BirdNet: A 3D Object Detection Framework from LiDAR Information

By Jorge Beltrán, Carlos Guindel, Francisco Miguel Moreno, Daniel Cruzado, Fernando Turrado García, Arturo de la Escalera. 2018

286 citations recorded by the source corpus.

Understanding driving situations regardless the conditions of the traffic scene is a cornerstone on the path towards autonomous vehicles; however, despite common sensor setups already include complementary devices such as LiDAR or radar, most of the research on perception systems has traditionally focused on computer vision. We present a LiDAR-based 3D object detection pipeline entailing three stages. First, laser information is projected into a novel cell encoding for bird's eye view projection. Later, both object location on the plane and its heading are estimated through a convolutional neural network originally designed for image processing. Finally, 3D oriented detections are computed in a post-processing phase. Experiments on KITTI dataset show that the proposed framework achieves state-of-the-art results among comparable methods. Further tests with different LiDAR sensors in real scenarios assess the multi-device capabilities of the approach.

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

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. Xiaogang Wang
4. Jiaya Jia
5. Binh Yang
6. Shu Liu
7. Roberto Cipolla
8. Ming Liang

In Computer Vision and Pattern Recognition

1. Xiaogang Wang
2. Luc Van Gool
3. Hongsheng Li
4. Ming-Hsuan Yang
5. Dacheng Tao
6. Jiaya Jia
7. Jitendra Malik
8. Alan L. Yuille

In Environmental Engineering

1. Shaoshuai Shi
2. Binh Yang
3. Raquel Urtasun
4. Jiaya Jia
5. Hongsheng Li
6. Shu Liu
7. Xiaogang Wang
8. Ming Liang

Citations in the corpus

• Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection (2021, background): “Many deep learning-based approaches (Li, Zhang, and Xia 2016; Chen et al. 2017; Beltrán et al. 2018; Yan, Mao, and Li 2018; Yang, Luo, and Urtasun 2018; Zeng et al. 2018; Zhou and Tuzel 2018; Chen et al. 2019; Lang et al. 2019; Qi et al. 2019; Shi, Wang, and Li 2019; Yang et al. 2019; Zhou et al.…”
• A Survey on 3D Object Detection Methods for Autonomous Driving Applications (2019, methodology): “[51] propose a novel encoding that normalizes”
• 3D Object Detection for Autonomous Driving: A Comprehensive Survey (2022, methodology): “The development of backbone networks has experienced four stages: (1) 2D networks to process BEV images that are generated by point cloud projection [10, 335], (2) 2D networks to process pillars that are generated by PointNet encoding [124], (3) 3D sparse convolutional networks to process voxelized ”
• Deep Learning for 3D Point Clouds: A Survey (2019, background): “0 - - - - - - - - BirdNet [153] L 9.”
• Orthographic Feature Transform for Monocular 3D Object Detection (2018, methodology): “Vision-only systems offer several advantages over more widespread LiDAR-based methods [1, 5, 6, 14, 21, 26, 31, 36], such as lower cost, higher resolution and robustness to adverse weather conditions.”
• Multi-Task Multi-Sensor Fusion for 3D Object Detection (2019, unknown): “This formulation is more accurate than plane based parametrization [3, 1], as in practice the road is often curved especially when we look far ahead.”
• LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving (2019, methodology): “Single shot based methods [1, 16, 28, 30] produce detections with a single stage network.”
• Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks (2021, background): “…[34], [49], [73] Count [15], [16] Height (min/max/mean) [15], [16], [20], [24], [33] Intensity (min/max/mean) [15], [16], [20], [30], [33], [34], [49] Density [20], [24], [33] Table I. Summary of commonly-used cell-level aggregated features in state-of-the-art LiDAR-based object detection models.”
• RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving (2020, background): “Therefor, most of the recent 3D object detection employ it in different representation to obtain the state-of-the-art model [48, 3, 9, 36, 21].”
• 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.”
• HDNET: Exploiting HD Maps for 3D Object Detection (2018, methodology): “7IoU (%) easy moderate hard BirdNet [22] LiDAR 110 75.”
• FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds (2019, methodology): “31% of BirdNet [12]).”
• Cooperative Perception for 3D Object Detection in Driving Scenarios Using Infrastructure Sensors (2019, background): “Models in category (b) usually project the input point cloud into a Bird-Eye-View (BEV) [16] or cylindrical coordinates [17] to obtain a structured, fixed-size representation that can be fed to convolutional neural networks for object detection.”
• Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review (2020, background): “There are several types of view generation methods to project 3D points into 2D images: BEV images [43, 116, 123, 124], front view images [123], spherical projections [50], and cylindral projection [9].”