Results 181 to 190 of about 6,422 (208)
Some of the next articles are maybe not open access.
Constrained Superpixel Tracking
IEEE Transactions on Cybernetics, 2018In this paper, we propose a constrained graph labeling algorithm for visual tracking where nodes denote superpixels and edges encode the underlying spatial, temporal, and appearance fitness constraints. First, the spatial smoothness constraint, based on a transductive learning method, is enforced to leverage the latent manifold structure in feature ...
Lijun Wang +2 more
openaire +2 more sources
Benchmarking superpixel descriptors
2015 23rd European Signal Processing Conference (EUSIPCO), 2015Superpixels are useful intermediate representations for many computer vision tasks. While the segmentation step is well studied, the subsequent creation of meaningful descriptors lacks this foundation. Superpixels have similar properties like affine covariant regions (keypoints), but there are fundamental differences that led to a different set of ...
Peer Neubert, Peter Protzel
openaire +2 more sources
Spherical Superpixel Segmentation
IEEE Transactions on Multimedia, 2018These days, superpixel algorithms are widely used in computer vision and multimedia applications. However, existing algorithms are designed for planar images, which are less suited to deal with wide angle images. In this paper, we present a superpixel segmentation method for $\text{360}^\circ$ spherical images.
Qiang Zhao 0005 +5 more
openaire +2 more sources
2022
Recently, Deep neural networks (DNNs) have been highly successful in solving complicated vision problems. However, these DNNs are regarded as black-box models in terms of the lack of transparency in their decision-making process. There has been an increase in research interest in explaining deep models.
YONGWEI YI, Hanshan Qing, Yingying Liu
openaire +1 more source
Recently, Deep neural networks (DNNs) have been highly successful in solving complicated vision problems. However, these DNNs are regarded as black-box models in terms of the lack of transparency in their decision-making process. There has been an increase in research interest in explaining deep models.
YONGWEI YI, Hanshan Qing, Yingying Liu
openaire +1 more source
2021 International Russian Automation Conference (RusAutoCon), 2021
This paper offers the simplest understanding of superpixels as maximal pixel clusters providing error-free obtaining of a limited sequence of accessible optimal piecewise constant image approximations with the minimum achievable approximation error (total squared error) E for each number of pixel clusters.
openaire +1 more source
This paper offers the simplest understanding of superpixels as maximal pixel clusters providing error-free obtaining of a limited sequence of accessible optimal piecewise constant image approximations with the minimum achievable approximation error (total squared error) E for each number of pixel clusters.
openaire +1 more source
Linear Spectral Clustering Superpixel
IEEE Transactions on Image Processing, 2017In this paper, we present a superpixel segmentation algorithm called linear spectral clustering (LSC), which is capable of producing superpixels with both high boundary adherence and visual compactness for natural images with low computational costs. In LSC, a normalized cuts-based formulation of image segmentation is adopted using a distance metric ...
Jiansheng Chen 0001 +2 more
openaire +2 more sources
Globally Measuring the Similarity of Superpixels by Binary Edge Maps for Superpixel Clustering
IEEE Transactions on Circuits and Systems for Video Technology, 2018This paper proposes an edge-based superpixel similarity measurement, which globally evaluates the similarity between superpixels by binary edge maps. The basic idea is to assess whether the superpixels are surrounded by the same edges. To this end, we first describe the edge spatial distributions by directional regions and then use the directional ...
Fanman Meng +5 more
openaire +1 more source
Object detection by labeling superpixels
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015Object detection is often conducted by object proposal generation and classification sequentially. This paper handles object detection in a superpixel oriented manner instead of the proposal oriented. Specially, this paper takes object detection as a multi-label superpixel labeling problem by minimizing an energy function. It uses the data cost term to
Junjie Yan +4 more
openaire +1 more source
Superpixels by Bilateral Geodesic Distance
IEEE Transactions on Circuits and Systems for Video Technology, 2017We present a novel superpixel generation algorithm based on a new definition of geodesic distance, called bilateral geodesic distance. In contrast to the traditional geodesic distance, the new bilateral geodesic distance of two pixels considers the distance between their positions as well as their color difference.
Yuanfeng Zhou +4 more
openaire +4 more sources
Haze removal on superpixel domain
2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), 2013Haze and fog cause poor visibility for vision sensor, and make computer vision problems challenging. In this paper, we propose a new de-hazing method for single image on super-pixel domain. One of widely used approaches for de-hazing is to introduce dark channel prior.
Sang-Woo Noh, Byungtae Ahn, In-So Kweon
openaire +2 more sources