Bayesian Spatial Kernel Smoothing for Scalable Dense Semantic Mapping
This work addresses the need for scalable and accurate semantic mapping in robotics, though it is incremental as it generalizes an existing framework.
The paper tackles the problem of creating dense 3D semantic occupancy maps from noisy point clouds by extending a Bayesian kernel inference model from binary to multi-class scenarios, resulting in a method that outperforms current baselines and runs at about 2 Hz on a laptop CPU.
This paper develops a Bayesian continuous 3D semantic occupancy map from noisy point clouds by generalizing the Bayesian kernel inference model for building occupancy maps, a binary problem, to semantic maps, a multi-class problem. The proposed method provides a unified probabilistic model for both occupancy and semantic probabilities and nicely reverts to the original occupancy mapping framework when only one occupied class exists in obtained measurements. The Bayesian spatial kernel inference relaxes the independent grid assumption and brings smoothness and continuity to the map inference, enabling to exploit local correlations present in the environment and increasing the performance. The accompanying software uses multi-threading and vectorization, and runs at about 2 Hz on a laptop CPU. Evaluations using multiple sequences of stereo camera and LiDAR datasets show that the proposed method consistently outperforms current baselines. We also present a qualitative evaluation using data collected with a bipedal robot platform on the University of Michigan - North Campus.