000176274 001__ 176274
000176274 005__ 20190316235346.0
000176274 037__ $$aCONF
000176274 245__ $$aHow is the Weather: Automatic Inference from Images
000176274 269__ $$a2012
000176274 260__ $$c2012
000176274 336__ $$aConference Papers
000176274 520__ $$aLow-cost monitoring cameras/webcams provide unique visual information. To take advantage of the vast image dataset captured by a typical webcam, we consider the problem of retrieving weather information from a database of still images. The task is to automatically label all images with different weather conditions (e.g., sunny, cloudy, and overcast), using limited human assistance. To address the drawbacks in existing weather prediction algorithms, we first apply image segmentation to the raw images to avoid disturbance of the non-sky region. Then, we propose to use multiple kernel learning to gather and select an optimal subset of image features from a certain feature pool. To further increase the recognition performance, we adopt multi-pass active learning for selecting the training set. The experimental results show that our weather recognition system achieves high performance.
000176274 6531_ $$aNCCR-MICS
000176274 6531_ $$aNCCR-MICS/EMSP
000176274 6531_ $$aweather recognition
000176274 700__ $$0242503$$aChen, Zichong$$g183100
000176274 700__ $$0242497$$aYang, Feng$$g180547
000176274 700__ $$0242496$$aLindner, Albrecht$$g185235
000176274 700__ $$0241123$$aBarrenetxea, Guillermo$$g136301
000176274 700__ $$0240184$$aVetterli, Martin$$g107537
000176274 7112_ $$aIEEE International Conference on Image Processing (ICIP 2012)
000176274 773__ $$tProceedings of IEEE International Conference on Image Processing (ICIP 2012)
000176274 8564_ $$s263333$$uhttps://infoscience.epfl.ch/record/176274/files/06467244.pdf$$yn/a$$zn/a
000176274 909C0 $$0252056$$pLCAV$$xU10434
000176274 909C0 $$0252320$$pIVRL$$xU10429
000176274 909CO $$ooai:infoscience.tind.io:176274$$pconf$$pIC$$qGLOBAL_SET
000176274 917Z8 $$x183100
000176274 917Z8 $$x125681
000176274 917Z8 $$x183100
000176274 917Z8 $$x183100
000176274 917Z8 $$x183100
000176274 917Z8 $$x222073
000176274 937__ $$aEPFL-CONF-176274
000176274 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000176274 980__ $$aCONF