Results 21 to 30 of about 16,201 (241)

Robust Superpixel Tracking [PDF]

open access: yesIEEE Transactions on Image Processing, 2014
While numerous algorithms have been proposed for object tracking with demonstrated success, it remains a challenging problem for a tracker to handle large appearance change due to factors such as scale, motion, shape deformation, and occlusion. One of the main reasons is the lack of effective image representation schemes to account for appearance ...
Yang, Fan, Lu, Huchuan, Yang, Ming-Hsuan
openaire   +2 more sources

Hybrid superpixel segmentation [PDF]

open access: yes2015 International Conference on Image and Vision Computing New Zealand (IVCNZ), 2015
Superpixel over-segment image into meaningful clusters so that pixels in each cluster belong to one object. Many state-of-art superpixel algorithms have to make trade-offs between different concerns. As a result, algorithms that can produce good result in some situations fail in another.
Yu, Y, Lai, S, Liu, Y, Du, T
openaire   +2 more sources

Brain tumor detection in MR image using superpixels, principal component analysis and template based K-means clustering algorithm

open access: yes, 2021
In the present era, human brain tumor is the extremist dangerous and devil to the human being that leads to certain death. Furthermore, the brain tumor arises more complexity of patients life with time.
K. Islam   +5 more
semanticscholar   +1 more source

Semi-automatic segmentation of skin lesions based on superpixels and hybrid texture information

open access: yesMedical Image Anal., 2022
Dermoscopic images are commonly used in the early diagnosis of skin lesions, and several computational systems have been proposed to analyze them. The segmentation of the lesions is a fundamental step in many of these systems. Therefore, a semi-automatic
E. Santos   +6 more
semanticscholar   +1 more source

HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation [PDF]

open access: yesIEEE Workshop/Winter Conference on Applications of Computer Vision, 2021
Superpixels serve as a powerful preprocessing tool in numerous computer vision tasks. By using superpixel representation, the number of image primitives can be largely reduced by orders of magnitudes. With the rise of deep learning in recent years, a few
Hankui Peng   +2 more
semanticscholar   +1 more source

Superpixel segmentation based on image density

open access: yesSystems Science & Control Engineering, 2023
Superpixel segmentation can get the middle features in image processing, effectively reduce the dimensionality of the image, and is widely used in image processing fields. To get the regular and compact superpixels in real-time, a superpixel segmentation
Dong-Fang Qiu   +3 more
doaj   +1 more source

Extended set of superpixel features

open access: yesКомпьютерная оптика, 2021
Superpixel-based image processing and analysis methods usually use a small set of superpixel features. Expanding the description of superpixels can improve the quality of processing algorithms. In the paper, a set of 25 basic superpixel features of shape,
A.A. Egorova, V.V. Sergeyev
doaj   +1 more source

Heterogeneous Images Change Detection Based on Iterative Joint Global–Local Translation

open access: yesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022
Most heterogeneous change detection methods based on transfer learning may not yield satisfactory results due to the lack of comprehensive utilization of the global and local characteristics of the image.
Hao Chen, Fachuan He, Jinming Liu
doaj   +1 more source

Self-Adaptive Superpixels Based on Neural Network Models

open access: yesIEEE Access, 2020
In this paper, the self-adaptive superpixels are generated based on a neural network model. Superpixels are clusters of pixels, which can simplify the expression of images. Superpixels are widely used in the field of video/image processing.
Xiuxiu Bai, Cong Wang, Zhiqiang Tian
doaj   +1 more source

PDC: Piecewise Depth Completion utilizing Superpixels [PDF]

open access: yesInternational Conference on Intelligent Transportation Systems, 2021
Depth completion from sparse LiDAR and high-resolution RGB data is one of the foundations for autonomous driving techniques. Current approaches often rely on CNN-based methods with several known drawbacks: flying pixel at depth discontinuities ...
Dennis Teutscher   +2 more
semanticscholar   +1 more source

Home - About - Disclaimer - Privacy