Performance Assessment of a People Tracker for Social Robots

Antonucci, Alessandro; Magnago, Valerio; Palopoli, Luigi; Fontanelli, Daniele

doi:10.1109/i2mtc.2019.8826999

Cited by 9 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several methods exist in the literature and fall under two main categories: object detectors and pose estimation techniques. The former identifies objects by bounding a box around them, while the latter detects the human joints and connects them resulting in pose estimates [7]. On the one hand, object detectors, such as YOLO models [8], are more general-purpose than pose estimation techniques, but their utility for identifying human subjects may require pruning and/or retraining.…”

Section: Person Detection and Localizationmentioning

confidence: 99%

See 1 more Smart Citation

A Social Distance Estimation and Crowd Monitoring System for Surveillance Cameras

Al-Sa'D

Kıranyaz

Ahmad

et al. 2022

Sensors

View full text Add to dashboard Cite

Social distancing is crucial to restrain the spread of diseases such as COVID-19, but complete adherence to safety guidelines is not guaranteed. Monitoring social distancing through mass surveillance is paramount to develop appropriate mitigation plans and exit strategies. Nevertheless, it is a labor-intensive task that is prone to human error and tainted with plausible breaches of privacy. This paper presents a privacy-preserving adaptive social distance estimation and crowd monitoring solution for camera surveillance systems. We develop a novel person localization strategy through pose estimation, build a privacy-preserving adaptive smoothing and tracking model to mitigate occlusions and noisy/missing measurements, compute inter-personal distances in the real-world coordinates, detect social distance infractions, and identify overcrowded regions in a scene. Performance evaluation is carried out by testing the system’s ability in person detection, localization, density estimation, anomaly recognition, and high-risk areas identification. We compare the proposed system to the latest techniques and examine the performance gain delivered by the localization and smoothing/tracking algorithms. Experimental results indicate a considerable improvement, across different metrics, when utilizing the developed system. In addition, they show its potential and functionality for applications other than social distancing.

show abstract

Section: Person Detection and Localizationmentioning

confidence: 99%

“…Moreover, their ability to work in dense crowds was verified in [10,11], which is the very same setting social distance monitoring is dealing with. Nonetheless, pose estimators are computationally more expensive than object detectors and their high entropy output requires further processing [7].…”

Section: Person Detection and Localizationmentioning

confidence: 99%

A Social Distance Estimation and Crowd Monitoring System for Surveillance Cameras

Al-Sa'D

Kıranyaz

Ahmad

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Our application requires 3D reconstruction of the human pose. The combination between Stereo and RGB-D sensor with skeleton-based approaches proves very useful to this purpose and it is significantly simplified by the availability of public domain software components [21]. However, the simple use of visual information has known limitations such as the sensitivity to lighting conditions, and the high computation times.…”

Section: Related Workmentioning

confidence: 99%

Humans as Path-Finders for Safe Navigation

Antonucci,

Bevilacqua,

Leonardi

et al. 2021

Preprint

View full text Add to dashboard Cite

One of the most important barriers toward a widespread use of mobile robots in unstructured and human populated work environments is the ability to plan a safe path. In this paper, we propose to delegate this activity to a human operator that walks in front of the robot marking with her/his footsteps the path to be followed. The implementation of this approach requires a high degree of robustness in locating the specific person to be followed (the leader). We propose a three phase approach to fulfil this goal: 1. identification and tracking of the person in the image space, 2. sensor fusion between camera data and laser sensors, 3. point interpolation with continuous curvature curves. The approach is described in the paper and extensively validated with experimental results.

show abstract

“…Using the motion model idea that underlies human dynamics [5], [18], we adopt two different models for the motion of the autonomous agents, which will be referred henceforth as robots. In the first model, the robots are modelled as points moving on a plane with respect to a fixed reference frame W .…”

Section: A Robot Modelsmentioning

confidence: 99%

“…either robots or human beings) even when Global Navigation Satellite Systems (GNSS) is not allowed, as typically happens in indoor environments. To mention a few, there are solutions based on laser beams [2], ultrasonic stimuli [3], cameras [4] or even radars [5]. One of the most effective and low cost solutions relies on ranging sensors, which comes using different approaches, such as Received Signal Strength (RSS) measurements and fingerprinting of standard wireless signals (e.g.…”

Section: Introductionmentioning

confidence: 99%

Majority Effect in Cooperative localisation of Mobile Agents using Ranging Measurements

Ben

Fontanelli

2020

2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)

View full text Add to dashboard Cite

Multi agent systems are becoming pervasive in modern industrial and service applications. Either being autonomous robotic agents or human beings performing a collaborative task, relative and/or absolute localisation of the team agents is a mandatory task to be efficiently solved for any meaningful application. In this paper, we will analyse the cooperative localisation problem from the perspective of the number and quality of the available measurements, rooting this analysis to a practical example of ranging measurements for robot localisation. We will make use of a known distributed Kalman filtering technique to highlight a trade off between number and quality of measurements, which is a known effect in estimation theory but never analysed for distributed estimation problems. What is surprising is that the net effect is quite similar to what happens in opinion formation for social groups, which is sometimes referred to as majority effect.

show abstract

Performance Assessment of a People Tracker for Social Robots

Cited by 9 publications

References 26 publications

A Social Distance Estimation and Crowd Monitoring System for Surveillance Cameras

A Social Distance Estimation and Crowd Monitoring System for Surveillance Cameras

Humans as Path-Finders for Safe Navigation

Majority Effect in Cooperative localisation of Mobile Agents using Ranging Measurements

Contact Info

Product

Resources

About