On the Complexity of Object Detection on Real-world Public Transportation Images for Social Distancing Measurement

• URL: http://arxiv.org/abs/2202.06639v1
• Date: Mon, 14 Feb 2022 11:47:26 GMT
• Title: On the Complexity of Object Detection on Real-world Public Transportation Images for Social Distancing Measurement
• Authors: Nik Khadijah Nik Aznan, John Brennan, Daniel Bell, Jennine Jonczyk and Paul Watson
• Abstract summary: Social distancing in public spaces has become an essential aspect in helping to reduce the impact of the COVID-19 pandemic. There has been no study of social distance measurement on public transport. We benchmark several state-of-the-art object detection algorithms using real-world footage taken from the London Underground and bus network.
• Score: 0.8347190888362194
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Social distancing in public spaces has become an essential aspect in helping to reduce the impact of the COVID-19 pandemic. Exploiting recent advances in machine learning, there have been many studies in the literature implementing social distancing via object detection through the use of surveillance cameras in public spaces. However, to date, there has been no study of social distance measurement on public transport. The public transport setting has some unique challenges, including some low-resolution images and camera locations that can lead to the partial occlusion of passengers, which make it challenging to perform accurate detection. Thus, in this paper, we investigate the challenges of performing accurate social distance measurement on public transportation. We benchmark several state-of-the-art object detection algorithms using real-world footage taken from the London Underground and bus network. The work highlights the complexity of performing social distancing measurement on images from current public transportation onboard cameras. Further, exploiting domain knowledge of expected passenger behaviour, we attempt to improve the quality of the detections using various strategies and show improvement over using vanilla object detection alone.

Related papers

• Camera-Radar Perception for Autonomous Vehicles and ADAS: Concepts, Datasets and Metrics [77.34726150561087]
  This work aims to carry out a study on the current scenario of camera and radar-based perception for ADAS and autonomous vehicles. Concepts and characteristics related to both sensors, as well as to their fusion, are presented. We give an overview of the Deep Learning-based detection and segmentation tasks, and the main datasets, metrics, challenges, and open questions in vehicle perception.
  arXiv  Detail & Related papers  (2023-03-08T00:48:32Z)
• Review on Action Recognition for Accident Detection in Smart City Transportation Systems [0.0]
  Monitoring traffic flows in a smart city using different surveillance cameras can play a significant role in recognizing accidents and alerting first responders. The utilization of action recognition (AR) in computer vision tasks has contributed towards high-precision applications in video surveillance, medical imaging, and digital signal processing. This paper provides potential research direction to develop and integrate accident detection systems for autonomous cars and public traffic safety systems.
  arXiv  Detail & Related papers  (2022-08-20T03:21:44Z)
• Scalable and Real-time Multi-Camera Vehicle Detection, Re-Identification, and Tracking [58.95210121654722]
  We propose a real-time city-scale multi-camera vehicle tracking system that handles real-world, low-resolution CCTV instead of idealized and curated video streams. Our method is ranked among the top five performers on the public leaderboard.
  arXiv  Detail & Related papers  (2022-04-15T12:47:01Z)
• Spatial Data Mining of Public Transport Incidents reported in Social Media [7.144384940254773]
  Social media communication of transport phenomena usually lacks GIS annotations. Most social media platforms do not allow attaching non-POI GPS coordinates to posts. We infer a six-class transport information typology through exploration. We show that our approach enables citizen science and use it to analyze the impact of three years of infrastructure incidents on passenger mobility.
  arXiv  Detail & Related papers  (2021-10-11T19:28:11Z)
• BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning [77.08836528980248]
  Social distancing, an essential public health measure, has gained significant attention since the outbreak of the COVID-19 pandemic. In this work, the problem of visual social distancing compliance assessment in busy public areas with wide field-of-view cameras is considered. A dataset of crowd scenes with people annotations under a bird's eye view (BEV) and ground truth for metric distances is introduced. A multi-branch network, BEV-Net, is proposed to localize individuals in world coordinates and identify high-risk regions where social distancing is violated.
  arXiv  Detail & Related papers  (2021-10-10T23:56:37Z)
• Surveilling Surveillance: Estimating the Prevalence of Surveillance Cameras with Street View Data [13.77902229604303]
  We build a camera detection model and apply it to 1.6 million street view images sampled from 10 large U.S. cities and 6 other major cities around the world. After adjusting for the estimated recall of our model, we are able to estimate the density of surveillance cameras visible from the road. In a detailed analysis of the 10 U.S. cities, we find that cameras are concentrated in commercial, industrial, and mixed zones, and in neighborhoods with higher shares of non-white residents.
  arXiv  Detail & Related papers  (2021-05-04T21:06:01Z)
• Monitoring Social-distance in Wide Areas during Pandemics: a Density Map and Segmentation Approach [0.0]
  We propose a new framework for monitoring the social-distance using end-to-end Deep Learning. Our framework consists in the creation of a new ground truth based on the ground truth density maps. We show that our framework performs well at providing the zones where people are not following the social-distance even when heavily occluded or far away from one camera.
  arXiv  Detail & Related papers  (2021-04-07T19:26:26Z)
• Automatic Social Distance Estimation From Images: Performance Evaluation, Test Benchmark, and Algorithm [78.88882860340797]
  COVID-19 virus has caused a global pandemic since March 2020. Maintaining a minimum of one meter distance from other people is strongly suggested to reduce the risk of infection. There is no suitable test benchmark for such algorithms.
  arXiv  Detail & Related papers  (2021-03-11T16:15:20Z)
• Perceiving Humans: from Monocular 3D Localization to Social Distancing [93.03056743850141]
  We present a new cost-effective vision-based method that perceives humans' locations in 3D and their body orientation from a single image. We show that it is possible to rethink the concept of "social distancing" as a form of social interaction in contrast to a simple location-based rule.
  arXiv  Detail & Related papers  (2020-09-01T10:12:30Z)
• Unsupervised Vehicle Counting via Multiple Camera Domain Adaptation [9.730985797769764]
  Monitoring vehicle flows in cities is crucial to improve the urban environment and quality of life of citizens. Current technologies for vehicle counting in images hinge on large quantities of annotated data, preventing their scalability to city-scale as new cameras are added to the system. We propose and discuss a new methodology to design image-based vehicle density estimators with few labeled data via multiple camera domain adaptations.
  arXiv  Detail & Related papers  (2020-04-20T13:00:46Z)
• Leveraging Multi-Source Weak Social Supervision for Early Detection of Fake News [67.53424807783414]
  Social media has greatly enabled people to participate in online activities at an unprecedented rate. This unrestricted access also exacerbates the spread of misinformation and fake news online which might cause confusion and chaos unless being detected early for its mitigation. We jointly leverage the limited amount of clean data along with weak signals from social engagements to train deep neural networks in a meta-learning framework to estimate the quality of different weak instances. Experiments on realworld datasets demonstrate that the proposed framework outperforms state-of-the-art baselines for early detection of fake news without using any user engagements at prediction time.
  arXiv  Detail & Related papers  (2020-04-03T18:26:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.