target true and false positive rates for a given detector.
Real-time human gesture grading based on OpenPose
  • Sen Qiao, Yilin Wang, J. Li
  • Computer Science
    2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)
  • 2017
Experimental results showed that the real-time 2D human gesture grading system from monocular images based on OpenPose worked efficiently with high real- time performance, low cost of equipment and strong robustness to the interference of noise.
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn
Active and passive range sensing for robotics
  • M. Hebert
  • Engineering, Computer Science
    Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065)
  • 2000
A brief survey of the technologies currently available for range sensing, of their use in robotics applications, and of emerging technologies for future systems, organized by type of sensing: laser range finder, triangulation range finders, and passive stereo.
Passive sonar applications: target tracking and navigation of an autonomous robot
  • L. Mattos, E. Grant
  • Computer Science
    IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004
  • 2004
The use of small area acoustic array technology as passive sonar for an autonomous mobile robot sound localization and direction control and real-time target tracking based solely on received audio signals is demonstrated.
How Can Robots Succeed in Unstructured Environments ?
Roboticists are working towards the realization of autonomous mobile manipulators that can perform useful tasks in human environments. These environments pose a significant challenge because of their