Filters








4,685 Hits in 4.0 sec

Recognizing human-vehicle interactions from aerial video without training

Jong Taek Lee, Chia-Chih Chen, J. K. Aggarwal
2011 CVPR 2011 WORKSHOPS  
We propose a novel framework to recognize humanvehicle interactions from aerial video.  ...  Our framework can be easily extended to recognize other types of human-vehicle interactions.  ...  With careful and sometimes repeated inspections, a human observer can recognize human-vehicle interactions from aerial video without seeing any examples from the same setup.  ... 
doi:10.1109/cvprw.2011.5981794 dblp:conf/cvpr/LeeCA11 fatcat:2sebwvikvbaglmgkrw53nke2oq

Recognizing Humans in Motion: Trajectory-based Aerial Video Analysis

Yumi Iwashita, Michael Ryoo, Thomas Fuchs, Curtis Padgett
2013 Procedings of the British Machine Vision Conference 2013  
We propose a novel method for recognizing people in aerial surveillance videos. Aerial surveillance images cover a wide area at low resolution.  ...  ., pedestrians) from such videos, conventional methods either utilize appearance information from raw videos or extract blob information from background subtraction results.  ...  In this dataset, more than 10 actors were asked to move on a ground while the quadrotor was recording the videos, by performing typical activities observed in aerial videos including human-vehicle interactions  ... 
doi:10.5244/c.27.127 dblp:conf/bmvc/IwashitaRFP13 fatcat:3awseveia5b7ncoxadycrjpqea

An Overview of Contest on Semantic Description of Human Activities (SDHA) 2010 [chapter]

M. S. Ryoo, Chia-Chih Chen, J. K. Aggarwal, Amit Roy-Chowdhury
2010 Lecture Notes in Computer Science  
A methodology using a spatio-temporal voting [19] successfully classified segmented videos in the UT-Interaction datasets, but had a difficulty correctly localizing activities from continuous videos.  ...  SDHA 2010 consists of three types of challenges, High-level Human Interaction Recognition Challenge, Aerial View Activity Classification Challenge, and Wide-Area Activity Search and Recognition Challenge  ...  This challenge is particularly motivated by military applications such as unmanned aerial vehicles taking videos from an aerial view.  ... 
doi:10.1007/978-3-642-17711-8_28 fatcat:b5zxatg7crfhxgn2ez6zinxq24

Joint Inference of Groups, Events and Human Roles in Aerial Videos [article]

Tianmin Shu, Dan Xie, Brandon Rothrock, Sinisa Todorovic, Song-Chun Zhu
2015 arXiv   pre-print
This paper addresses a new problem of parsing low-resolution aerial videos of large spatial areas, in terms of 1) grouping, 2) recognizing events and 3) assigning roles to people engaged in events.  ...  With the advent of drones, aerial video analysis becomes increasingly important; yet, it has received scant attention in the literature.  ...  As they frequently occur in the data, they can be robustly extracted from training videos through unsupervised clustering.  ... 
arXiv:1505.05957v1 fatcat:xngaqq25unet7jmakl4vu7zpum

Joint inference of groups, events and human roles in aerial videos

Tianmin Shu, Dan Xie, Brandon Rothrock, Sinisa Todorovic, Song-Chun Zhu
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
., information that cannot be re- liably extracted from our aerial videos.  ...  Addressing a more challenging setting of aerial videos; proaches mainly focus on detecting and tracking people or vehicles [38, 23, 13].  ... 
doi:10.1109/cvpr.2015.7299088 dblp:conf/cvpr/ShuXRTZ15 fatcat:vlewglatrva5ndtjsfsosx5ma4

Context augmented Dynamic Bayesian Networks for event recognition

Xiaoyang Wang, Qiang Ji
2014 Pattern Recognition Letters  
in surveillance videos.  ...  This paper proposes a new Probabilistic Graphical Model (PGM) to incorporate the scene, event object interaction, and the event temporal contexts into Dynamic Bayesian Networks (DBNs) for event recognition  ...  The first dataset is the VIRAT aerial dataset (ApHill) (Oh et al., 2011) with approximately 4 h of videos. We choose to recognize eight events from this dataset.  ... 
doi:10.1016/j.patrec.2013.07.015 fatcat:q2z4dpn76rgqhgwwdsjqtytsyq

Multi-source Multi-modal Activity Recognition in Aerial Video Surveillance

Riad I. Hammoud, Cem S. Sahin, Erik P. Blasch, Bradley J. Rhodes
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops  
(voice-to-text) made by a human watching the streamed FMV from an aerial platform.  ...  Recognizing activities in wide aerial/overhead imagery remains a challenging problem due in part to low-resolution video and cluttered scenes with a large number of moving objects.  ...  Acknowledgments This work was supported under contract number FA8750-13-C-0099 from the Air Force Research laboratory.  ... 
doi:10.1109/cvprw.2014.44 dblp:conf/cvpr/HammoudSBR14 fatcat:p7pqnfbzefdplpm5eztcgk2lge

Object and event recognition for aerial surveillance

Yi Li, Indriyati Atmosukarto, Masaharu Kobashi, Jenny Yuen, Linda G. Shapiro, Theodore T. Saito
2005 Optics and Photonics in Global Homeland Security  
Unmanned aerial vehicles with high quality video cameras are able to provide videos from 50,000 feet up that show a surprising amount of detail on the ground.  ...  Recognizing both the moving and static objects is important in order to find events of interest to human analysts.  ...  ACKNOWLEDGMENTS This research was supported by the National Science Foundation under grant IIS0097329 and by ARDA through a subcontract from the Boeing company.  ... 
doi:10.1117/12.609109 fatcat:i4uep23q5nabfbhlekg3eel5he

Automatic Association of Chats and Video Tracks for Activity Learning and Recognition in Aerial Video Surveillance

Riad Hammoud, Cem Sahin, Erik Blasch, Bradley Rhodes, Tao Wang
2014 Sensors  
VIVA and MINER examples are demonstrated for wide aerial/overhead imagery over common data sets affording an improvement in tracking from video data alone, leading to 84% detection with modest misdetection  ...  We also present an activity pattern learning framework that uses the multi-source associated data as training to index a large archive of full-motion videos (FMV).  ...  Acknowledgments This work was supported under contract number FA8750-13-C-0099 from the Air Force Research laboratory.  ... 
doi:10.3390/s141019843 pmid:25340453 pmcid:PMC4239870 fatcat:ony3ylej4nhzxbnap2zide3kwi

The State of Aerial Surveillance: A Survey [article]

Kien Nguyen, Clinton Fookes, Sridha Sridharan, Yingli Tian, Feng Liu, Xiaoming Liu, Arun Ross
2022 arXiv   pre-print
This paper provides a comprehensive overview of human-centric aerial surveillance tasks from a computer vision and pattern recognition perspective.  ...  The main object of interest is humans, where single or multiple subjects are to be detected, identified, tracked, re-identified and have their behavior analyzed.  ...  Popular human-human interactions can be in forms of violence [111] , [127] , social interactions [80] .  ... 
arXiv:2201.03080v2 fatcat:x7o6zgx2x5cwjkz5ftuizll7nu

A survey of video datasets for human action and activity recognition

Jose M. Chaquet, Enrique J. Carmona, Antonio Fernández-Caballero
2013 Computer Vision and Image Understanding  
Vision-based human action and activity recognition has an increasing importance among the computer vision community with applications to visual surveillance, video retrieval and human-computer interaction  ...  The survey introduced in this paper tries to cover the lack of a complete description of the most important public datasets for video-based human activity and action recognition and to guide researchers  ...  Video samples generated from training movies correspond to the automatic training subset with noisy action labels.  ... 
doi:10.1016/j.cviu.2013.01.013 fatcat:dbfnlrug3vhfrjfgyxcj2cnuli

A large-scale benchmark dataset for event recognition in surveillance video

Sangmin Oh, Anthony Hoogs, Amitha Perera, Naresh Cuntoor, Chia-Chih Chen, Jong Taek Lee, Saurajit Mukherjee, J. K. Aggarwal, Hyungtae Lee, Larry Davis, Eran Swears, Xioyang Wang (+12 others)
2011 CVPR 2011  
The dataset includes large numbers of instances for 23 event types distributed throughout 29 hours of video.  ...  Our dataset consists of many outdoor scenes with actions occurring naturally by non-actors in continuously captured videos of the real world.  ...  The dataset includes videos collected from both stationary ground cameras and moving aerial vehicles.  ... 
doi:10.1109/cvpr.2011.5995586 dblp:conf/cvpr/OhHPCCLMALDSWJRSVPRYTSFRD11 fatcat:fkkxv762izfetdrthrhnopjbb4

Understanding Transit Scenes: A Survey on Human Behavior-Recognition Algorithms

J. Candamo, M. Shreve, D.B. Goldgof, D.B. Sapper, R. Kasturi
2010 IEEE transactions on intelligent transportation systems (Print)  
., loitering), multipleperson interactions (e.g., fighting and personal attacks), personvehicle interactions (e.g., vehicle vandalism), and person-facility/ location interactions (e.g., object left behind  ...  This paper provides a thorough description of the research on relevant human behavior-recognition methods for transit surveillance.  ...  aerial video.  ... 
doi:10.1109/tits.2009.2030963 fatcat:tiajxro6sbc23p2rdaam2pwyna

Convolutional Neural Networks for Aerial Vehicle Detection and Recognition [article]

Amir Soleimani, Nasser M. Nasrabadi, Elias Griffith, Jason Ralph, Simon Maskell
2018 arXiv   pre-print
We train and test our model on a synthetic aerial dataset and our desired classes consist of the combination of the class types and colors of the vehicles.  ...  This paper investigates the problem of aerial vehicle recognition using a text-guided deep convolutional neural network classifier.  ...  Also, it can be used in human-human, human-vehicle, and vehicle-vehicle interaction understanding.  ... 
arXiv:1808.08560v1 fatcat:ystejzgprvferiqhahydt6haey

A Multiviewpoint Outdoor Dataset for Human Action Recognition

Asanka G. Perera, Yee Wei Law, Titilayo T. Ogunwa, Javaan Chahl
2020 IEEE Transactions on Human-Machine Systems  
All videos are cropped and resized to 720x720 without distorting the original aspect ratio of the human subjects in videos.  ...  Owing to the articulated nature of the human body, it is challenging to detect an action from multiple viewpoints, particularly from an aerial viewpoint.  ...  We cropped and resized the clips from their original videos without distorting their original aspect ratios.  ... 
doi:10.1109/thms.2020.2971958 fatcat:q4gs4twbyjbsdgsc7rqc5zbfhy
« Previous Showing results 1 — 15 out of 4,685 results