Matteo Munaro

Tracking people within groups with RGB-D data

This paper proposes a very fast and robust multi-people tracking algorithm suitable for mobile platforms equipped with a RGB-D sensor. Our approach features a novel depth-based sub-clustering method explicitly designed for detecting people within groups or near the background and a three-term joint likelihood for limiting drifts and ID switches. Moreover, an online learned appearance classifier is proposed, that robustly specializes on a track while using the other detections as negative examples. Tests have been performed with data acquired from a mobile robot in indoor environments and on a publicly available dataset acquired with three RGB-D sensors and results have been evaluated with the CLEAR MOT metrics. Our method reaches near state of the art performance and very high frame rates in our distributed ROS-based CPU implementation.

Fast RGB-D people tracking for service robots

Service robots have to robustly follow and interact with humans. In this paper, we propose a very fast multi-people tracking algorithm designed to be applied on mobile service robots. Our approach exploits RGB-D data and can run in real-time at very high frame rate on a standard laptop without the need for a GPU implementation. It also features a novel depth-based sub-clustering method which allows to detect people within groups or even standing near walls. Moreover, for limiting drifts and track ID switches, an online learning appearance classifier is proposed featuring a three-term joint likelihood. We compared the performances of our system with a number of state-of-the-art tracking algorithms on two public datasets acquired with three static Kinects and a moving stereo pair, respectively. In order to validate the 3D accuracy of our system, we created a new dataset in which RGB-D data are acquired by a moving robot. We made publicly available this dataset which is not only annotated by hand, but the ground-truth position of people and robot are acquired with a motion capture system in order to evaluate tracking accuracy and precision in 3D coordinates. Results of experiments on these datasets are presented, showing that, even without the need for a GPU, our approach achieves state-of-the-art accuracy and superior speed.

Performance evaluation of the 1st and 2nd generation Kinect for multimedia applications

Microsoft Kinect had a key role in the development of consumer depth sensors being the device that brought depth acquisition to the mass market. Despite the success of this sensor, with the introduction of the second generation, Microsoft has completely changed the technology behind the sensor from structured light to Time-Of-Flight. This paper presents a comparison of the data provided by the first and second generation Kinect in order to explain the achievements that have been obtained with the switch of technology. After an accurate analysis of the accuracy of the two sensors under different conditions, two sample applications, i.e., 3D reconstruction and people tracking, are presented and used to compare the performance of the two sensors.

3D reconstruction of freely moving persons for re-identification with a depth sensor

In this work, we describe a novel method for creating 3D models of persons freely moving in front of a consumer depth sensor and we show how they can be used for long-term person re-identification. For overcoming the problem of the different poses a person can assume, we exploit the information provided by skeletal tracking algorithms for warping every point cloud frame to a standard pose in real time. Then, the warped point clouds are merged together to compose the model. Re-identification is performed by matching body shapes in terms of whole point clouds warped to a standard pose with the described method. We compare this technique with a classification method based on a descriptor of skeleton features and with a mixed approach which exploits both skeleton and shape features. We report experiments on two datasets we acquired for RGB-D re-identification which use different skeletal tracking algorithms and which are made publicly available to foster research in this new research branch.

One-shot person re-identification with a consumer depth camera

In this chapter, we propose a comparison between two techniques for one-shot person re-identification from soft biometric cues. One is based upon a descriptor composed of features provided by a skeleton estimation algorithm; the other compares body shapes in terms of whole point clouds. This second approach relies on a novel technique we propose to warp the subject’s point cloud to a standard pose, which allows to disregard the problem of the different poses a person can assume. This technique is also used for composing 3D models which are then used at testing time for matching unseen point clouds. We test the proposed approaches on an existing RGB-D re-identification dataset and on the newly built BIWI RGBD-ID dataset. This dataset provides sequences of RGB, depth, and skeleton data for 50 people in two different scenarios and it has been made publicly available to foster advancement in this new research branch.

A feature-based approach to people re-identification using skeleton keypoints.

In this paper we propose a novel methodology for people re-identification based on skeletal information. Features are evaluated on the skeleton joints and a highly distinctive and compact feature-based signature is generated for each user by concatenating descriptors of all visible joints. We compared a number of state-of-the-art 2D and 3D feature descriptors to be used with our signature on two newly acquired public datasets for people re-identification with RGB-D sensors. Moreover, we tested our approach against the best re-identification methods in the literature and on a widely used public video surveillance dataset. Our approach proved to be robust to strong illumination changes and occlusions. It achieved very high performance also on low resolution images, overcoming state-of-the-art methods in terms of recognition accuracy and efficiency. These features make our approach particularly suited for mobile robotics.

OpenPTrack: Open source multi-camera calibration and people tracking for RGB-D camera networks

Abstract OpenPTrack is an open source software for multi-camera calibration and people tracking in RGB-D camera networks. It allows to track people in big volumes at sensor frame rate and currently supports a heterogeneous set of 3D sensors. In this work, we describe its user-friendly calibration procedure, which consists of simple steps with real-time feedback that allow to obtain accurate results in estimating the camera poses that are then used for tracking people. On top of a calibration based on moving a checkerboard within the tracking space and on a global optimization of cameras and checkerboards poses, a novel procedure which aligns people detections coming from all sensors in a x - y - t i m e space is used for refining camera poses. While people detection is executed locally, in the machines connected to each sensor, tracking is performed by a single node which takes into account detections from all over the network. Here we detail how a cascade of algorithms working on depth point clouds and color, infrared and disparity images is used to perform people detection from different types of sensors and in any indoor light condition. We present experiments showing that a considerable improvement can be obtained with the proposed calibration refinement procedure that exploits people detections and we compare Kinect v1, Kinect v2 and Mesa SR4500 performance for people tracking applications. OpenPTrack is based on the Robot Operating System and the Point Cloud Library and has already been adopted in networks composed of up to ten imagers for interactive arts, education, culture and human–robot interaction applications.

Fast and Robust Multi-people Tracking from RGB-D Data for a Mobile Robot

This paper proposes a fast and robust multi-people tracking algorithm for mobile platforms equipped with a RGB-D sensor. Our approach features an efficient point cloud depth-based clustering, an HOG-like classification to robustly initialize a person tracking and a person classifier with online learning to manage the person ID matching even after a full occlusion. For people detection, we make the assumption that people move on a ground plane. Tests are presented on a challenging real-world indoor environment and results have been evaluated with the CLEAR MOT metrics. Our algorithm proved to correctly track 96% of people with very limited ID switches and few false positives, with an average frame rate of 25 fps. Moreover, its applicability to robot-people following tasks have been tested and discussed.

Human Action Recognition from RGB-D Frames Based on Real-Time 3D Optical Flow Estimation

Modern advances in the area of intelligent agents have led to the concept of cognitive robots. A cognitive robot is not only able to perceive complex stimuli from the environment, but also to reason about them and to act coherently. Computer vision-based recognition systems serve the perception task, but they also go beyond it by finding challenging applications in other fields such as video surveillance, HCI, content-based video analysis and motion capture. In this context, we propose an automatic system for real-time human action recognition. We use the Kinect sensor and the tracking system in [1] to robustly detect and track people in the scene. Next, we estimate the 3D optical flow related to the tracked people from point cloud data only and we summarize it by means of a 3D grid-based descriptor. Finally, temporal sequences of descriptors are classified with the Nearest Neighbor technique and the overall application is tested on a newly created dataset. Experimental results show the effectiveness of the proposed approach.

RGB-D Human Detection and Tracking for Industrial Environments

Reliably detecting and tracking movements of nearby workers on the factory floor are crucial to the safety of advanced manufacturing automation in which humans and robots share the same workspace. In this work, we address the problem of multiple people detection and tracking in industrial environments by proposing algorithms which exploit both color and depth data to robustly track people in real time. For people detection, a cascade organization of these algorithms is proposed, while tracking is performed based on a particle filter which can interpolate sparse detection results by exploiting color histograms of people. Tracking results of different combinations of the proposed methods are evaluated on a novel dataset collected with a consumer RGB-D sensor in an industrial-like environment. Our techniques obtain good tracking performances even in an industrial setting and reach more than 30 Hz update rate. All these algorithms have been released as open source as part of the ROS-Industrial project.