Video Compass

By Jana Kosecka. 2002

395 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

SUN database: Large-scale scene recognition from abbey to zoo (2010, methodology): “Line Features: We detect straight lines from Canny edges using the method described in Video Compass [15].”
IM2GPS: estimating geographic information from a single image (2008, methodology): “We find straight lines from Canny edges using the method described in Video Compass [7].”
SUN Database: Exploring a Large Collection of Scene Categories (2014, methodology): “Line Hists: We find straight lines from Canny edges using the method described in Video Compass [23].”
Marr Revisited: 2D-3D Alignment via Surface Normal Prediction (2016, background): “Prior work has sought to recover the overall global shape of the room by fitting a global parametric 3D box [17, 39] or recovering informative edge maps [29] that align to the shape of the room, typically based on Manhattan world constraints [8, 21].”
Geometric context from a single image (2005, methodology): “Our system finds long, straight edges in the image using the method of [15].”
Handling Urban Location Recognition as a 2D Homothetic Problem (2010, methodology): “We detect line segments in the image using a method based on [19], estimate vanishing points as intersections of these lines, followed by a subsequent reﬁnement step.”
A Survey of Urban Reconstruction (2013, methodology): “Hoiem et al. [HEH05] proposed a method for creation of simpliﬁed “pop-up” 3d models from a single image, by using image segmentation and depth assignments based on vanishing points [RC02, KZ02].”
Human vs. Computer in Scene and Object Recognition (2014, background): “line hist features [7] are histograms based on the statistics of detected lines from an edge detector- one with bins corresponding to line angles and one with bins corresponding to line lengths.”
Putting Objects in Perspective (2006, methodology): “We investigated using image statistics, including vanishing points [13]”
Geometric reasoning for single image structure recovery (2009, methodology): “Kosecka and Wei [14] developed a method to recover vanishing points and camera parameters from a single image by using line segments found in Manhattan structures.”
Estimating Spatial Layout of Rooms using Volumetric Reasoning about Objects and Surfaces (2010, methodology): “[5] developed a method to recover vanishing points and camera parameters from a single image by using line segments found in Manhattan structures.”
3D Traffic Scene Understanding From Movable Platforms (2014, neutral): “Conclusions are drawn in Section 6.”
SKYLINE2GPS: Localization in urban canyons using omni-skylines (2010, methodology): “Small misalignments could be easily corrected using vanishing points [17].”
Recovering free space of indoor scenes from a single image (2012, background): “The ability to estimate the scene’s 3D geometry is important for many tasks, such as robot navigation and object placement/manipulation.”
Non-iterative approach for fast and accurate vanishing point detection (2009, methodology): “However, this is easily corrected by refining the solution using EM [3, 13].”
D Traffic Scene Understanding from Movable Platforms (2013, methodology): “[43], which we have modified slightly for taking into account the known camera calibration information.”
Orientation in Manhattan: equiprojective classes and sequential estimation (2005, neutral): “In the single-image case, typical methods involve feature grouping [5], [6], [7].”
Recovering Surface Layout from an Image (2007, methodology): “We compute these vanishing points over the entire image (without regard to any segmentation), using the EM approach described by Kosecka and Zhang (2002).”