Đồ án tốt nghiệp - Development of a multimodal 3D object recognition and visualization system FTEUCF

MINISTRY OF EDUCATION AND TRAINING
HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION

GRADUATION THESIS
MAJOR: AUTOMOTIVE ENGINEERING

DEVELOPMENT OF A MULTIMODAL 3D
OBJECT RECOGNITION AND VISUALIZATION
SYSTEM FOR TRAFFIC ENVIRONMENTS USING
CAMERA-LIDAR FUSION
INSTRUCTOR: TRAN VU HOANG
STUDENT:

LE HOANG TIEN
LE HO MINH KHOA

Ho Chi Minh city, May 2025

HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION
FACULTY OF INTERNATIONAL EDUCATION

GRADUATION PROJECT

DEVELOPMENT OF A MULTIMODAL 3D
OBJECT RECOGNITION AND VISUALIZATION
SYSTEM FOR TRAFFIC ENVIRONMENTS USING
CAMERA-LIDAR FUSION
LÊ HOÀNG TIẾN
Student ID: 21145617
LÊ HỒ MINH KHOA
Student ID: 21145019
Major: AUTOMOTIVE ENGINEERING
Supervisor: TRẦN VŨ HOÀNG, PhD.
Ho Chi Minh City, May 2025

HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION
FACULTY OF INTERNATIONAL EDUCATION

GRADUATION PROJECT

DEVELOPMENT OF A MULTIMODAL 3D
OBJECT RECOGNITION AND VISUALIZATION
SYSTEM FOR TRAFFIC ENVIRONMENTS USING
CAMERA-LIDAR FUSION
LÊ HOÀNG TIẾN
Student ID: 21145617
LÊ HỒ MINH KHOA
Student ID: 21145019
Major: AUTOMOTIVE ENGINEERING
Supervisor: TRẦN VŨ HOÀNG, PhD.
Ho Chi Minh City, May 2025

ACKNOWLEDGEMENTS
First and foremost, our group would like to express our sincere gratitude to our
advisor, Vu Hoang Tran, Ph.D., for his invaluable contributions and support
throughout the completion of this graduation project. Thanks to his dedication and
meticulous guidance, we were able to accomplish our project in the best possible way.
We would also like to extend our heartfelt appreciation to the Faculty of
International Education - Ho Chi Minh City University of Technology and Education,
which has provided us with the environment to acquire valuable lessons and
experiences, forming the foundation for this project.
In addition, we cannot forget to mention our families and friends, who have always
accompanied, supported, and served as a vital source of motivation during our studies
and work at the university. Their encouragement and belief in us have helped us
overcome difficulties and continuously improve ourselves.
The knowledge, skills, and support from our supervisor and everyone involved have
been the solid foundation that enabled us to overcome challenges and successfully
complete the project titled “Development of a Multimodal 3D Object Recognition and
Visualization System for Traffic Environments Using Camera-LiDAR Fusion.”
We would like to express our deepest gratitude!

ii


...

...
Object Detection Task. https://www.nuscenes.org/objectdetection (accessed May 13, 2025).
Z. Liu, Tang, Haotian, Amini, Alexander, Yang, Xinyu, Mao, Huizi, Rus, Daniela
L, Han, Song, Bevfusion: Multi-task multi-sensor fusion with unified birds-eye
view representation, 2023, vol. 35: IEEE, pp. 2774-2781.
J. Ahmad and A. Del Bue, mmfusion: Multimodal fusion for 3d objects detection,
arXiv preprint arXiv:2311.04058, 2023.
T. Yin, X. Zhou, and P. Krahenbuhl, Center-based 3d object detection and
tracking, in Proceedings of the IEEE/CVF conference on computer vision and
pattern recognition, 2021, pp. 11784-11793.
Y. Wang, V. C. Guizilini, T. Zhang, Y. Wang, H. Zhao, and J. Solomon, Detr3d:
3d object detection from multi-view images via 3d-to-2d queries, in Conference on
Robot Learning, 2022: PMLR, pp. 180-191.
Y. Liu, T. Wang, X. Zhang, and J. Sun, Petr: Position embedding transformation
for multi-view 3d object detection, in European conference on computer vision,
2022: Springer, pp. 531-548.
X. Bai et al., Transfusion: Robust lidar-camera fusion for 3d object detection with
transformers, in Proceedings of the IEEE/CVF conference on computer vision and
pattern recognition, 2022, pp. 1090-1099.
J. Cha, M. Joo, J. Park, S. Lee, I. Kim, and H. J. Kim, Robust Multimodal 3D
Object Detection via Modality-Agnostic Decoding and Proximity-based Modality
Ensemble, arXiv preprint arXiv:2407.19156, 2024.
J. Yan et al., Cross modal transformer: Towards fast and robust 3d object
detection, in Proceedings of the IEEE/CVF international conference on computer
vision, 2023, pp. 18268-18278.
H. Hu et al., Ea-lss: Edge-aware lift-splat-shot framework for 3d bev object
detection, arXiv preprint arXiv:2303.17895, 2023.
H. Wang et al., Unitr: A unified and efficient multi-modal transformer for birdseye-view representation, in Proceedings of the IEEE/CVF international conference
on computer vision, 2023, pp. 6792-6802.
Y. Xie et al., Sparsefusion: Fusing multi-modal sparse representations for multisensor 3d object detection, in Proceedings of the IEEE/CVF International
Conference on Computer Vision, 2023, pp. 17591-17602.
Z. Li et al., BEVFormer: Learning Bird’s-Eye-View Representation from MultiCamera Images via Spatiotemporal Transformers.(2022), URL https://arxiv.
org/abs/2203.17270, 2022.
N. S. Council, Reference Material for DDC Instructors, 5th Edition ed. Itasca, IL:
National Safety Council, 2005.
97

S

K

L

0

0

2

1

5

4