OVVV: Using Virtual Worlds to Design and Evaluate Surveillance Systems

By Geoffrey R. Taylor, Andrew J. Chosak, Paul C. Brewer. 2007

118 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Strike (With) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects (2018, methodology): “Previous research has successfully used 3D graphics as a diagnostic tool for computer vision systems [7, 31, 47, 32, 50].”
Playing for Data: Ground Truth from Computer Games (2016, methodology): “Development tools accompanying the game Half Life 2 were used for evaluating visual surveillance systems [47].”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “with different levels of labeling for free and therefore have great promise for deep learning across a variety of computer vision problems, including optical ﬂow [179, 180, 181, 182], object trackers [183, 177], depth estimation from RGB [184], object detection [185, 186, 187] semantic segmentation ”
VirtualWorlds as Proxy for Multi-object Tracking Analysis (2016, background): “In the context of video surveillance too, [20] proposes a virtual simulation test bed for system design and evaluation.”
UnrealCV: Connecting Computer Vision to Unreal Engine (2016, methodology): “Virtual worlds have been used for autonomous driving[5], naive physics simulations[1] and evaluating surveillance system[19].”
Adopting Abstract Images for Semantic Scene Understanding (2016, methodology): “Synthetic images and video data have been used to advance computer vision in a variety of ways including evaluating the performance of tracking and surveillance algorithms [56], training classifiers for”
Learning scene-specific pedestrian detectors without real data (2015, methodology): “Synthetic data can also be used for evaluation [35].”
Synthetic Data for Deep Learning (2019, methodology): “[582] used the Half-Life 2 game engine with additional camera parameters designed to simulate real-world surveillance cameras to detect a variety of different events.”
Crowd Analysis Using Computer Vision Techniques (2010, methodology): “Despite the successful use of computer graphics techniques to train and/or validate computer vision algorithms in some specific cases [9], [10], using crowd simulation algorithms to help crowd analysis techniques still presents several open problems.”
Play and Learn: Using Video Games to Train Computer Vision Models (2016, methodology): “[44] present a system called ObjectVideo Virtual Video (OVVV) based on Half-life [1] for evaluation of tracking in surveillance systems.”
Soccer on Your Tabletop (2018, background): “An alternative would be to use synthetic data [49, 22, 47, 44], but these virtual worlds are far from our soccer scenario.”