Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation
This work addresses the need for efficient and accurate 3D perception in autonomous systems, but it is incremental as it builds upon an existing method.
The paper tackles the problem of 3D object detection and semantic segmentation by extending LaserNet with a sensor fusion method that combines LiDAR and image data, resulting in state-of-the-art performance on both tasks with improved detection at long ranges and low runtime.
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.