Ihsen Alouani - Datasets

Datasets

1. 3MDAD : Multimodal Multiview and Multispectral Driver Action Dataset

A. Description :

This Novel Public Dataset for Multimodal Multiview and Multispectral Driver Distraction Analysis is the result of collaboration between :

- Pr. Mohamed Ali MAHJOUB, Dr. Anouar BEN KHALIFA and Miss Imen JEGHAM from Laboratory of Advanced Technology and Intelligent Systems (LATIS)-National Engineering School of Sousse, Tunisia.

- Pr. Ihsen ALOUANI from the Polytechnic University Hauts-De-France.

The 3MDAD dataset is mainly composed of two real-world driving sets: the first one recorded at daytime and the second one at nighttime. Each set consists of two synchronised data modalities, each from frontal and side views. Two Microsoft Kinect cameras are employed. The first Kinect is mounted on the car handle on the top of the passenger window, and the second is placed on the dashboard in front of the driver.

3MDAD (Day) provides temporally synchronized RGB frames and depth frames. 50 participants (38 males and 12 females) aged between 19 and 41 were asked to drive the vehicle.
3MDAD (Night) provdes temporally synchronized IR frames and depth frames. 19 participants (11 males and 8 females) aged between 19 and 53 were asked to drive the vehicle.
To download this database, please send a request to : ihsen.alouani@uphf.fr :

- [DAY]: Data captured from the side view : Kinect 1 : RGB1 (4.02 Go) Depth1 (3.28 Go)

- [DAY]: Data captured from the front view : Kinect 2 : RGB2 (3.61 Go) Depth2 (2.7 Go)

- [NIGHT]: Data captured from the side view : Kinect 1 : IR1 (8.23 Go) Depth1 (1.45 Go)

- [NIGHT]: Data captured from the front view : Kinect 2 : IR2 (9.77 Go) Depth2 (1.01 Go)

This dataset can be downloaded and used for education and research purposes under the Creative Commons Attribution-NonCommercial-NoDerivatives Licence CC BY-NC-ND . To use this dataset please give credit by citing the following papers:

Imen Jegham, Anouar Ben Khalifa, Ihsen Alouani, Mohamed Ali Mahjoub, A novel public dataset for multimodal multiview and multispectral driver distraction analysis: 3MDAD, Signal Processing: Image Communication, Volume 88, October 2020, 115966, DOI: https://doi.org/10.1016/j.image.2020.115960

Imen Jegham, Anouar Ben Khalifa, Ihsen ALOUANI, Mohamed Ali MAHJOUB, MDAD : A Multimodal and Multiview in-Vehicle Driver Action Dataset, In: Vento M., Percannella G. (eds) Computer Analysis of Images and Patterns. CAIP 2019. Lecture Notes in Computer Science, vol 11679. Springer, Cham, pp. 518-529. DOI: https://doi.org/10.1007/978-3-030-29888-3_42

2. Infrastructure to Vehicle Multi-View Pedestrian Detection dataset (I2V-MVPD)

This database is the result of collaboration between :

- Pr. Mohamed Ali MAHJOUB and Dr. Anouar BEN KHALIFA from Laboratory of Advanced Technology and Intelligent Systems ((LATIS)-National Engineering School of Sousse, Tunisia.

- Pr. Ihsen ALOUANI from the Polytechnic University Hauts-De-France.

It consists of a multi-view database for collaborative advanced perception. The objects are filmed using an in-car embedded camera, as well as an infrastructure fixed camera.

A. Ben Khalifa, I. Alouani, M. A. Mahjoub, A Rivenq, "A novel multi-view pedestrian detection database for collaborative Intelligent Transportation Systems", Future Generation Computer Systems, Volume 113, 2020, Pages 506-527, ISSN 0167-739X, https://doi.org/10.1016/j.future.2020.07.025. (http://www.sciencedirect.com/science/article/pii/S0167739X20300340)

3. OLIMP: A Heterogeneous Multimodal dataset for Advanced Environment Perception

This database is designed in the context of Ms Amira MIMOUNA's PhD works. She is supervised by :

- Pr. Ihsen ALOUANI, Pr Abdelmalik TALEB from the Polytechnic University Hauts-De-France.

- Dr. Anouar BEN KHALIFA and Pr Najoua BEN AMARA from Laboratory of Advanced Technology and Intelligent Systems (LATIS)-National Engineering School of Sousse, Tunisia.

OLIMP is a multimodal dataset for advanced environment perception for Intelligent Transportation Systems. It has been recorded in real-world conditions and the scenes are recorded using 4 modalities:

Camera
Ultra-Wideband Radar
Narrow-band Radar
Acoustic sensor

The figure below shows some samples of the dataset.

To download this database, please send a request to : ihsen.alouani@uphf.fr

- Data samples for Class 0 (Background) : C_0 (0.5 Go)

- Data samples for Class 1 (Pedestrian) : C_1 (4.4 Go)

- Data samples for Class 2 (Cyclist) : C_2 (0.99 Go)

- Data samples for Class 3 (Vehicle) : C_3 (1.82 Go)

- Data samples for Class 4 (Tramway) : C_4 ( 0.64 Go)

- Data samples for Class 5 (Several combinations of classes) : C_5 (7.58 Go)

Link to the paper: OLIMP

@Article{electronics9040560,

AUTHOR = {Mimouna, Amira and Alouani, Ihsen and Ben Khalifa, Anouar and El Hillali, Yassin and Taleb-Ahmed, Abdelmalik and Menhaj, Atika and Ouahabi, Abdeldjalil and Ben Amara, Najoua Essoukri},

TITLE = {OLIMP: A Heterogeneous Multimodal Dataset for Advanced Environment Perception},

JOURNAL = {Electronics},

VOLUME = {9},

YEAR = {2020},

NUMBER = {4},

ARTICLE-NUMBER = {560},

URL = {https://www.mdpi.com/2079-9292/9/4/560},

ISSN = {2079-9292},

DOI = {10.3390/electronics9040560}

}