Full-duplex strategy for video object segmentation
Appearance and motion are two important sources of information in video object
segmentation (VOS). Previous methods mainly focus on using simplex solutions, lowering …
segmentation (VOS). Previous methods mainly focus on using simplex solutions, lowering …
An object-oriented CNN model based on improved superpixel segmentation for high-resolution remote sensing image classification
Z Li, E Li, A Samat, T Xu, W Liu… - IEEE Journal of Selected …, 2022 - ieeexplore.ieee.org
Object-oriented convolutional neural network (CNN) has been proven to be an effective
classification method for very fine spatial resolution remotely sensed imagery. It can obtain …
classification method for very fine spatial resolution remotely sensed imagery. It can obtain …
Content-sensitive superpixel generation for SAR images with edge penalty and contraction–expansion search strategy
In this article, we present a content-sensitive superpixel generation method with edge
penalty and the contraction–expansion search strategy (EPCES) for synthetic aperture radar …
penalty and the contraction–expansion search strategy (EPCES) for synthetic aperture radar …
Superpixel embedding network
U Gaur, BS Manjunath - IEEE Transactions on Image …, 2019 - ieeexplore.ieee.org
Superpixel segmentation is a fundamental computer vision technique that finds application
in a multitude of high level computer vision tasks. Most state-of-the-art superpixel …
in a multitude of high level computer vision tasks. Most state-of-the-art superpixel …
[HTML][HTML] Reducing human efforts in video segmentation annotation with reinforcement learning
Manual annotation of video segmentation datasets requires an immense amount of human
effort, thus, reduction of human annotation costs is an active topic of research. While many …
effort, thus, reduction of human annotation costs is an active topic of research. While many …
Fast and accurate superpixel segmentation algorithm with a guidance image
Y Zhang, Y Zhang, L Fan, N Wang - Image and Vision Computing, 2023 - Elsevier
Superpixels are generated by automatically grouping image pixels into lots and lots of
compact segments. In computer vision, it is widely used as an effective way to reduce the …
compact segments. In computer vision, it is widely used as an effective way to reduce the …
Adaptive and fast image superpixel segmentation approach
N Wang, Y Zhang - Image and Vision Computing, 2021 - Elsevier
Superpixel is one of the most popular image over-segmentations with broad applications in
the computer vision field to reduce their computations by replacing pixels as primitives. The …
the computer vision field to reduce their computations by replacing pixels as primitives. The …
Tracking-by-segmentation using superpixel-wise neural network
A tracking-by-segmentation algorithm, which tracks and segments a target object in a video
sequence, is proposed in this paper. In the first frame, we segment out the target object in a …
sequence, is proposed in this paper. In the first frame, we segment out the target object in a …
Simple and fast image superpixels generation with color and boundary probability
Y Zhang, Q Guo, C Zhang - The Visual Computer, 2021 - Springer
As one of the most popular preprocessing steps in computer vision fields, superpixel
generation algorithm has been extensively studied in recent years. Researchers have to find …
generation algorithm has been extensively studied in recent years. Researchers have to find …
Fast and robust superpixel generation method
Y Zhang, Q Guo, Y Zhang, C Zhang - IET Image Processing, 2020 - Wiley Online Library
Superpixel segmentation approach, as a preprocessing step in computer vision tasks,
groups pixels into perceptually coherence atomic regions to replace the pixel grid in images …
groups pixels into perceptually coherence atomic regions to replace the pixel grid in images …