TY - GEN
T1 - Shadow estimation of outdoor environments via multi-cue optimization
AU - Gao, Ting
AU - Chen, Zhihua
AU - Sheng, Bin
AU - Li, Ping
AU - Gao, Daqi
PY - 2019/4
Y1 - 2019/4
N2 - Illumination condition prediction from given outdoor images is challenging but widely useful. Most of the existing methods predict the illumination based on the inserted markers or the limitation on the environment, which makes them impossible to directly predict the illumination condition from the nature images. We propose a multi-cues based illumination prediction approach that can predict the illumination condition by the input images only. Our approach combines the prediction results from the illumination-related information of input images. The illumination-related information is obtained by the proposed classification algorithm. The classification algorithm detects the geometry and shadow of the image at first, and then classifies the pixels of illumination-related cues by the requirement of the prediction algorithm. All of the illumination-related cues are used to predict the possible illumination condition by suitable algorithms, and the the markov random field is used to obtain the most likely illumination condition from all of the possible condition. Results of our approach and the comparison demonstrate the efficiency of our proposed multi-cues based illumination prediction approach.
AB - Illumination condition prediction from given outdoor images is challenging but widely useful. Most of the existing methods predict the illumination based on the inserted markers or the limitation on the environment, which makes them impossible to directly predict the illumination condition from the nature images. We propose a multi-cues based illumination prediction approach that can predict the illumination condition by the input images only. Our approach combines the prediction results from the illumination-related information of input images. The illumination-related information is obtained by the proposed classification algorithm. The classification algorithm detects the geometry and shadow of the image at first, and then classifies the pixels of illumination-related cues by the requirement of the prediction algorithm. All of the illumination-related cues are used to predict the possible illumination condition by suitable algorithms, and the the markov random field is used to obtain the most likely illumination condition from all of the possible condition. Results of our approach and the comparison demonstrate the efficiency of our proposed multi-cues based illumination prediction approach.
KW - Illumination prediction
KW - Illumination-related cues
KW - Image processing
KW - Markov random field
UR - http://www.scopus.com/inward/record.url?scp=85073171686&partnerID=8YFLogxK
U2 - 10.1109/ICICN.2019.8834930
DO - 10.1109/ICICN.2019.8834930
M3 - Conference article published in proceeding or book
AN - SCOPUS:85073171686
T3 - 2019 7th International Conference on Information, Communication and Networks, ICICN 2019
SP - 130
EP - 134
BT - 2019 7th International Conference on Information, Communication and Networks, ICICN 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th International Conference on Information, Communication and Networks, ICICN 2019
Y2 - 23 April 2019 through 26 April 2019
ER -