YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud

By Waleed Ali, Sherif Abdelkarim, Mohamed Zahran, Mahmoud Zidan, Ahmad El Sallab. 2018

172 citations recorded by the source corpus.

Object detection and classification in 3D is a key task in Automated Driving (AD). LiDAR sensors are employed to provide the 3D point cloud reconstruction of the surrounding environment, while the task of 3D object bounding box detection in real time remains a strong algorithmic challenge. In this paper, we build on the success of the one-shot regression meta-architecture in the 2D perspective image space and extend it to generate oriented 3D object bounding boxes from LiDAR point cloud. Our main contribution is in extending the loss function of YOLO v2 to include the yaw angle, the 3D box center in Cartesian coordinates and the height of the box as a direct regression problem. This formulation enables real-time performance, which is essential for automated driving. Our results are showing promising figures on KITTI benchmark, achieving real-time performance (40 fps) on Titan X GPU.

Subfields: Aerospace Engineering, Automotive Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Shaoshuai Shi
2. Hongsheng Li
3. Jiageng Mao
4. Jiaya Jia
5. Xiaoyong Shen
6. Yilun Chen
7. Shu Liu
8. Yilun Chen

In Automotive Engineering

1. Jiaya Jia
2. Xiaoyong Shen
3. Shaoshuai Shi
4. Yilun Chen
5. Shu Liu
6. Xiaogang Wang
7. Hongsheng Li

In Computer Vision and Pattern Recognition

1. Xiaogang Wang
2. Hongsheng Li
3. Jiaya Jia
4. Luc Van Gool
5. Ming-Hsuan Yang
6. Dacheng Tao
7. Chunhua Shen
8. Yi Yang

Citations in the corpus

• Fast Point R-CNN (2019, background): “One line of solutions is to use a coarse grid [43, 40, 23, 2, 31, 1]; but coarse quantization prevents following CNN from utilizing fine-grained information.”
• Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds (2022, unknown): “Due to the unstructured and orderless nature of 3D point clouds, early works usually first convert the raw point clouds into intermediate regular representation, including projecting the 3D point clouds into 2D images from birdseye-view or frontal view [1, 17, 18, 41, 42, 50, 60], or transformed int”
• 3D Object Detection for Autonomous Driving: A Comprehensive Survey (2022, methodology): “8) [263, 3, 10, 364, 333, 382, 124, 383, 358] [344, 65, 388, 292, 347, 8, 187, 57] [375, 66, 152, 340, 203, 339, 44, 253] [94, 285, 97, 195, 204, 185, 255] L(1)θ (Eqn.”