DensePeds: Pedestrian Tracking in Dense Crowds Using Front-RVO and Sparse Features

Chandra, Rohan; Bhattacharya, Uttaran; Bera, Aniket; Dinesh, M. S.

doi:10.48550/arxiv.1906.10313

Cited by 7 publications

(14 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pedestrian tracking has been widely applied in surveillance video analysis and is well developed based on research on multi-object tracking problems [4]- [7].…”

Section: A Perception For Surveillance Systemsmentioning

confidence: 99%

Autonomous Social Distancing in Urban Environments using a Quadruped Robot

Fan¹,

Chen²,

Zhao³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

COVID-19 pandemic has become a global challenge faced by people all over the world. Social distancing has been proved to be an effective practice to reduce the spread of COVID-19. Against this backdrop, we propose that the surveillance robots can not only monitor but also promote social distancing. Robots can be flexibly deployed and they can take precautionary actions to remind people of practicing social distancing. In this paper, we introduce a fully autonomous surveillance robot based on a quadruped platform that can promote social distancing in complex urban environments. Specifically, to achieve autonomy, we mount multiple cameras and a 3D LiDAR on the legged robot. The robot then uses an onboard real-time social distancing detection system to track nearby pedestrian groups. Next, the robot uses a crowd-aware navigation algorithm to move freely in highly dynamic scenarios. The robot finally uses a crowdaware routing algorithm to effectively promote social distancing by using human-friendly verbal cues to send suggestions to overcrowded pedestrians. We demonstrate and validate that our robot can be operated autonomously by conducting several experiments in various urban scenarios.

show abstract

“…Pedestrian tracking has been widely applied in surveillance video analysis and is well developed based on research on multi-object tracking problems [4]- [7].…”

Section: A Perception For Surveillance Systemsmentioning

confidence: 99%

Autonomous Social Distancing in Urban Environments using a Quadruped Robot

Fan¹,

Chen²,

Zhao³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The detection bounding boxes are used as inputs to DensePeds [26], a state-of-the-art pedestrian tracking algorithm that assigns a unique ID to each detected pedestrian across multiple consecutive images. This ID is used to compute each pedestrian's position in the image over time.…”

Section: Pedestrian Detection and Trackingmentioning

confidence: 99%

Frozone: Freezing-Free, Pedestrian-Friendly Navigation in Human Crowds

Sathyamoorthy¹,

Patel²,

Guan³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

We present Frozone, a novel algorithm to deal with the Freezing Robot Problem (FRP) that arises when a robot navigates through dense scenarios and crowds. Our method senses and explicitly predicts the trajectories of pedestrians and constructs a Potential Freezing Zone (PFZ); a spatial zone where the robot could freeze or be obtrusive to humans. Our formulation computes a deviation velocity to avoid the PFZ, which also accounts for social constraints. Furthermore, Frozone is designed for robots equipped with sensors with a limited sensing range and field of view. We ensure that the robot's deviation is bounded, thus avoiding sudden angular motion which could lead to the loss of perception data of the surrounding obstacles. We have combined Frozone with a Deep Reinforcement Learning-based (DRL) collision avoidance method and use our hybrid approach to handle crowds of varying densities. Our overall approach results in smooth and collision-free navigation in dense environments. We have evaluated our method's performance in simulation and on real differential drive robots in challenging indoor scenarios. We highlight the benefits of our approach over prior methods in terms of success rates (upto 50 % increase), pedestrianfriendliness (100 % increase) and the rate of freezing ( > 80% decrease) in challenging scenarios.

show abstract

“…In the deep learning era, interesting methods like [39], [47], [31], [35] have been proposed to this end. Traffic trajectory prediction [9,13,14] and tracking [8,[10][11][12], have been widely studied robotics and computer vision, whereas driver behavior modeling has mostly been restricted to traffic psychology and the social sciences [1-4, 7, 15-17, 19, 20, 22, 25, 33, 34, 34, 38, 42, 45, 48].…”

Section: Driving Scene Understandingmentioning

confidence: 99%

“…We stack 3 layers of ST-GCN i.e. the pair of equations (8) and (9) with temporal span τ = 3. The last layer of ST-GCN is followed by the classifier that includes average pooling and fully connected layers to obtain the classification logits, which are further converted into class probabilities using the softmax layer.…”

Section: Implementation Detailsmentioning

confidence: 99%

RAIST: Learning Risk Aware Traffic Interactions via Spatio-Temporal Graph Convolutional Networks

Videsh¹,

Pham²,

Bera³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

A key aspect of driving a road vehicle is to interact with the other road users, assess their intentions and make riskaware tactical decisions. An intuitive approach of enabling an intelligent automated driving system would be to incorporate some aspects of the human driving behavior. To this end, we propose a novel driving framework for egocentric views, which is based on spatio-temporal traffic graphs. The traffic graphs not only model the spatial interactions amongst the road users, but also their individual intentions through temporally associated message passing. We leverage spatio-temporal graph convolutional network (ST-GCN) to train the graph edges. These edges are formulated using parameterized functions of 3D positions and sceneaware appearance features of road agents. Along with tactical behavior prediction, it is crucial to evaluate the risk assessing ability of the proposed framework. We claim that our framework learns risk aware representations by improving on the task of risk object identification, especially in identifying objects with vulnerable interactions like pedestrians and cyclists.

show abstract

DensePeds: Pedestrian Tracking in Dense Crowds Using Front-RVO and Sparse Features

Cited by 7 publications

References 0 publications

Autonomous Social Distancing in Urban Environments using a Quadruped Robot

Autonomous Social Distancing in Urban Environments using a Quadruped Robot

Frozone: Freezing-Free, Pedestrian-Friendly Navigation in Human Crowds

RAIST: Learning Risk Aware Traffic Interactions via Spatio-Temporal Graph Convolutional Networks

Contact Info

Product

Resources

About