Results 191 to 200 of about 471,167 (221)

Entropy rate superpixel segmentation

CVPR 2011, 2011
We propose a new objective function for superpixel segmentation. This objective function consists of two components: entropy rate of a random walk on a graph and a balancing term. The entropy rate favors formation of compact and homogeneous clusters, while the balancing function encourages clusters with similar sizes.
Ming-Yu Liu, Oncel Tuzel, Srikumar Ramalingam, Rama Chellappa   +3 more
openaire   +1 more source

4D Light Field Superpixel and Segmentation

IEEE Transactions on Image Processing, 2020
Superpixel segmentation of 2D images has been widely used in many computer vision tasks. Previous algorithms model the color, position, or higher spectral information for segmenting a 2D image. However, limited to the Gaussian imaging principle in a traditional camera, where each pixel is formed by summing lots of light rays from different angles ...
Hao Zhu, Qi Zhang, Qing Wang, Hongdong Li   +3 more
openaire   +2 more sources

Hierarchical Superpixel Segmentation via Structural Information Theory

SDM
Superpixel segmentation is a foundation for many higher-level computer vision tasks, such as image segmentation, object recognition, and scene understanding.
Minhui Xie, Hao Peng, Pu Li, Guangjie Zeng, Shuhai Wang, Jia Wu, Peng Li, Philip S. Yu   +7 more
semanticscholar   +1 more source

Superpixel segmentation: A benchmark

Signal Processing: Image Communication, 2017
Abstract Various superpixel approaches have been published recently. These algorithms are assessed using different evaluation metrics and datasets resulting in discrepancy in algorithm comparison. This calls for a benchmark to compare the state-of-the-arts methods and evaluate their pros and cons.
Murong Wang, Xiabi Liu, Yixuan Gao, Xiao Ma, Nouman Q. Soomro   +4 more
openaire   +1 more source

Two-Stage Registration of SAR Images With Large Distortion Based on Superpixel Segmentation

IEEE Transactions on Geoscience and Remote Sensing
When the geometric distortion of the synthetic aperture radar (SAR) images to be registered is large, the spatial correspondence between the feature points of the two images will change significantly.
D. Xiang, Xiaoyu Pan, Huaiyue Ding, Jianda Cheng, Xiaokun Sun   +4 more
semanticscholar   +1 more source

ESNet: An Efficient Framework for Superpixel Segmentation

IEEE transactions on circuits and systems for video technology (Print)
Superpixel segmentation divides an original image into mid-level regions to reduce the number of computational primitives for subsequent tasks. The two-stage approaches work better but have high computational complexity among the existing deep superpixel
Sen Xu, Shikui Wei, Tao Ruan, Yao Zhao
semanticscholar   +1 more source

Land cover classification based on the PSPNet and superpixel segmentation methods with high spatial resolution multispectral remote sensing imagery

Journal of Applied Remote Sensing, 2021
. Classifying land cover using high-resolution remote-sensing images is challenging. The emergence of deep learning provides improved possibilities, but owing to the limitations of network structures, traditional convolutional neural network methods lose
Xiuzhong Yuan, Zeqiang Chen, Nengcheng Chen, J. Gong   +3 more
semanticscholar   +1 more source

Minimum barrier superpixel segmentation

Image and Vision Computing, 2018
Abstract Superpixel has become an essential processing unit in many computer vision systems, and superpixel segmentation of images is one of the most important step. In this paper, an efficient superpixel segmentation algorithm was proposed. We introduce a new compact-aware minimum barrier distance for superpixel segmentation (MBS), and a propagation
Yinlin Hu, Yunsong Li, Rui Song, Peng Rao, Yangli Wang   +4 more
openaire   +1 more source

Lazy Random Walks for Superpixel Segmentation

IEEE Transactions on Image Processing, 2014
We present a novel image superpixel segmentation approach using the proposed lazy random walk (LRW) algorithm in this paper. Our method begins with initializing the seed positions and runs the LRW algorithm on the input image to obtain the probabilities of each pixel.
Jianbing, Shen, Yunfan, Du, Wenguan, Wang, Xuelong, Li   +3 more
openaire   +2 more sources

Superpixel Segmentation via Density Peaks

2021 4th International Conference on Information and Computer Technologies (ICICT), 2021
Superpixel segmentation, a preprocessing component, is widely used in computer vision tasks. Superpixel algorithm is supposed to generate superpixels with required boundary adherence, compactness as well as less computational complexity. However, most of the existing superpixel algorithms do not perform satisfactorily when it comes to compactness and ...
Sayed Asad Hussain Shah, Liang Li, Yajun Li, Jiawan Zhang   +3 more
openaire   +1 more source