The three academic partners have focused their research works on sets of methods for the perception of driving scenes (project action 1) and higher-level data analysis (action 2). Furthermore, partners acquired datasets on their instrumented vehicles (action 3), on both Chinese and French roads, and performed evaluations on these real data. We list hereafter the research works, and results obtained in the three actions, conducted with the help of undergraduate, Master and PhD students. Some of these projects have given rise to direct collaborations between French and Chinese partners, with mobility of researchers and students between the three involved laboratories.

In this section, references [0a - 0b], [1a, 2a] and [1] to [14] are co-publications resulting from a joint research between French and Chinese partners.

Projects conducted in Beijing, KLMP (PKU) partner, with the name of the principal student.

Action 1: Methods.
- Monocular Pedestrian Tracking from a Moving Vehicle, Fan Zipei [10];
- Visual-based localization using road structural features, Yu Yufeng [2];
- Pairwise LIDAR Calibration Using Multi-Type 3D Geometric Features in Natural Scene, He Mengwen [7];
- Omni-directional detection and tracking of on-road vehicles using multiple horizontal laser scanners, Wang Chao [13];
- A System of Automated Training Sample Generation for Visual-based Car Detection, Wang Chao [11].

Action 2: Methods.
- Lane change trajectory prediction for risk assessment through learning from human driving data, Yao Wen [8, 12];
- Computing Object-based Saliency in Urban Scenes Using Laser Sensing, Zhao Yipu [14];
- Visual-based human behavior analysis, focus of attention, intention prediction, Huang Yingning [3, 4];
- Pedestrian trajectory analysis from monocular video, Zhang Junhua.

Action 3: Experiments conducted by groups of people.
- Acquisitions in the intersection close to the west gate of Peking University campus;
- Acquisitions in Beijing ring roads with a host vehicle for driving behavior analysis;
- Acquisitions in Beijing ring roads/downtown streets with a host vehicle and a tracked one for SLAM, car detection and tracking;
- Acquisitions in Beijing ring roads/downtown streets with a host vehicle for multi-LIDAR calibration, 3D data analysis and object discovery;
- Video acquisition in Beijing intersection/downtown streets for visual-based moving object detection and tracking, ego-motion estimation.

Projects conducted in Heudiasyc, Compiègne:

Task 1:
- Local dynamic mapping with evidential grids, Julien Moras [48, 49];
- Fast road detection from color images, Bihao Wang [40];
- Vision-based road detection using contextual blocks, Teodoro Mendes [22];
- Local information fusion for scene understanding, Philippe Xu [2a, 37, 52];
- Multiple obstacle detection and tracking using stereo vision, Bihao Wang [32];
- Map-aided fusion using evidential grids for mobile perception in urban environment, Marek Kurdej [15, 17, 41, 42, 44, 47];
- On Modeling Ego-motion Uncertainty for Moving Object Detection from a Mobile Platform, Zhou Dingfu [35];
- Velodyne data for positioning in a map, Tarcisio Mendes [61];
- Evidential Combination of Pedestrian Detectors [23];
- Multi-modal object detection and localization for high integrity driving assistance, S. Rodriguez [19];
- Object tracking and behavior prediction for driving assistance in urban areas, LI Hui;
- Multi-Modal Object Detection and Localization for High Integrity Driving Assistance [18];

Task 2:
- Multiple tracks fusion for local dynamic maps, Adam Houenou [6, 46];
- An evidential sensor model for Velodyne scan grids [27, 47];
- An evidential occupancy grid mapping with stereo-vision [15];
- Evidential grids information management in dynamic environments, Adam Houenou [26];
- Vehicle trajectory prediction based on motion model and maneuver recognition, Adam Houenou [64];
- Belief-based driving scene understanding starting from a prior segmentation, Jean- Baptiste Bordes [5, 38];
- Evidential calibration of classifiers, Philippe Xu [2a, 21, 1b];
- Soft Label Based Semi-Supervised Boosting for Classification and Object Recognition, Zhou Dingfu [30].

Task 3:
- Validation of perception algorithms. 200 meters and the scenario has been repeated 3 times, in Compiègne. During one run 2 pedestrians cross the road in front of the vehicle;
- Positioning improvement using Velodyne LIDAR data, imprecise GPS pose and OpenStreetMap data, in Compiègne.
- Creation of a dataset for intelligent vehicles. Evaluation of an infrared camera (Pearleye LWIR from Allied Vision Technologie) coupled with a ToF camera (Time-of-Flight from PMD). M. Nour [57].

Projects conducted in Grenoble

In Grenoble, e-motion (Inria) was mainly involved in Task 2, sub-task 2.3 on Traffic situation awareness with uncertainty, scene semantics and information fusion. The partner has developed specific methods for lane change prediction on highways, including:
- A visual lane tracker, based on a particle filter methodology, implemented on GPU and tested on an instrumented vehicle;
- An algorithm for predicting the driver’s intention to change lane on Highway, using a multi- class SVM for classifying maneuvers [36]. A Bayesien strategy is used to filter the classification output and to provide a smooth prediction of the maneuver. The method has been further used in PRETIV for risk estimation and for dynamic free space characterization.
Additionally, E-Motion had built a benchmark composed of an evaluation methodology, a simulated experimental platform based on the Torcs simulator and real data gathered with their instrumented vehicle. The first prototype of this benchmark has been developed together with a student of Peking University (Yufeng Yu) [33]. A survey of Motion Prediction and Risk Assessment has been published in [19], and recent methods presented in [34, 35].

Task 3, involving both Chinese and French partners** (with PKU students in Compiègne):

- Acquisitions on the A1 highway between Compiègne and Paris, and on the ring road (boulevard périphérique) of Paris;
- Experiment Design for Collecting Acceleration Data from Different Drivers, in Compiègne (Fig. 1);
- Visual Odometry assisted Vehicle localization in structured-road environment in Compiègne;
- Velodyn-based 3D SLAM within Compiègne.

Direct relations with the industry:

PSA Peugeot Citroen, DRIA-Vélizy and the China Tech. Center in Shanghai. PSA had the role of Advisory board of the Pretiv project. PSA expert scientists follow the research, via regular video Skype-based meetings with PKU, give advises and recommendations. Several other meetings have been organized with PSA experts in Paris with Heudiasyc and PKU colleagues, involving researchers and students. Furthermore, Stéphane Géromini, PSA expert, has been the co- director of the (Cifre-) PhD thesis of Adam Houenou with Véronique Cherfaoui from Heudiasyc. A collaborative research conducted by Adam Houenou, and Yao Wen (PKU) during his stay in Compiègne, has given rise to joint publications [6, 8].
Besides the PRETIV project, discussions are on-going about more direct collaborations between PSA, PKU, and Heudiasyc, through a Partenariat stratégique de recherche.

Other partnerships:

During the life of PRETIV, the partners have been involved in Predimap - ICT-Asia research network on Vehicle Perception and Reasoning Enhanced with Digital Maps, funded by CNRS and the French Ministry of Foreign and European Affairs [2012 - 2013]. This network gathered seven partners: University of Tokyo, Shanghai Jiao Tong University, Geoinformatics Center of Asian Institute of Technology, Peking university, Heudiasyc laboratory (CNRS coordinator), the French national mapping agency (IGN) and Inria. This collaboration, particularly with IGN, helped the PRETIV partners to make intelligent use of digital maps for some problems of localization. Future researches in collaboration with IGN should be promoted.

Heudiasyc open-source codes and datasets on: https://www.hds.utc.fr/~xuphilip/dokuwiki/en/data

• Evidential Multiclass Classifier Calibration: we provide the MATLAB® code for our evidential multiclass classifier calibration method [21].
• Pedestrian detection: we provide the MATLAB® code for our evidential combination of pedestrian detectors [23].
• A set of 107 images (70 for training and 37 for testing) from the KITTI Vision Benchmark Suite has been fully manually annotated with the software Adobe® Photoshop® CS2 [2, 37]: joint work between Heudiasyc and PKU partners. The left color images of the stereo-pair were annotated at the pixel level considering a set of 28 classes. For convenience, we also provide the left and right images, as well as the Velodyne’s 3D LiDAR data, associated to the ground truth annotations. These data were extracted from the raw sequences. The dataset is used in [38], and available on http://www.cvlibs.net/datasets/kitti/eval_semantics.php

PKU datasets and video collections on: http://www.poss.pku.edu.cn/download.html

• A Trajectory Set on the Beijing Ring Roads: A video of on-road vehicle trajectory collection and a video of trajectory-based lane change analysis. Driving during 97 minutes on the 4th Ring Road of Beijing: 69,2 kilometers. These trajectory data have been used in references [8, 12, 13]: joint work between PKU and Heudiasyc partners;
• Two on-road vehicle visual datasets, described and used in [54] and in [53];

List of the multi-partner publications (resulting from jointly conducted Sino-French work).

0a. Zhao,H., Wang,C., Lin,Y., Guillemard,F., Geronimi,S., Aioun,F., On-road Vehicle Trajectory Collection and Scene-based Lane Change Analysis: Part I, IEEE Trans on Intelligent Transportation Systems, 2016.
0b. Yao,W., Zeng,Q., Lin,Y., Xu,D., Zhao,H., Wang,C., Lin,Y., Guillemard,F., Geronimi,S., Aioun,F., On-road Vehicle Trajectory Collection and Scene-based Lane Change Analysis: Part II, IEEE Trans on Intelligent Transportation Systems, 2016.
0c. Wang,C., Fang,Y., Zhao,H., Guo,C., Mita,S., Zha,H., Probabilistic Inference for Occluded and Multiview On-road Vehicle Detection, IEEE Trans. on Intelligent Transportation Systems, 17(1), 215–229, 2016.
1a. Philippe Xu, Franck Davoine, Hongbin Zha and Thierry Denœux. Evidential calibration of binary SVM classifiers. International Journal of Approximate Reasoning (IJAR), 2015.
2a. Philippe Xu, Franck Davoine, Jean-Baptiste Bordes, Huijing Zhao, Thierry Denœux, Multimodal Information Fusion for Urban Scene Understanding, Machine Vision and Applications, 2015

1. Yingning Huang, Dingrui Duan, Jinshi Cui, Franck Davoine, Li Wang, Hongbin Zha. Joint estimation of head pose and visual focus of attention. IEEE ICIP - International Conference on Image Processing, Paris, Oct. 27-30, 2014.
2. Yufeng Yu, Huijing Zhao, Franck Davoine, Jinshi Cui, Hongbin Zha, Monocular Visual Localization Using Road Structural Features. IEEE IV - Intelligent Vehicles Symposium, June 8-11, Dearborn, Michigan, USA, 2014.
3. Yingning Huang, Dingrui Duan, Jinshi Cui, Franck Davoine, Li Wang, Hongbin Zha: Joint estimation of head pose and visual focus of attention. IEEE Intl. Conference ICIP, 2014.
4. Yingning Huang, Jinshi Cui, Franck Davoine, Huijing Zhao, Hongbin Zha. Head Pose Based Intention Prediction Using Discrete Dynamic Bayesian Network. In the seventh ACM/IEEE ICDSC - International Conference on Distributed Smart Cameras. California, USA, Oct. 29 – Nov. 1, 2013.
5. Jean-Baptiste Bordes, Philippe Xu, Franck Davoine, Huijing Zhao, Thierry Denœux, Information Fusion and Evidential Grammars for Object Class Segmentation, IEEE/RSJ IROS PPNIV - 5th Workshop on Planning, Perception and Navigation for Intelligent Vehicles, Nov. 3rd, Tokyo, 2013.
6. Adam Houenou, Philippe Bonnifait, Véronique Cherfaoui, Wen Yao. Vehicle Trajectory Prediction based on Motion Model and Maneuver Recognition. In IEEE/RSJ IROS - International Conference on Intelligent Robots and Systems, Tokyo, Nov. 2013.
7. Mengwen He, Huijing Zhao, Franck Davoine, Jinshi Cui, Hongbin Zha. Pairwise LIDAR Calibration Using Multi-Type 3D Geometric Features in Natural Scene. In IEEE/RSJ IROS - International Conference on Intelligent Robots and Systems, Tokyo, November 2013.
8. Yao Wen, Huijing Zhao, Philippe Bonnifait, Hongbin Zha, Lane Change Trajectory Prediction by Using Recorded Human Driving Data, Proc. of IV - IEEE Intelligent Vehicles Symposium, Gold Coast, Australia, 23-26 June, 2013.
9. Philippe Xu, Franck Davoine, Jean-Baptiste Bordes, Huijing Zhao, and Thierry Denoeux. Information fusion on over-segmented images:an application for rban scene understanding. Proc. of MVA intl. Conference, Kyoto, Japan, May 2013.
10. Zipei Fan, Zeliang Wang, Jinshi Cui, Franck Davoine, Huijing Zhao, and Hongbin Zha. Monocular pedestrian tracking from a moving vehicle. In ACCV Workshop on Detection and Tracking in Challenging Environments, Daejeon, Korea, November 2012.
11. Chao Wang, Huijing Zhao, Franck Davoine, and Hongbin Zha. A system of automated training sample generation for visual-based car detection. In IEEE/RSJ IROS - International Conference on Intelligent Robots and Systems, Vilamoura, Algarve, Portugal, October 7-12, 2012.
12. Wen Yao, Huijing Zhao, and Franck Davoine. Learning lane change trajectories from on-road driving data. In IEEE IV - Intelligent Vehicles Symposium, Alcalaa de Henares, Spain, June 3-7, 2012.
13. Huijing Zhao, Chao Wang, Yao Wen, Franck Davoine, Jinshi Cui and Hongbin Zha. Omni- directional detection and tracking of on-road vehicles using multiple horizontal laser scanners. In IEEE IV - Intelligent Vehicles Symposium, Alcalaa de Henares, Spain, June 3-7, 2012.
14. Yipu Zhao, Mengwen He, Huijing Zhao, Franck Davoine, and Hongbin Zha. Computing object- based saliency in urban scenes using laser sensing. In IEEE ICRA - International Conference on Robotics and Automation, St. Paul, Minnesota, USA, May 14-18, 2012.

List of single-partner publications (involving a single French partner):

15. Marek Kurdej, Julien Moras, Philippe Bonnifait, Véronique Cherfaoui. Map-Aided Evidential Grids for Driving Scene Understanding IEEE Intelligent Transportation Systems Magazine, 2015, pp.30-41.
16. Thierry Denoeux, Nicole El Zoghby, Véronique Cherfaoui, Antoine Jouglet. Optimal object association in the Dempster-Shafer framework. IEEE Transactions on Cybernetics, IEEE, 2014, 44 (22), pp.2521- 2531.
17. Marek Kurdej, Julien Moras, Véronique Cherfaoui, Philippe Bonnifait. Controlling Remanence in Evidential Grids Using Geodata for Dynamic Scene Perception International Journal of Approximate Reasoning, Elsevier, 2014, 55 (1), pp.355-375.
18. Sergio Alberto Rodriguez Florez, Vincent Fremont, Philippe Bonnifait, Véronique Cherfaoui. Multi- modal object detection and localization for high integrity driving assistance. Machine Vision and Applications, Springer Verlag, 2014, 1, pp.1-18.
19. Stéphanie Lefevre, Dizan Vasquez, Christian Laugier. A Survey on Motion Prediction and Risk Assessment for Intelligent vehicles. Robomech Journal, Springer, 2014.
20. Chunlei Yu, Cherfaoui, V., Bonnifait, P. Evidential occupancy grid mapping with stereo-vision. Intelligent Vehicles Symposium (IV), 2015, IEEE, pp 712 – 717.
21. 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 (FUSION), pages 1106-1112, Washington, D.C., July 6-9, 2015
22. Teodoro Mendes, C.C. and Fremont, V. and Wolf, D. F., Vision-Based Road Detection using Contextual Blocks, 7th Workshop on Planning, Perception and Navigation for Intelligent Vehicles, in conjunction with IEEE IROS, Hamburg, Germany, September 28, 2015
23. Ph. Xu, F. Davoine and T. Denoeux. Evidential Combination of Pedestrian Detectors. In Proceedings of the 25th British Machine Vision Conference (BMVC), Nottingham, UK, September 1-5, 2014.
24. Ph. Xu, F. Davoine and T. Denœux.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 (BELIEF), Springer, LNCS 8764, pages 49-57, Oxford, UK, September 26-28, 2014. (Best student paper award)
25. Marek Kurdej, Julien Moras, Véronique Cherfaoui, Philippe Bonnifait. Controlling Remanence in Evidential Grids Using Geodata for Dynamic Scene Perception International Journal of Approximate Reasoning, Elsevier, 2014, 55 (1), pp.355-375
26. Adam Houenou, Philippe Bonnifait, Véronique Cherfaoui. Risk Assessment for Collision Avoidance Systems International Conference on Intelligent Transportation Systems, Oct 2014, Qingdao, China. pp.386-391, 2014
27. Julien Moras, Véronique Cherfaoui, Philippe Bonnifait. Evidential Grids Information Management in Dynamic Environments. 17th International Conference on Information Fusion, Salamanca, Spain. pp.65, 2014
28. Chunlei Yu, Véronique Cherfaoui, Philippe Bonnifait. An Evidential Sensor Model for Velodyne Scan Grids 13th International Conference on Control, Automation, Robotics and Vision, December 2014, Singapore.
29. Wang, B. and Rodriguez Florez, S. A. and Fremont, V., Multiple Obstacle Detection and Tracking using Stereo Vision: Application and Analysis, 13th International Conference on Control, Automation, Robotics & Vision (ICARCV), Singapore, December 10-12, 2014
30. Zhou, D. and Quost, B. and Fremont, V., Soft Label Based Semi-Supervised Boosting for Classification and Object Recognition, 13th International Conference on Control, Automation, Robotics & Vision (ICARCV), Singapore, December 10-12, 2014
31. Wang, B. and Fremont, V. and Rodriguez Florez, S. A., Color-based Road Detection and its Evaluation on the KITTI Road Benchmark, IEEE Intelligent Vehicles Symposium 2014 (IV 2014), Workshop on Benchmarking Road Terrain and Lane Detection Algorithms for In-Vehicle Application, June 8-11, Dearborn, Michigan, USA, 2014.
32. Zhou, D. and Fremont, V. and Quost, B. and Wang, B., On Modeling Ego-motion Uncertainty for Moving Object Detection from a Mobile Platform, IEEE Intelligent Vehicles Symposium 2014 (IV 2014), June 8-11, Dearborn, Michigan, USA, 2014.
33. Dizan Vasquez, Yufeng Yu, Suryansh Kumar, Christian Laugier. An open framework for human-like autonomous driving using Inverse Reinforcement Learning. IEEE Vehicle Power and Propulsion Conference. 2014.
34. Christian Laugier. Technologies for next cars generation. Session on “Future Key Advances on Autonomous Systems / Robots”, IEEE ICARCV, Singapore, 2014.
35. Christian Laugier. Risk Assessment & Decision-making for safe Vehicle Navigation under Uncertainty. IET Workshop “Autonomous Vehicles: From Theory to full scale applications”, Paris, June 2015.
36. P. Kumar, Mathias Perrollaz, Stéphanie Lefèvre, and Christian Laugier: Learning-Based Approach for Online Lane Change Intention Prediction, in IEEE International Symposium on Intelligent Vehicles, 2013.
37. Ph. Xu, F. Davoine, J.-B. Bordes, H. Zhao and T. Denoeux. Information Fusion on Oversegmented Images: An Application for Urban Scene Understanding. InProceedings of the Thirteenth IAPR International Conference on Machine Vision Applications (MVA), pages 189-193, Kyoto, Japan, May 20-23, 2013.
38. Jean-Baptiste Bordes, Franck Davoine, Philippe Xu, Thierry Denoeux, Evidential Grammars for Image Interpretation. Application to multimodal traffic scene understanding, IUKM - Third International Symposium on Integrated Uncertainty in Knowledge Modeling and Decision Making, Springer-Verlag LNCS, Beijing, China, July 12-14, 2013.
39. J.-B. Bordes,Ph. Xu, F. Davoine, H. Zhao and T. Denœux. Information Fusion and Evidential Grammars for Object Class Segmentation. In Proceedings of the Fifth IROS Workshop on Planning, Perception and Navigation for Intelligent Vehicles (PPNIV), pages 165-170, Tokyo, Japan, November 03, 2013.
40. Bihao Wang and Vincent Frémont. Fast road detection from color images. IEEE Intelligent Vehicles Symposium (IV) June 23-26, 2013, Gold Coast, Australia.
41. Marek Kurdej, Julien Moras, Véronique Cherfaoui and Philippe Bonnifait, Controlling Remanence in Evidential Grids Using Geodata for Dynamic Scene Perception, International Journal of Approximate Reasoning, March 2013.
42. Marek Kurdej, Véronique Cherfaoui. Conservative, Proportional and Optimistic Contextual Discounting in the Belief Functions Theory, 16th International Conference on Information Fusion, July 2013.
43. Thierry Denoeux. Maximum likelihood estimation from Uncertain Data in the Belief Function Framework. IEEE Transactions on Knowledge and Data Engineering, 25(1), pp. 119-130, 2013.
44. Marek Kurdej, Julien Moras, Véronique Cherfaoui, Philippe Bonnifait. Controlling Remanence in Evidential Grids Using Geodata for Dynamic Scene Perception. International Journal of Approximate Reasoning, Available online on 31 March 2013.
45. Sergio A. Rodriguez Florez, Vincent Fremont, Philippe Bonnifait, and Véronique Cherfaoui. An embedded multimodal system for object localization and tracking. IEEE Intelligent Transportation Systems Magazine, 4(4), 2012.
46. Adam Houenou, Philippe Bonnifait, Véronique Cherfaoui, and Jean-François Boissou. A track- to-track association method for automotive perception systems. In IEEE IV - Intelligent Vehicles Symposium, Alcalaa de Henares, Spain, June 3-7 2012.
47. Marek Kurdej, Julien Moras, Véronique Cherfaoui, and Philippe Bonnifait. Map-aided fusion using evidential grids for mobile perception in urban environment. In Springer, editor, International Conference on Belief Functions, vol. 164 in Advances in Intelligent and Soft Computing, pages 343– 350, 2012.
48. Julien Moras, Véronique Cherfaoui, and Philippe Bonnifait. Moving objects detection by conflict analysis in evidential grids. In IEEE IV - Intelligent Vehicles Symposium, Alcalaa de Henares, Spain, June 3-7 2012.
49. Julien Moras, Sergio A. Rodriguez Florez, Vincent Drevelle, Gérald Dherbomez, Véronique Cherfaoui, and Philippe Bonnifait. Drivable space characterization using automotive lidar and georeferenced map information. In IEEE IV - Intelligent Vehicles Symposium, Alcalaa de Henares, Spain, June 3-7 2012.
50. Chunlei Yu, Philippe Bonnifait, Véronique Cherfaoui. An Evidential Scheme for a Velodyne Ground Truth Perception for the Intelligent Vehicles, Dix-neuvième congrès national sur la Reconnaissance de Formes et l’Intelligence Artificielle (RFIA), Rouen, France, Juin 2014.
51. Ph. Xu, F. Davoine and T. Denœux. Transformation de scores SVM en fonctions de croyance. Dix- neuvième congrès national sur la Reconnaissance de Formes et l’Intelligence Artificielle (RFIA), Rouen, France, Juin 2014.
52. Philippe Xu, Franck Davoine, Thierry Denoeux and Jean-Baptiste Bordes. Fusion dʼinformations sur des images sur-segmentées: une application à la compréhension de scènes routières. Proc. of ORASIS, Abbaye de Cluny, France, 2013.

1b. Ph. Xu, F. Davoine, J.-B. Bordes and T. Denœux. Fusion d’informations pour la compréhension de scènes. Traitement du signal (TS), Vol. 31, Number 1-2, pages 57-80, June 2014.

List of single-partner publications (involving only the Chinese partner):

53. Chao Wang, Huijing Zhao, Chunzhao Guo, Seiichi Mita, Hongbin Zha: Visual-based on-road vehicle detection: A transnational experiment and comparison. Intelligent Vehicles Symposium 2015: 455-462
54. Chao Wang, Huijing Zhao, Chunzhao Guo, Seiichi Mita, Hongbin Zha: On-road vehicle detection through part model learning and probabilistic inference. IROS 2014: 4965-4972 55. Mengwen He, Huijing Zhao, Jinshi Cui, Hongbin Zha: Calibration method for multiple 2D LIDARs system. ICRA 2014: 3034-3041
56. Jinshi Cui, Ye Liu, Yandong Xu, Huijing Zhao, and Hongbin Zha. Tracking generic human tracking generic human motion via fusion of low- and high-dimensional approaches. In IEEE Transactions on Systems, Man and Cybernetics, Part A., 43(4), 2013.
57. Ye Liu, Jinshi Cui, Huijing Zhao, and Hongbin Zha. Fusion of low-and high-dimensional approaches by trackers sampling for generic human motion tracking. In IAPR ICPR - International Conference on Pattern Recognition, Tsukuba Science City, Japan, November 11-15, 2012.

List of internship reports, PhD theses, postdoc report (involving only a French partner):

58. Xuhong Li. Détection des marquages au sol et alignement sur une carte. Projet de fin d’études de l’Ecole Centrale de Pékin. Heudiasyc Lab. Compiègne, France, June-November 2015.
59. Abdelkamel Tighidet. Intégration des marquages au sol dans une grille évidentielle pour les véhicules autonomes. Supervisors. Master project report, Université de Technologie de Compiègne, France, 2014.
60. Nour Mohamad. Creation of a dataset for intelligent vehicles, Final Year Project – Lebanon University, Heudiasyc Lab. Compiègne. 2014.
61. Tarcisio Mendes De Farias, : Velodyne’s 3D LiDAR data for vehicle positioning in a digital map. Final Year Project, Heudiasyc Lab. Compiègne. 2013.
62. Marek Kurdej. Exploitation of map data for the perception of intelligent vehicules. PhD thesis, Université de Technologie de Compiègne, France, 2015
63. Philippe Xu. Information fusion for scene understanding. PhD thesis, Université de Technologie de Compiègne, France, 2014.
64. Adam Houenou. Calcul de trajectoires pour la préconisation de manœuvres automobiles sur la base d’une perception multi-capteur - Application à l’évitement de collision. PhD thesis co-directed with PSA Peugeot Citroen, Université de Technologie de Compiègne, France, 2013
65. Giovani Bernardes Vitor, Multimodal Perception System’s data acquisition for transnational usage. Post-Doc PRETIV, final report. Heudiasyc Lab. Compiegne, France. August 6th, 2015. 23 pages.

List of internship reports (resulting from jointly conducted work between French and Chinese supervisers, in Beijing):

66. Jiaqian Yu. Automatic Understanding of Road Scenes with Management of Uncertainty. Projet de fin d’études, Ecole Centrale de Pékin. Work done in Peking University, supervised by F. Davoine, H. Zha, J.-B. Bordes, June-December 2013.
67. Martin Gaussier. Internship ENSEIRB-MATMECA / Exeter University, UK. Work done in Peking University, supervised by F. Davoine, H. Zha, Ph. Xu, May-August 2013.
68. Gautier Marti. A modelisation scheme of uncertainty and its application in motion detection. Intership report, Magistere Informatique et Télécommunications, ENS Cachan, 2013. Work done in Peking University, supervised by F. Davoine, H. Zha, Ph. Xu, May-August 2013.
69. Meixi Wang. Transforming pedestrian detection SVM scores into likelihood measures. Masterʼs project (Master 1), Ecole Polytechnique, Paris. Work done in Peking University, supervised by F. Davoine and H. Zhao, April-August 2012.