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

road detection

FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION


Road detection is a key component of Advanced Driving Assistance Systems, which provides valid space and candidate regions of objects for vehicles. Mainstream road detection methods have focused on extracting discriminative features. In this paper, we propose a robust feature fusion framework, called “Feature++”, which is combined with superpixel feature and 3D feature extracted from stereo images. Then a neural network classifier is been trained to decide whether a superpixel is road region or not. Finally, the classified results are further refined by conditional random field.

Paper Details

Authors:
Guorong Cai,Zhun Zhong,Songzhi Su
Submitted On:
8 May 2017 - 5:17am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster_hwl.pdf

(27 downloads)

Keywords

Additional Categories

Subscribe

[1] Guorong Cai,Zhun Zhong,Songzhi Su, "FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1794. Accessed: Jun. 25, 2017.
@article{1794-17,
url = {http://sigport.org/1794},
author = {Guorong Cai;Zhun Zhong;Songzhi Su },
publisher = {IEEE SigPort},
title = {FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION},
year = {2017} }
TY - EJOUR
T1 - FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION
AU - Guorong Cai;Zhun Zhong;Songzhi Su
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1794
ER -
Guorong Cai,Zhun Zhong,Songzhi Su. (2017). FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION. IEEE SigPort. http://sigport.org/1794
Guorong Cai,Zhun Zhong,Songzhi Su, 2017. FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION. Available at: http://sigport.org/1794.
Guorong Cai,Zhun Zhong,Songzhi Su. (2017). "FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION." Web.
1. Guorong Cai,Zhun Zhong,Songzhi Su. FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1794

FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION


Road detection is a key component of Advanced Driving Assistance Systems, which provides valid space and candidate regions of objects for vehicles. Mainstream road detection methods have focused on extracting discriminative features. In this paper, we propose a robust feature fusion framework, called “Feature++”, which is combined with superpixel feature and 3D feature extracted from stereo images. Then a neural network classifier is been trained to decide whether a superpixel is road region or not. Finally, the classified results are further refined by conditional random field.

Paper Details

Authors:
Guorong Cai,Zhun Zhong,Songzhi Su
Submitted On:
8 May 2017 - 5:17am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

poster_hwl.pdf

(24 downloads)

Keywords

Additional Categories

Subscribe

[1] Guorong Cai,Zhun Zhong,Songzhi Su, "FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1793. Accessed: Jun. 25, 2017.
@article{1793-17,
url = {http://sigport.org/1793},
author = {Guorong Cai;Zhun Zhong;Songzhi Su },
publisher = {IEEE SigPort},
title = {FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION},
year = {2017} }
TY - EJOUR
T1 - FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION
AU - Guorong Cai;Zhun Zhong;Songzhi Su
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1793
ER -
Guorong Cai,Zhun Zhong,Songzhi Su. (2017). FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION. IEEE SigPort. http://sigport.org/1793
Guorong Cai,Zhun Zhong,Songzhi Su, 2017. FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION. Available at: http://sigport.org/1793.
Guorong Cai,Zhun Zhong,Songzhi Su. (2017). "FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION." Web.
1. Guorong Cai,Zhun Zhong,Songzhi Su. FEATURE++: CROSS DIMENSION FEATURE FUSION FOR ROAD DETECTION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1793