UMR CNRS 7253

Site Tools

en:data

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
en:data [2014/11/11 23:39] – xuphilipen:data [2016/11/08 12:01] (current) – xuphilip
Line 1: Line 1:
-====== KITTI semantic segmentation ground truth ====== +====== Evidential Calibration ====== 
-{{ :en:sample.png?nolink |}} + 
-{{ :en:classes.png?nolink |}} +We provide the MATLAB® code for our evidential multiclass classifier calibration method. 
-A set of 107 images (70 for training and 37 for testing) from the [[http://www.cvlibs.net/datasets/kitti/index.php|KITTI Vision Benchmark Suite]] were manually annotated with the software Adobe® Photoshop® CS2. +  * calibTrain.m:  train the calibration model given some validation data 
-The left color images were annotated at the pixel level considering a set of 28 classes.+  * score2prob.m:  transform a vector of scores into probabilities 
 +  * score2plaus.m: transform a vector of scores into plausibilities over singletons
  
 == Download == == Download ==
-^  ^  Training set  ^  Testing set  ^ +^  ^  Link  ^ 
-^ Ground truth | {{:en:gttrain.zip|}} | {{:en:gttest.zip|}} | +^ Calibration code | {{:en:codes:multinomial_calibration.zip|}} |
-^ Left images | {{:en:lefttrain.zip|}} | {{:en:lefttest.zip|}} | +
-^ Right images | {{:en:righttrain.zip|}} | {{:en:righttest.zip|}} | +
-^ Velodyne data | {{:en:velotrain.zip|}} | {{:en:velotest.zip|}} | +
- +
-For convenience, we also provide the left and right images, as well as the Velodyne data, associated to the ground truth annotations. +
-These data were extracted from the raw sequences. +
-They are copyright by the [[http://www.cvlibs.net/datasets/kitti/index.php|KITTI Vision Benchmark Suite]] and published under the [[http://creativecommons.org/licenses/by-nc-sa/3.0/|Creative Commons Attribution-NonCommercial-ShareAlike 3.0]] License.+
  
 == References == == References ==
-Ph. Xu, F. Davoine, J.-B. Bordes, H. Zhao and T. Denoeux. 
-**Multimodal Information Fusion for Urban Scene Understanding**. 
-//Machine Vision and Applications (MVA)//, 2014. [accepted for publication] 
  
-Ph. Xu, F. Davoine, J.-B. Bordes, H. Zhao and T. Denoeux. +**__Ph. Xu__**, F. Davoine, H. Zha and T. Denœux. 
-**Information Fusion on Oversegmented Images: An Application for Urban Scene Understanding**. +**Evidential calibration of binary SVM classifiers**. 
-In //Proceedings of the Thirteenth IAPR International Conference on Machine Vision Applications (MVA)//, pages 189-193, Kyoto, Japan, May 20-23, 2013. +//International Journal of Approximate Reasoning (IJAR)//, Vol. 72, pages 55--70, May 2016.\\ 
-{{en/publi/xu13_mva_information_fusion_on_oversegmentated_images_an_application_for_urban_scene_understanding.pdf|paper}}{{en/publi/xu13_mva_presentation.pdf|oral}} +{{:en:publis:xu14_ijar_evidential_calibration_of_binary_svm_classifiers.pdf|Paper}} 
-[[http://hal.archives-ouvertes.fr/hal-00932896|HAL]]+[[https://hal.archives-ouvertes.fr/hal-01154794|HAL]] 
 +[[https://dx.doi.org/10.1016/j.ijar.2015.05.002|DOI]]
  
-----+**__Ph. Xu__**, F. Davoine and T. Denœux. 
 +**Evidential Multinomial Logistic Regression for Multiclass Classifier Calibration**. 
 +In //Proceedings of the 18th International Conference on Information Fusion//, pages 1106-1112, Washington, D.C., July 6-9, 2015.\\ 
 +{{:en:publis:xu15_fusion_evidential_multimodal_logistic_regression_for_multiclass_classifier_calibration.pdf|Paper}}
  
-====== KITTI moving object segmentation ground truth ====== +**__Ph. Xu__**, F. Davoine and T. Denœux. 
-Coming soon...+**Evidential Logistic Regression for Binary SVM Classifier Calibration**. 
 +In F. Cuzzolin, editor, //Belief Functions: Theory and Applications//. 
 +//Proceedings of the 3rd International Conference on Belief Functions//, Springer, LNCS 8764, pages 49-57, Oxford, UK, September 26-28, 2014.\\ 
 +{{:en:publis:xu14_belief_evidential_logistic_regression_for_binary_svm_classifier_calibration.pdf|Paper}} 
 +{{:en:publis:xu14_belief_presentation.pdf|Oral}} 
 +[[https://dx.doi.org/10.1007/978-3-319-11191-9_6|DOI]] 
 +{{:en:publi:xu14_belief.bib|BibTeX}}
  
 ---- ----
Line 60: Line 61:
 {{:en:publis:xu14_bmvc_evidential_combination_of_pedestrian_detectors.pdf|paper}} {{:en:publis:xu14_bmvc_evidential_combination_of_pedestrian_detectors.pdf|paper}}
 {{:en:publis:xu14_bmvc_presentation.pdf|oral}} {{:en:publis:xu14_bmvc_presentation.pdf|oral}}
 +
 +----
 +
 +====== KITTI semantic segmentation ======
 +{{ :en:sample.png?nolink |}}
 +{{ :en:classes.png?nolink |}}
 +A set of 107 images (70 for training and 37 for testing) from the [[http://www.cvlibs.net/datasets/kitti/index.php|KITTI Vision Benchmark Suite]] were manually annotated with the software Adobe® Photoshop® CS2.
 +The left color images were annotated at the pixel level considering a set of 28 classes.
 +
 +== Download ==
 +^  ^  Training set  ^  Testing set  ^
 +^ Ground truth | {{:en:gttrain.zip|}} | {{:en:gttest.zip|}} |
 +^ Left images | {{:en:lefttrain.zip|}} | {{:en:lefttest.zip|}} |
 +^ Right images | {{:en:righttrain.zip|}} | {{:en:righttest.zip|}} |
 +^ Velodyne data | {{:en:velotrain.zip|}} | {{:en:velotest.zip|}} |
 +
 +For convenience, we also provide the left and right images, as well as the Velodyne data, associated to the ground truth annotations.
 +These data were extracted from the raw sequences.
 +They are copyright by the [[http://www.cvlibs.net/datasets/kitti/index.php|KITTI Vision Benchmark Suite]] and published under the [[http://creativecommons.org/licenses/by-nc-sa/3.0/|Creative Commons Attribution-NonCommercial-ShareAlike 3.0]] License.
 +
 +== References ==
 +**__Ph. Xu__**, F. Davoine, J.-B. Bordes, H. Zhao and T. Denœux.
 +**Multimodal Information Fusion for Urban Scene Understanding**.
 +//Machine Vision and Applications (MVA)//, Vol. 27, Issue 3, pages 331--349, April 2016.\\
 +[[https://hal.archives-ouvertes.fr/hal-01133430|HAL]]
 +[[https://dx.doi.org/10.1007/s00138-014-0649-7|DOI]]
 +
 +**__Ph. Xu__**, F. Davoine, J.-B. Bordes, H. Zhao and T. Denoeux.
 +**Information Fusion on Oversegmented Images: An Application for Urban Scene Understanding**.
 +In //Proceedings of the Thirteenth IAPR International Conference on Machine Vision Applications (MVA)//, pages 189-193, Kyoto, Japan, May 20-23, 2013.
 +{{en/publi/xu13_mva_information_fusion_on_oversegmentated_images_an_application_for_urban_scene_understanding.pdf|paper}}{{en/publi/xu13_mva_presentation.pdf|oral}}
 +[[http://hal.archives-ouvertes.fr/hal-00932896|HAL]]
 +

Page Tools

User Tools

en/data.txt · Last modified: 2016/11/08 12:01 by xuphilip
Mentions légales