EnforceNet: Monocular Camera Localization in Large Scale Indoor Sparse LiDAR Point Cloud
This addresses the cost barrier for robotic applications like autonomous vehicles and AR by reducing reliance on expensive sensors, though it is incremental as it builds on existing neural network methods.
The paper tackles the problem of high-cost centimeter-level pose estimation by proposing EnforceNet, a neural network that localizes a consumer-grade RGB camera within a prior sparse LiDAR map, achieving comparable precision in large-scale indoor parking garage scenes.
Pose estimation is a fundamental building block for robotic applications such as autonomous vehicles, UAV, and large scale augmented reality. It is also a prohibitive factor for those applications to be in mass production, since the state-of-the-art, centimeter-level pose estimation often requires long mapping procedures and expensive localization sensors, e.g. LiDAR and high precision GPS/IMU, etc. To overcome the cost barrier, we propose a neural network based solution to localize a consumer degree RGB camera within a prior sparse LiDAR map with comparable centimeter-level precision. We achieved it by introducing a novel network module, which we call resistor module, to enforce the network generalize better, predicts more accurately, and converge faster. Such results are benchmarked by several datasets we collected in the large scale indoor parking garage scenes. We plan to open both the data and the code for the community to join the effort to advance this field.