DepthCN: Vehicle detection using 3D-LIDAR and ConvNet

By Alireza Asvadi, Luis Garrote, Cristiano Premebida, Paulo Peixoto, Urbano Jose C. Nunes. 2017

69 citations recorded by the source corpus.

Subfields: Automotive 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 Automotive Engineering

1. Di Feng
2. Klaus C. J. Dietmayer
3. Wei Zhan
4. Steven L. Waslander
5. Zining Wang
6. Masayoshi Tomizuka
7. Ali Harakeh
8. Lars Rosenbaum

In Computer Vision and Pattern Recognition

1. Di Feng
2. Steven L. Waslander
3. Klaus C. J. Dietmayer
4. Ali Harakeh
5. Christian Haase-Schuetz
6. Werner Wiesbeck
7. Jing Ye
8. Wei Zhan

In Environmental Engineering

1. Steven L. Waslander
2. Ali Harakeh
3. Wei Zhan
4. Di Feng
5. Zining Wang
6. Masayoshi Tomizuka
7. Klaus C. J. Dietmayer
8. Lars Rosenbaum

Citations in the corpus

• Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection (2018, background): “[18] cluster the point clouds into several segments, and generates a frontview Dense-depth Map (DM) for each segment.”
• RT3D: Real-Time 3-D Vehicle Detection in LiDAR Point Cloud for Autonomous Driving (2018, background): “[9], [14], [15] constructed a compact 2D representation of 3D point cloud from bird’s-eye view, while [16] placed 3D windows on a front-view range map for vehicle detection.”
• YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud (2018, background): “ values in the z dimension are much smaller than that of the x and y (most objects have very similar box elevations). The height of the box h Eq. (8) is also predicted similarly to the width w in Eq. (6) and length l in Eq. (7) 6 Fig.3. Sample of the grid output when extended to the third dimension ”
• Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges (2019, background): “mean average [110], nearest neighbors [143], or bilateral filter [144].”
• Fusing Bird View LIDAR Point Cloud and Front View Camera Image for Deep Object Detection (2017, methodology): “Some fusion-based networks [8, 9] directly adapt from the Faster-RCNN structure with proposals from LIDAR so as to preserve the 3D information.”
• A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving (2020, methodology): “Those ROI can be extracted by non-deep learning approaches such as clustering [139] and voting [140], or by a neural network such as a Region Proposal Network (RPN) in the Faster-RCNN architecture [93].”