Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation

Gregory P. Meyer; Jake Charland; Darshan Hegde; Ankit Laddha; Carlos Vallespi-Gonzalez

Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation

Computer Vision and Pattern Recognition 2019-04-26 v1 Machine Learning Robotics

Authors: Gregory P. Meyer , Jake Charland , Darshan Hegde , Ankit Laddha , Carlos Vallespi-Gonzalez

Abstract

In this paper, we present an extension to LaserNet, an efficient and state-of-the-art LiDAR based 3D object detector. We propose a method for fusing image data with the LiDAR data and show that this sensor fusion method improves the detection performance of the model especially at long ranges. The addition of image data is straightforward and does not require image labels. Furthermore, we expand the capabilities of the model to perform 3D semantic segmentation in addition to 3D object detection. On a large benchmark dataset, we demonstrate our approach achieves state-of-the-art performance on both object detection and semantic segmentation while maintaining a low runtime.

Keywords

point cloud segmentation multi-sensor fusion semantic segmentation

Cite

@article{arxiv.1904.11466,
  title  = {Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation},
  author = {Gregory P. Meyer and Jake Charland and Darshan Hegde and Ankit Laddha and Carlos Vallespi-Gonzalez},
  journal= {arXiv preprint arXiv:1904.11466},
  year   = {2019}
}

Comments

Accepted for publication at CVPR Workshop on Autonomous Driving 2019

Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation

Abstract

Keywords

Cite

Comments

Related papers