Active Crowd Analysis for Pandemic Risk Mitigation for Blind or Visually Impaired Persons

Shrestha, Samridha; Lu, Daohan; Tian, Hanlin; Cao, Qing; Liu, Julie; Rizzo, John Ross; Seiple, William; Porfiri, Maurizio; Fang, Yi

doi:10.1007/978-3-030-66823-5_25

Cited by 8 publications

(5 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Shrestha et al (2020) train their VSDM system on the PASCAL visual object classes challenge (VOC) 2007 ( Everingham et al, 2008 ) and VOC 2012 ( Everingham & Winn, 2011 ) datasets. Next, the system is tested on the PASCAL VOC 2007 test set.…”

Section: Datasetsmentioning

confidence: 99%

“…On the other hand, blind and visually impaired (BVI) people have some issues when practicing SD because of their low vision, which impedes them from maintaining a safe physical distance from other persons. To that end, the authors in Shrestha et al (2020) introduced a smartphone-based VSDM based on CNN crowd detection before associating risks to BVI users via directive audio alerts on their mobile phones. Typically, pedestrians are first detected, and their distances from the mobile phone’s monocular camera feed are estimated.…”

Section: Visual Social Distancing Monitoring (Vsdm)mentioning

confidence: 99%

“…Lastly, the system tracks each detection in previous frames to create motion maps that help (i) predict the crowds’ motion information and (ii) produce corresponding audio alerts. Active Crowd Analysis is designed for real-time smartphone use, utilizing the phone’s native hardware to ensure the BVI can safely maintain SD ( Shrestha et al, 2020 ).…”

Section: Visual Social Distancing Monitoring (Vsdm)mentioning

confidence: 99%

See 2 more Smart Citations

Deep visual social distancing monitoring to combat COVID-19: A comprehensive survey

Himeur

Al‐Maadeed

Almadeed

et al. 2022

Sustainable Cities and Society

View full text Add to dashboard Cite

Section: Datasetsmentioning

confidence: 99%

Section: Visual Social Distancing Monitoring (Vsdm)mentioning

confidence: 99%

Section: Visual Social Distancing Monitoring (Vsdm)mentioning

confidence: 99%

See 1 more Smart Citation

Deep visual social distancing monitoring to combat COVID-19: A comprehensive survey

Himeur

Al‐Maadeed

Almadeed

et al. 2022

Sustainable Cities and Society

View full text Add to dashboard Cite

“…Their ages are within 24-30. Due to COVID-19 restrictions especially the social-distancing regulation challenging for the visually impaired [39,47], the voluntary participants were sighted, and they were blindfolded during the tests. The first task focuses on the functionality of obstacle avoidance, whereas the second tests the functionality of instance locating and guidance ability for assisting users to find their interested objects.…”

Section: Function Testmentioning

confidence: 99%

HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor

Liu¹,

Liu²,

Yang

et al. 2021

Preprint

View full text Add to dashboard Cite

Independently exploring unknown spaces or finding objects in an indoor environment is a daily but challenging task for visually impaired people. However, common 2D assistive systems lack depth relationships between various objects, resulting in difficulty to obtain accurate spatial layout and relative positions of objects. To tackle these issues, we propose HIDA, a lightweight assistive system based on 3D point cloud instance segmentation with a solid-state LiDAR sensor, for holistic indoor detection and avoidance. Our entire system consists of three hardware components, two interactive functions (obstacle avoidance and object finding) and a voice user interface. Based on voice guidance, the point cloud from the most recent state of the changing indoor environment is captured through an on-site scanning performed by the user. In addition, we design a point cloud segmentation model with dual lightweight decoders for semantic and offset predictions, which satisfies the efficiency of the whole system. After the 3D instance segmentation, we post-process the segmented point cloud by removing outliers and projecting all points onto a top-view 2D map representation. The system integrates the information above and interacts with users intuitively by acoustic feedback. The proposed 3D instance segmentation model has achieved state-of-the-art performance on ScanNet v2 dataset. Comprehensive field tests with various tasks in a user study verify the usability and effectiveness of our system for assisting visually impaired people in holistic indoor understanding, obstacle avoidance and object search.

show abstract

“…Most advances in visual assistive technologies [ 4 ] rely on computer vision techniques and the use of a global positioning system (GPS) [ 5 ]. The centralized vision-based systems or those using GPS share limitations and problems with the previously mentioned crowd monitoring systems.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Network Model for Assisting People with Disabilities through Crowd Monitoring and Control

Falcon-Caro,

Peytchev,

Sanei

2024

Bioengineering

View full text Add to dashboard Cite

Here, we present an effective application of adaptive cooperative networks, namely assisting disables in navigating in a crowd in a pandemic or emergency situation. To achieve this, we model crowd movement and introduce a cooperative learning approach to enable cooperation and self-organization of the crowd members with impaired health or on wheelchairs to ensure their safe movement in the crowd. Here, it is assumed that the movement path and the varying locations of the other crowd members can be estimated by each agent. Therefore, the network nodes (agents) should continuously reorganize themselves by varying their speeds and distances from each other, from the surrounding walls, and from obstacles within a predefined limit. It is also demonstrated how the available wireless trackers such as AirTags can be used for this purpose. The model effectiveness is examined with respect to the real-time changes in environmental parameters and its efficacy is verified.

show abstract

Active Crowd Analysis for Pandemic Risk Mitigation for Blind or Visually Impaired Persons

Cited by 8 publications

References 38 publications

Deep visual social distancing monitoring to combat COVID-19: A comprehensive survey

Deep visual social distancing monitoring to combat COVID-19: A comprehensive survey

HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor

Adaptive Network Model for Assisting People with Disabilities through Crowd Monitoring and Control

Contact Info

Product

Resources

About