Superpixel lattices

By Alastair Moore, Simon J. D. Prince, Jonathan H. Warrell, Umar Mohammed, Graham Jones. 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008

427 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1328880541640d3c9aa1ce7b5201f90d6c4e0925

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

SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection (2015, background): “CNNs and other deep learning techniques have been shown to be effective in many vision applications, such as face detection and pose estimation (Osadchy et al. 2007), facial point detection (Sun et al. 2013), scene parsing (Farabet et al. 2013; Pinheiro and Collobert 2014), and image classification…”
Entropy rate superpixel segmentation (2011, methodology): “[14, 13] propose an alternative approach for obtaining superpixels aligned with a grid.”
Class segmentation and object localization with superpixel neighborhoods (2009, methodology): “We consider small regions obtained from a conservative oversegmentation, or “superpixels,” [29, 10, 25] to be the elementary unit of any detection, categorization or localization scheme.”
Lazy Random Walks for Superpixel Segmentation (2014, background): “The second category of superpixel algorithms considers the compactness constrains, such as normalized cuts [7], lattice cut [16], TurboPixels [17], and graph cut [19] approaches.”
Streaming Hierarchical Video Segmentation (2012, neutral): “Explained Variation is proposed in [20] as a humanindependent metric.”
Superpixels and Supervoxels in an Energy Optimization Framework (2010, methodology): “The formulation in [20, 21] poses certain restrictions on superpixel shapes: the boundary between superpixels cannot “turn back” on itself.”
SLIC Superpixels ? (2010, neutral): “A superpixel lattice is generated by [14] (SL08) by finding optimal vertical (horizontal) seams/paths that cut the image, within vertical (horizontal) strips of pixels, using graph cuts on strips of the image.”
Superpixels and Polygons Using Simple Non-iterative Clustering (2017, background): “Moore et al. [23] generate superpixels (SLAT) by finding the shortest paths that split an image into vertical and horizontal strips.”
SLIC Superpixels Compared to State-of-the-Art Superpixel Methods (2012, methodology): “SL08 – Moore et al. propose a method to generate superpixels that conform to a grid by ﬁnding optimal paths, or seams, that split the image into smaller vertical or horizontal regions [ 21].”
Voxel Cloud Connectivity Segmentation - Supervoxels for Point Clouds (2013, methodology): “[8] produce superpixels which conform to a regular lattice structure by seeking optimal paths horizontally and vertically across a boundary image.”
Superpixels: An evaluation of the state-of-the-art (2016, methodology): “We further proposed Average Recall, Average Undersegmentation Error and Average Explained Variation to summarize algorithm performance independent of the number of generated superpix-els.”
SEEDS: Superpixels Extracted Via Energy-Driven Sampling (2012, methodology): “[10,11] finds the optimal cuts by using precomputed boundary maps.”
Superpixel segmentation using Linear Spectral Clustering (2015, methodology): “We compare LSC to eight state of the art superpixel segmentation algorithms including SLIC [1], SEEDS [2], Ncuts [23], Lattice [15], ERS [12], Turbopixel [11], EneOpt1 and EneOpt0 [20].”