Sorry, you need to enable JavaScript to visit this website.

Image/Video Processing

Context-aware cascade network for semantic labeling in VHR image


Semantic labeling for the very high resolution (VHR) image of urban areas is challenging, because of many complex man-made objects with different materials and fine-structured ob-jects located together. Under the framework of convolutional neural networks (CNNs), this paper proposes a novel end-to-end network for semantic labeling.

Paper Details

Authors:
Yongcheng Liu, Bin Fan, Lingfeng Wang, Jun Bai, Shiming Xiang, Chunhong Pan
Submitted On:
15 September 2017 - 9:54am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2017ICIP_Lecture.pdf

(79 downloads)

Keywords

Additional Categories

Subscribe

[1] Yongcheng Liu, Bin Fan, Lingfeng Wang, Jun Bai, Shiming Xiang, Chunhong Pan, "Context-aware cascade network for semantic labeling in VHR image", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2136. Accessed: Apr. 20, 2018.
@article{2136-17,
url = {http://sigport.org/2136},
author = {Yongcheng Liu; Bin Fan; Lingfeng Wang; Jun Bai; Shiming Xiang; Chunhong Pan },
publisher = {IEEE SigPort},
title = {Context-aware cascade network for semantic labeling in VHR image},
year = {2017} }
TY - EJOUR
T1 - Context-aware cascade network for semantic labeling in VHR image
AU - Yongcheng Liu; Bin Fan; Lingfeng Wang; Jun Bai; Shiming Xiang; Chunhong Pan
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2136
ER -
Yongcheng Liu, Bin Fan, Lingfeng Wang, Jun Bai, Shiming Xiang, Chunhong Pan. (2017). Context-aware cascade network for semantic labeling in VHR image. IEEE SigPort. http://sigport.org/2136
Yongcheng Liu, Bin Fan, Lingfeng Wang, Jun Bai, Shiming Xiang, Chunhong Pan, 2017. Context-aware cascade network for semantic labeling in VHR image. Available at: http://sigport.org/2136.
Yongcheng Liu, Bin Fan, Lingfeng Wang, Jun Bai, Shiming Xiang, Chunhong Pan. (2017). "Context-aware cascade network for semantic labeling in VHR image." Web.
1. Yongcheng Liu, Bin Fan, Lingfeng Wang, Jun Bai, Shiming Xiang, Chunhong Pan. Context-aware cascade network for semantic labeling in VHR image [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2136

A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction

Paper Details

Authors:
Submitted On:
15 September 2017 - 9:09am
Short Link:
Type:
Event:

Document Files

ICIP2017_1924.pdf

(55 downloads)

Keywords

Subscribe

[1] , "A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2134. Accessed: Apr. 20, 2018.
@article{2134-17,
url = {http://sigport.org/2134},
author = { },
publisher = {IEEE SigPort},
title = {A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction},
year = {2017} }
TY - EJOUR
T1 - A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2134
ER -
. (2017). A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction. IEEE SigPort. http://sigport.org/2134
, 2017. A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction. Available at: http://sigport.org/2134.
. (2017). "A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction." Web.
1. . A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2134

ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS


We propose a method for accurate alignment of ground and aerial multi-view stereo (MVS) models. We achieve this goal by reconstructing the surface meshes from MVS point clouds generated by aerial and ground images respectively, and then iteratively removing the gap between them. The key issue is how to establish reliable correspondences between two meshes.

Paper Details

Authors:
Yang Zhou, Shuhan shen, Xiang Gao, Zhanyi Hu
Submitted On:
15 September 2017 - 8:51am
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

ICIP_poster.pdf

(59 downloads)

Keywords

Additional Categories

Subscribe

[1] Yang Zhou, Shuhan shen, Xiang Gao, Zhanyi Hu, "ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2130. Accessed: Apr. 20, 2018.
@article{2130-17,
url = {http://sigport.org/2130},
author = {Yang Zhou; Shuhan shen; Xiang Gao; Zhanyi Hu },
publisher = {IEEE SigPort},
title = {ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS},
year = {2017} }
TY - EJOUR
T1 - ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS
AU - Yang Zhou; Shuhan shen; Xiang Gao; Zhanyi Hu
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2130
ER -
Yang Zhou, Shuhan shen, Xiang Gao, Zhanyi Hu. (2017). ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS. IEEE SigPort. http://sigport.org/2130
Yang Zhou, Shuhan shen, Xiang Gao, Zhanyi Hu, 2017. ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS. Available at: http://sigport.org/2130.
Yang Zhou, Shuhan shen, Xiang Gao, Zhanyi Hu. (2017). "ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS." Web.
1. Yang Zhou, Shuhan shen, Xiang Gao, Zhanyi Hu. ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2130

COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER


In this paper, we propose an infinite impulse response (IIR)
filtering with complex coefficients for Euclid distance based
filtering, e.g. bilateral filtering. Recursive filtering of edgepreserving
filtering is the most efficient filtering. Recursive
bilateral filtering and domain transform filtering belong to
this type. These filters measure the difference between pixel
intensities by geodesic distance. Also, these filters do not
have separability. The aspects make the filter sensitive to

Paper Details

Authors:
Norishige Fukushima, Kenjiro Sugimoto, Sei-ichiro Kamata
Submitted On:
15 September 2017 - 8:43am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip_fukushima.pdf

(56 downloads)

Keywords

Subscribe

[1] Norishige Fukushima, Kenjiro Sugimoto, Sei-ichiro Kamata, "COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2129. Accessed: Apr. 20, 2018.
@article{2129-17,
url = {http://sigport.org/2129},
author = {Norishige Fukushima; Kenjiro Sugimoto; Sei-ichiro Kamata },
publisher = {IEEE SigPort},
title = {COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER},
year = {2017} }
TY - EJOUR
T1 - COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER
AU - Norishige Fukushima; Kenjiro Sugimoto; Sei-ichiro Kamata
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2129
ER -
Norishige Fukushima, Kenjiro Sugimoto, Sei-ichiro Kamata. (2017). COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER. IEEE SigPort. http://sigport.org/2129
Norishige Fukushima, Kenjiro Sugimoto, Sei-ichiro Kamata, 2017. COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER. Available at: http://sigport.org/2129.
Norishige Fukushima, Kenjiro Sugimoto, Sei-ichiro Kamata. (2017). "COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER." Web.
1. Norishige Fukushima, Kenjiro Sugimoto, Sei-ichiro Kamata. COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2129

Trademark Image Retrieval Using Hierarchical Region Feature Description


A novel trademark image retrieval(TIR) method is proposed in this work. The proposed approach commences with region partitioning through rotationally capturing multi-level regions of an image in a hierarchical manner, and then an effective region measurement is used as shape description of the regions generated from region partitioning stage. A shifting feature matching strategy is used to evaluate the similarity between the query and database images. The experimental results on the standard shape databases demonstrate its superiority performance over the state-of-the-art approaches.

Paper Details

Authors:
Feng Liu,Bin Wang,Fanqing Zeng
Submitted On:
15 September 2017 - 7:45am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

paper3209_poster.pdf

(60 downloads)

Keywords

Subscribe

[1] Feng Liu,Bin Wang,Fanqing Zeng, "Trademark Image Retrieval Using Hierarchical Region Feature Description", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2127. Accessed: Apr. 20, 2018.
@article{2127-17,
url = {http://sigport.org/2127},
author = {Feng Liu;Bin Wang;Fanqing Zeng },
publisher = {IEEE SigPort},
title = {Trademark Image Retrieval Using Hierarchical Region Feature Description},
year = {2017} }
TY - EJOUR
T1 - Trademark Image Retrieval Using Hierarchical Region Feature Description
AU - Feng Liu;Bin Wang;Fanqing Zeng
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2127
ER -
Feng Liu,Bin Wang,Fanqing Zeng. (2017). Trademark Image Retrieval Using Hierarchical Region Feature Description. IEEE SigPort. http://sigport.org/2127
Feng Liu,Bin Wang,Fanqing Zeng, 2017. Trademark Image Retrieval Using Hierarchical Region Feature Description. Available at: http://sigport.org/2127.
Feng Liu,Bin Wang,Fanqing Zeng. (2017). "Trademark Image Retrieval Using Hierarchical Region Feature Description." Web.
1. Feng Liu,Bin Wang,Fanqing Zeng. Trademark Image Retrieval Using Hierarchical Region Feature Description [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2127

Instance Flow Based Online Multiple Object Tracking

Paper Details

Authors:
Sebastian Bullinger, Christoph Bodensteiner, Michael Arens
Submitted On:
15 September 2017 - 7:41am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

InstanceFlowMOT.pdf

(55 downloads)

Keywords

Subscribe

[1] Sebastian Bullinger, Christoph Bodensteiner, Michael Arens, "Instance Flow Based Online Multiple Object Tracking", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2123. Accessed: Apr. 20, 2018.
@article{2123-17,
url = {http://sigport.org/2123},
author = {Sebastian Bullinger; Christoph Bodensteiner; Michael Arens },
publisher = {IEEE SigPort},
title = {Instance Flow Based Online Multiple Object Tracking},
year = {2017} }
TY - EJOUR
T1 - Instance Flow Based Online Multiple Object Tracking
AU - Sebastian Bullinger; Christoph Bodensteiner; Michael Arens
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2123
ER -
Sebastian Bullinger, Christoph Bodensteiner, Michael Arens. (2017). Instance Flow Based Online Multiple Object Tracking. IEEE SigPort. http://sigport.org/2123
Sebastian Bullinger, Christoph Bodensteiner, Michael Arens, 2017. Instance Flow Based Online Multiple Object Tracking. Available at: http://sigport.org/2123.
Sebastian Bullinger, Christoph Bodensteiner, Michael Arens. (2017). "Instance Flow Based Online Multiple Object Tracking." Web.
1. Sebastian Bullinger, Christoph Bodensteiner, Michael Arens. Instance Flow Based Online Multiple Object Tracking [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2123

LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES


Semantic segmentation of indoor scene images has a wide range of
applications. However, due to a large number of classes and uneven
distribution in indoor scenes, mislabels are often made when facing
small objects or boundary regions. Technically, contextual infor-
mation may benefit for segmentation results, but has not yet been
exploited sufficiently. In this paper, we propose a learnable contex-
tual regularization model for enhancing the semantic segmentation
results of color indoor scene images. This regularization model is

Paper Details

Authors:
Jun Chu , Xu Xiao, Gaofeng Meng , Lingfeng Wang and Chunhong Pan
Submitted On:
15 September 2017 - 7:33am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES

(114 downloads)

Keywords

Subscribe

[1] Jun Chu , Xu Xiao, Gaofeng Meng , Lingfeng Wang and Chunhong Pan , "LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2122. Accessed: Apr. 20, 2018.
@article{2122-17,
url = {http://sigport.org/2122},
author = {Jun Chu ; Xu Xiao; Gaofeng Meng ; Lingfeng Wang and Chunhong Pan },
publisher = {IEEE SigPort},
title = {LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES},
year = {2017} }
TY - EJOUR
T1 - LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES
AU - Jun Chu ; Xu Xiao; Gaofeng Meng ; Lingfeng Wang and Chunhong Pan
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2122
ER -
Jun Chu , Xu Xiao, Gaofeng Meng , Lingfeng Wang and Chunhong Pan . (2017). LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES. IEEE SigPort. http://sigport.org/2122
Jun Chu , Xu Xiao, Gaofeng Meng , Lingfeng Wang and Chunhong Pan , 2017. LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES. Available at: http://sigport.org/2122.
Jun Chu , Xu Xiao, Gaofeng Meng , Lingfeng Wang and Chunhong Pan . (2017). "LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES." Web.
1. Jun Chu , Xu Xiao, Gaofeng Meng , Lingfeng Wang and Chunhong Pan . LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2122

Cross-scale Color Image Restoration Under High Density Salt-and-pepper Noise


High-fidelity color image restoration is always of high de- manding for high-density noise corrupted images. Such problem becomes more challenging if the degraded image and the expected restored image are of different resolutions, as conventional ‘cascaded: denoising followed by sampling’ and ‘operation on RGB channel independently’ methods induce error amplification and color artifacts.

Paper Details

Authors:
Ketan Tang, Lu Fang
Submitted On:
15 September 2017 - 6:33am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP_poster.pdf

(65 downloads)

Keywords

Subscribe

[1] Ketan Tang, Lu Fang, "Cross-scale Color Image Restoration Under High Density Salt-and-pepper Noise", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2119. Accessed: Apr. 20, 2018.
@article{2119-17,
url = {http://sigport.org/2119},
author = {Ketan Tang; Lu Fang },
publisher = {IEEE SigPort},
title = {Cross-scale Color Image Restoration Under High Density Salt-and-pepper Noise},
year = {2017} }
TY - EJOUR
T1 - Cross-scale Color Image Restoration Under High Density Salt-and-pepper Noise
AU - Ketan Tang; Lu Fang
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2119
ER -
Ketan Tang, Lu Fang. (2017). Cross-scale Color Image Restoration Under High Density Salt-and-pepper Noise. IEEE SigPort. http://sigport.org/2119
Ketan Tang, Lu Fang, 2017. Cross-scale Color Image Restoration Under High Density Salt-and-pepper Noise. Available at: http://sigport.org/2119.
Ketan Tang, Lu Fang. (2017). "Cross-scale Color Image Restoration Under High Density Salt-and-pepper Noise." Web.
1. Ketan Tang, Lu Fang. Cross-scale Color Image Restoration Under High Density Salt-and-pepper Noise [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2119

EFFICIENT CLOUD DETECTION IN REMOTE SENSING IMAGES USING EDGE-AWARE SEGMENTATION NETWORK AND EASY-TO-HARD TRAINING STRATEGY


Detecting cloud regions in remote sensing image (RSI) is very challenging yet of great importance to meteorological forecasting and other RSI-related applications. Technically, this task is typically implemented as a pixel-level segmentation. However, traditional methods based on handcrafted or low-level cloud features often fail to achieve satisfactory performances from images with bright non-cloud and/or semitransparent cloud regions.

Paper Details

Authors:
Kun Yuan, Gaofeng Meng, Dongcai Cheng, Jun Bai, Shiming Xiang and Chunhong Pan
Submitted On:
15 September 2017 - 5:07am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Efficient cloud detection using edge-aware network and easy-to-hard training strategy

(75 downloads)

Keywords

Subscribe

[1] Kun Yuan, Gaofeng Meng, Dongcai Cheng, Jun Bai, Shiming Xiang and Chunhong Pan, "EFFICIENT CLOUD DETECTION IN REMOTE SENSING IMAGES USING EDGE-AWARE SEGMENTATION NETWORK AND EASY-TO-HARD TRAINING STRATEGY", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2115. Accessed: Apr. 20, 2018.
@article{2115-17,
url = {http://sigport.org/2115},
author = {Kun Yuan; Gaofeng Meng; Dongcai Cheng; Jun Bai; Shiming Xiang and Chunhong Pan },
publisher = {IEEE SigPort},
title = {EFFICIENT CLOUD DETECTION IN REMOTE SENSING IMAGES USING EDGE-AWARE SEGMENTATION NETWORK AND EASY-TO-HARD TRAINING STRATEGY},
year = {2017} }
TY - EJOUR
T1 - EFFICIENT CLOUD DETECTION IN REMOTE SENSING IMAGES USING EDGE-AWARE SEGMENTATION NETWORK AND EASY-TO-HARD TRAINING STRATEGY
AU - Kun Yuan; Gaofeng Meng; Dongcai Cheng; Jun Bai; Shiming Xiang and Chunhong Pan
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2115
ER -
Kun Yuan, Gaofeng Meng, Dongcai Cheng, Jun Bai, Shiming Xiang and Chunhong Pan. (2017). EFFICIENT CLOUD DETECTION IN REMOTE SENSING IMAGES USING EDGE-AWARE SEGMENTATION NETWORK AND EASY-TO-HARD TRAINING STRATEGY. IEEE SigPort. http://sigport.org/2115
Kun Yuan, Gaofeng Meng, Dongcai Cheng, Jun Bai, Shiming Xiang and Chunhong Pan, 2017. EFFICIENT CLOUD DETECTION IN REMOTE SENSING IMAGES USING EDGE-AWARE SEGMENTATION NETWORK AND EASY-TO-HARD TRAINING STRATEGY. Available at: http://sigport.org/2115.
Kun Yuan, Gaofeng Meng, Dongcai Cheng, Jun Bai, Shiming Xiang and Chunhong Pan. (2017). "EFFICIENT CLOUD DETECTION IN REMOTE SENSING IMAGES USING EDGE-AWARE SEGMENTATION NETWORK AND EASY-TO-HARD TRAINING STRATEGY." Web.
1. Kun Yuan, Gaofeng Meng, Dongcai Cheng, Jun Bai, Shiming Xiang and Chunhong Pan. EFFICIENT CLOUD DETECTION IN REMOTE SENSING IMAGES USING EDGE-AWARE SEGMENTATION NETWORK AND EASY-TO-HARD TRAINING STRATEGY [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2115

Improving the Discrimination Between Foreground and Background for Semantic Segmentation


#2125.pdf

PDF icon ICIP1701 (61 downloads)

Paper Details

Authors:
Submitted On:
15 September 2017 - 4:49am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP1701

(61 downloads)

Keywords

Subscribe

[1] , "Improving the Discrimination Between Foreground and Background for Semantic Segmentation", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2110. Accessed: Apr. 20, 2018.
@article{2110-17,
url = {http://sigport.org/2110},
author = { },
publisher = {IEEE SigPort},
title = {Improving the Discrimination Between Foreground and Background for Semantic Segmentation},
year = {2017} }
TY - EJOUR
T1 - Improving the Discrimination Between Foreground and Background for Semantic Segmentation
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2110
ER -
. (2017). Improving the Discrimination Between Foreground and Background for Semantic Segmentation. IEEE SigPort. http://sigport.org/2110
, 2017. Improving the Discrimination Between Foreground and Background for Semantic Segmentation. Available at: http://sigport.org/2110.
. (2017). "Improving the Discrimination Between Foreground and Background for Semantic Segmentation." Web.
1. . Improving the Discrimination Between Foreground and Background for Semantic Segmentation [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2110

Pages