Nicola Bellotto

Vision and Laser Data Fusion for Tracking People with a Mobile Robot

In this paper we present a multi-sensor fusion system for tracking people with a mobile robot, which integrates the information provided by a laser range sensor and a PTZ camera. We introduce the algorithms used for detecting legs from laser scans and faces from video images, then we illustrate a human motion model for the estimation of people position, orientation and height. The ego-motion of the robot is also taken into account and the information fused using an implementation of the unscented Kalman filter. Finally, multiple human tracks are generated and maintained thanks to an appropriate data association procedure. The results of several experiments are illustrated, proving the effectiveness of our approach, and some considerations drawn.

A distributed camera system for multi-resolution surveillance

We describe an architecture for a multi-camera, multi-resolution surveillance system. The aim is to support a set of distributed static and pan-tilt-zoom (PTZ) cameras and visual tracking algorithms, together with a central supervisor unit. Each camera (and possibly pan-tilt device) has a dedicated process and processor. Asynchronous interprocess communications and archiving of data are achieved in a simple and effective way via a central repository, implemented using an SQL database.

Computationally efficient solutions for tracking people with a mobile robot: an experimental evaluation of Bayesian filters

Modern service robots will soon become an essential part of modern society. As they have to move and act in human environments, it is essential for them to be provided with a fast and reliable tracking system that localizes people in the neighborhood. It is therefore important to select the most appropriate filter to estimate the position of these persons. This paper presents three efficient implementations of multisensor-human tracking based on different Bayesian estimators: Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF) and Sampling Importance Resampling (SIR) particle filter. The system implemented on a mobile robot is explained, introducing the methods used to detect and estimate the position of multiple people. Then, the solutions based on the three filters are discussed in detail. Several real experiments are conducted to evaluate their performance, which is compared in terms of accuracy, robustness and execution time of the estimation. The results show that a solution based on the UKF can perform as good as particle filters and can be often a better choice when computational efficiency is a key issue.

Cue-based aggregation with a mobile robot swarm: a novel fuzzy-based method

Aggregation in swarm robotics is referred to as the gathering of spatially distributed robots into a single aggregate. Aggregation can be classified as cue-based or self-organized. In cue-based aggregation, there is a cue in the environment that points to the aggregation area, whereas in self-organized aggregation no cue is present. In this paper, we proposed a novel fuzzy-based method for cue-based aggregation based on the state-of-the-art BEECLUST algorithm. In particular, we proposed three different methods: naïve, that uses a deterministic decision-making mechanism; vector-averaging, using a vectorial summation of all perceived inputs; and fuzzy, that uses a fuzzy logic controller. We used different experiment settings: one-source and two-source environments with static and dynamic conditions to compare all the methods. We observed that the fuzzy method outperformed all the other methods and it is the most robust method against noise.

Multisensor data fusion for joint people tracking and identification with a service robot

Tracking and recognizing people are essential skills modern service robots have to be provided with. The two tasks are generally performed independently, using ad-hoc solutions that first estimate the location of humans and then proceed with their identification. The solution presented in this paper, instead, is a general framework for tracking and recognizing people simultaneously with a mobile robot, where the estimates of the human location and identity are fused using probabilistic techniques. Our approach takes inspiration from recent implementations of joint tracking and classification, where the considered targets are mainly vehicles and aircrafts in military and civilian applications. We illustrate how people can be robustly tracked and recognized with a service robot using an improved histogram-based detection and multisensor data fusion. Some experiments in real challenging scenarios show the good performance of our solution.

A Bank of Unscented Kalman Filters for Multimodal Human Perception with Mobile Service Robots

A new generation of mobile service robots could be ready soon to operate in human environments if they can robustly estimate position and identity of surrounding people. Researchers in this field face a number of challenging problems, among which sensor uncertainties and real-time constraints. In this paper, we propose a novel and efficient solution for simultaneous tracking and recognition of people within the observation range of a mobile robot. Multisensor techniques for legs and face detection are fused in a robust probabilistic framework to height, clothes and face recognition algorithms. The system is based on an efficient bank of Unscented Kalman Filters that keeps a multi-hypothesis estimate of the person being tracked, including the case where the latter is unknown to the robot. Several experiments with real mobile robots are presented to validate the proposed approach. They show that our solutions can improve the robot’s perception and recognition of humans, providing a useful contribution for the future application of service robotics.

Appearance-based localization for mobile robots using digital zoom and visual compass

This paper describes a localization system for mobile robots moving in dynamic indoor environments, which uses probabilistic integration of visual appearance and odometry information. The approach is based on a novel image matching algorithm for appearance-based place recognition that integrates digital zooming, to extend the area of application, and a visual compass. Ambiguous information used for recognizing places is resolved with multiple hypothesis tracking and a selection procedure inspired by Markov localization. This enables the system to deal with perceptual aliasing or absence of reliable sensor data. It has been implemented on a robot operating in an office scenario and the robustness of the approach is demonstrated experimentally.

Analysis of human-robot spatial behaviour applying a qualitative trajectory calculus

The analysis and understanding of human-robot joint spatial behaviour (JSB) - such as guiding, approaching, departing, or coordinating movements in narrow spaces - and its communicative and dynamic aspects are key requirements on the road towards more intuitive interaction, safe encounter, and appealing living with mobile robots. This endeavours demand for appropriate models and methodologies to represent JSB and facilitate its analysis. In this paper, we adopt a qualitative trajectory calculus (QTC) as a formal foundation for the analysis and representation of such spatial behaviour of a human and a robot based on a compact encoding of the relative trajectories of two interacting agents in a sequential model. We present this QTC together with a distance measure and a probabilistic behaviour model and outline its usage in an actual JSB study. We argue that the proposed QTC coding scheme and derived methodologies for analysis and modelling are flexible and extensible to be adapted for a variety of other scenarios and studies.

Cognitive visual tracking and camera control

Cognitive visual tracking is the process of observing and understanding the behavior of a moving person. This paper presents an efficient solution to extract, in real-time, high-level information from an observed scene, and generate the most appropriate commands for a set of pan-tilt-zoom (PTZ) cameras in a surveillance scenario. Such a high-level feedback control loop, which is the main novelty of our work, will serve to reduce uncertainties in the observed scene and to maximize the amount of information extracted from it. It is implemented with a distributed camera system using SQL tables as virtual communication channels, and Situation Graph Trees for knowledge representation, inference and high-level camera control. A set of experiments in a surveillance scenario show the effectiveness of our approach and its potential for real applications of cognitive vision.

Stress Detection Using Wearable Physiological Sensors

As the population increases in the world, the ratio of health carers is rapidly decreasing. Therefore, there is an urgent need to create new technologies to monitor the physical and mental health of people during their daily life. In particular, negative mental states like depression and anxiety are big problems in modern societies, usually due to stressful situations during everyday activities including work. This paper presents a machine learning approach for stress detection on people using wearable physiological sensors with the final aim of improving their quality of life. The presented technique can monitor the state of the subject continuously and classify it into ”stressful” or ”non-stressful” situations. Our classification results show that this method is a good starting point towards real-time stress detection.