• Corpus ID: 17984475

Quantitative performance evaluation of a people tracking system on a mobile robot

  title={Quantitative performance evaluation of a people tracking system on a mobile robot},
  author={Grzegorz Cielniak and Andr{\'e} Treptow and Tom Duckett},
Future service robots will need to keep track of the persons in their environment. A number of people tracking systems have been developed for mobile robots, but it is currently impossible to make ... 

Figures and Tables from this paper

Evaluation of navigation of an autonomous mobile robot
These metrics, collectively, provide an indication of the quality of the navigation, useful for comparing and analyzing control architectures of mobile robots.
Performance metrics for robot navigation
Various quality metrics are described that are useful for comparing and analyzing control architectures of mobile robots, in order to evaluate their navigational performance. Two control
Multisensor-Based Human Detection and Tracking for Mobile Service Robots
  • N. BellottoHuosheng Hu
  • Computer Science
    IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
  • 2009
A solution for human tracking with a mobile robot that implements multisensor data fusion techniques based on the recognition of typical leg patterns extracted from laser scans, showing that robust human tracking can be performed within complex indoor environments.
Suggestions for the assessment of navigation algorithms in educational robotics
A simple way of teaching the topics performance metrics and benchmarks in educational robotics is presented. Aspects related with the performance assessment of navigation algorithms in mobile
Simulation and Assessment Educational Framework for Mobile Robot Algorithms
A mobile robot simulator useful in research and education was implemented in Matlab, it models the differential kinematics as well as proximity sensors of the robot. It allows the performance
Benchmark Framework for Mobile Robots Navigation Algorithms
This method is suggested as an educational tool, which allows the student to optimize the algorithms quality, relating to important aspectsof science, technology and engineering teaching, as energy consumption, optimization and design.
Person Following Robot with Vision-based and Sensor Fusion Tracking Algorithm
This work has developed ApriAttendaTM, a person following robot that finds a specified person using visual tracking functions and follows him/her while avoiding obstacles and adopts a stereo vision system.
Mobile Robots in Human Environments: towards safe, comfortable and natural navigation
It is demonstrated, that the robot is able to learn where to position itself, and is capable of adapting to a changing environment, and it is then shown that the developed framework can be used in other applications as well.
1 Quantitative Performance Metrics for Mobile Robots Navigation
This chapter describes aspects related with a procedure used for the performance evaluation of mobile robots navigation algorithms, and several performance metrics used in the navigation of mobile Robots, and the protocol to be followed in the performance evaluated is defined.
Real-time pedestrian learning-tracking with information fusion
The results of the experiments show good robustness and performance when facing extreme cases such as the object rotation, long-period occlusion, and high similarity between object and background.


Tracking multiple moving targets with a mobile robot using particle filters and statistical data association
A sample-based variant of joint probabilistic data association filters is introduced to track features originating from individual objects and to solve the correspondence problem between the detected features and the filters.
Providing the basis for human-robot-interaction: a multi-modal attention system for a mobile robot
An attention system for a mobile robot which enables the robot to shift its attention to the person of interest and to maintain attention during interaction is presented.
Human-robot interaction based on Haar-like features and eigenfaces
A machine learning approach for visual object detection and recognition which is capable of processing images rapidly and achieving high detection and recognized faces at 10.9 frames per second is described.
Performance Evaluation Metrics and Statistics for Positional Tracker Evaluation
The fundamental issues of trajectory comparison are addressed, and metrics are presented which allow the key features to be described which give quantitative positional evaluation of the performance of computer vision tracking systems.
CONDENSATION—Conditional Density Propagation for Visual Tracking
The Condensation algorithm uses “factored sampling”, previously applied to the interpretation of static images, in which the probability distribution of possible interpretations is represented by a randomly generated set.
An MCMC-Based Particle Filter for Tracking Multiple Interacting Targets
It is proved that incorporating an MRF to model interactions is equivalent to adding an additional interaction factor to the importance weights in a joint particle filter, and replaced the traditional importance sampling step in the particle filter with an MCMC sampling step.
Metrics for performance evaluation of video object segmentation and tracking without ground-truth
Detailed results are presented to evaluate the segmentation map of the "Man" object in the "Hall Monitor" sequence both in terms of a single numerical measure, as well as localization of the good and bad segments of the boundary.
Tools and techniques for video performance evaluation
We outline a reconfigurable video performance evaluation resource (ViPER), which provides an interface for ground truth generation, metrics for evaluation and tools for visualization of video
Sequential Monte Carlo Methods in Practice
Sequential importance sampling (cid:2)SIS(cid:3) was (cid:4)rst developed in (cid:5)(cid:6)(cid:7)(cid:8)s for molecular simulation(cid:9) Although half a century has passed by(cid:10) the SIS
Say Cheese! Experiences with a Robot Photographer
The overall architecture of the system is outlined and how the various components interrelate are described, and the experiences deploying the robot photographer at a number of real-world events are described.