ACVR2017
所属分类：模式识别(视觉/语音等)
开发工具：HTML
文件大小：28079KB
下载次数：0
上传日期：2019-05-10 02:41:57
上 传 者：
sh-1993
说明： 一种新颖的基于中心暗通道先验的突出目标检测方法
(An Innovative Salient Object Detection Using Center-Dark Channel Prior)
文件列表:
CDCP_iccv17.zip (1588226, 2019-05-10)
ICCV_RGBD2.zip (21921134, 2019-05-10)
LICENSE (1092, 2019-05-10)
images (0, 2019-05-10)
images\fig1.png (478426, 2019-05-10)
images\fig2.png (597457, 2019-05-10)
images\fig3.png (50304, 2019-05-10)
images\fig4.png (2708628, 2019-05-10)
images\fig5.png (289714, 2019-05-10)
index.html (7217, 2019-05-10)
logo (0, 2019-05-10)
logo\ACVRLogo.png (25952, 2019-05-10)
logo\ICCVLogo.png (202049, 2019-05-10)
logo\czhu.png (275862, 2019-05-10)
logo\gl.jpg (308892, 2019-05-10)
logo\wrg.jpg (253629, 2019-05-10)
logo\wwm.jpg (226565, 2019-05-10)
main.css (5609, 2019-05-10)
## An Innovative Salient Object Detection Using Center-Dark Channel Prior
| ![ICCV 2017 logo][logo-iccv] | Paper accepted at [2017 IEEE International Conference on Computer Vision (ICCV) Workshop](http://iccv2017.thecvf.com/) |
|:-:|---|
[logo-iccv]: https://github.com/ChunbiaoZhu/ACVR2017/blob/master/logo/ICCVLogo.png "ICCV 2017 logo"
## Journal Version (ACM Intelligent Systems and Technology)
Extended verision is published on ACM Intelligent Systems and Technology (Exploiting the Value of the Center-dark Channel Prior for Salient Object Detection), which can be downloaded at [here](https://dl.acm.org/citation.cfm?id=3319368).
## Abstract
Saliency detection aims to detect the most attractive objects in images, which has been widely used as a foundation for various multimedia applications. In this paper, we propose a novel salient object detection algorithm for RGB-D images using center-dark channel prior. First, we generate an initial saliency map based on color saliency map and depth saliency map of a given RGB-D image. Then, we generate a center-dark channel map based on centre saliency prior and dark channel prior. Finally, we fuse the initial saliency map with centre dark channel map to generate the final saliency map. The proposed algorithm is evaluated on two public RGB-D datasets, and the experimental results show that our method outperforms the state-of-the-art methods.
## Framework
## Web Page
https://chunbiaozhu.github.io/ACVR2017/
## Code & Results
Source code is released! You can download in [here](https://github.com/ChunbiaoZhu/ACVR2017/blob/master/CDCP_iccv17.zip)
You can download our Results on RGBD2 Dataset in [here](https://github.com/ChunbiaoZhu/ACVR2017/blob/master/ICCV_RGBD2.zip)
Reference
@INPROCEEDINGS{8265388,
author={C. Zhu and G. Li and W. Wang and R. Wang},
booktitle={2017 IEEE International Conference on Computer Vision Workshops (ICCVW)},
title={An Innovative Salient Object Detection Using Center-Dark Channel Prior},
year={2017},
volume={},
number={},
pages={1509-1515},
keywords={image colour analysis;object detection;RGB-D image;center-dark channel map;color saliency map;saliency detection;salient object detection algorithm;Euclidean distance;Feature extraction;Fuses;Image color analysis;Object detection;Visualization},
doi={10.1109/ICCVW.2017.178},
ISSN={},
month={Oct},}
@article{Zhu:2019:EVC:3325195.3319368,
author = {Zhu, Chunbiao and Zhang, Wenhao and Li, Thomas H. and Liu, Shan and Li, Ge},
title = {Exploiting the Value of the Center-dark Channel Prior for Salient Object Detection},
journal = {ACM Trans. Intell. Syst. Technol.},
issue_date = {May 2019},
volume = {10},
number = {3},
month = may,
year = {2019},
issn = {2157-6904},
pages = {32:1--32:20},
articleno = {32},
numpages = {20},
url = {http://doi.acm.org/10.1145/3319368},
doi = {10.1145/3319368},
acmid = {3319368},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {Salient object detection, center-dark channel prior},
}
## Previous work
If you were interested in this work, you may want to also check our previous work, [CAIP2017](https://chunbiaozhu.github.io/CAIP2017/), which offers a whole new idea.
If you were interested in this work, you may want to also check our previous work, [MM2017](https://chunbiaozhu.github.io/MM2017/), which offers a whole new application.
## Acknowledgements
This work was supported by the grant of National Natural Science Foundation of China (No.U1611461), Shenzhen Peacock Plan (20130408-183003656), and Science and Technology Planning Project of Guangdong Province, China (No. 2014B090910001).
## Contact
If you have any general doubt about our work or code which may be of interest for other researchers, please use the [public issues section](https://github.com/ChunbiaoZhu/ACVR2017/issues) on this github repo. Alternatively, drop us an e-mail at .
近期下载者：
相关文件：
收藏者：