Sensor Equivariance by LiDAR Projection Images
This addresses sensor bias for machine vision tasks in highly automated driving, but it is incremental as it extends existing methods with an additional channel.
The paper tackles the problem of sensor-dependent object representation in projection-based sensors like LiDAR, which causes distortions due to variations in resolution and field of view, and demonstrates that their method reduces bias in LiDAR instance segmentation in a synthetic environment.
In this work, we propose an extension of conventional image data by an additional channel in which the associated projection properties are encoded. This addresses the issue of sensor-dependent object representation in projection-based sensors, such as LiDAR, which can lead to distorted physical and geometric properties due to variations in sensor resolution and field of view. To that end, we propose an architecture for processing this data in an instance segmentation framework. We focus specifically on LiDAR as a key sensor modality for machine vision tasks and highly automated driving (HAD). Through an experimental setup in a controlled synthetic environment, we identify a bias on sensor resolution and field of view and demonstrate that our proposed method can reduce said bias for the task of LiDAR instance segmentation. Furthermore, we define our method such that it can be applied to other projection-based sensors, such as cameras. To promote transparency, we make our code and dataset publicly available. This method shows the potential to improve performance and robustness in various machine vision tasks that utilize projection-based sensors.