Differences

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

--- en:data [2014/11/11 23:39] – xuphilip
+++ en:data [2016/11/05 04:38] – xuphilip
@@ Line 1: / Line 1: @@
-====== KITTI semantic segmentation ground truth ======
+====== Grand Cooperative Driving Challenge ======
-{{ :en:sample.png?nolink |}}
-{{ :en:classes.png?nolink |}}
+We provide the C++ code as well as the data recorded during our participation in the GCDC 2016.
-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.
+The code has been developped within the [[https://devel.hds.utc.fr/software/pacpus|PACPUS]] open-source framework.
 == Download ==
-^  ^  Training set  ^  Testing set  ^
+^ Component ^  Link  ^
-^ Ground truth | {{:en:gttrain.zip|}} | {{:en:gttest.zip|}} |
+^ Localisation | {{:en:codes:GCDC_localisation.zip|}} |
-^ Left images | {{:en:lefttrain.zip|}} | {{:en:lefttest.zip|}} |
+^ Perception | {{:en:codes:GCDC_perception.zip|}} |
-^ Right images | {{:en:righttrain.zip|}} | {{:en:righttest.zip|}} |
+^ Control | {{:en:codes:GCDC_control.zip|}} |
-^ Velodyne data | {{:en:velotrain.zip|}} | {{:en:velotest.zip|}} |
+^ Communication | {{:en:codes:GCDC_communication.zip|}} |
+^ Supervisor | {{:en:codes:GCDC_supervisor.zip|}} |
-For convenience, we also provide the left and right images, as well as the Velodyne data, associated to the ground truth annotations.
+^ Data ^  Heat 1  ^  Heat 3  ^  Heat 5  ^
-These data were extracted from the raw sequences.
+^ Localization | {{:en:codes:GCDC_data_heat1_localisation.zip|}} | {{:en:codes:GCDC_data_heat3_localisation.zip|}} | {{:en:codes:GCDC_data_heat5_localisation.zip|}} |
-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.
+^ Perception | {{:en:codes:GCDC_data_heat1_perception.zip|}} | {{:en:codes:GCDC_data_heat3_perception.zip|}} | {{:en:codes:GCDC_data_heat5_perception.zip|}} |
+^ Communication | {{:en:codes:GCDC_data_heat1_communication.zip|}} | {{:en:codes:GCDC_data_heat3_communication.zip|}} | {{:en:codes:GCDC_data_heat5_communication.zip|}} |
+====== Evidential Calibration ======
+We provide the MATLAB® code for our evidential multiclass classifier calibration method.
+  * calibTrain.m:  train the calibration model given some validation data
+  * score2prob.m:  transform a vector of scores into probabilities
+  * score2plaus.m: transform a vector of scores into plausibilities over singletons
+== Download ==
+^  ^  Link  ^
+^ Calibration code | {{:en:codes:multinomial_calibration.zip|}} |
 == 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 80: @@
 {{:en:publis:xu14_bmvc_evidential_combination_of_pedestrian_detectors.pdf|paper}}
 {{: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]]

UMR CNRS 7253

Site Tools

Differences

Page Tools

User Tools