SD-DefSLAM: Semi-Direct Monocular SLAM for Deformable and Intracorporeal Scenes
This addresses the challenge of mapping deforming environments like surgical scenes for medical applications, representing a domain-specific advancement.
The authors tackled the problem of performing SLAM in highly deforming and intracorporeal scenes, where conventional methods fail due to dynamic parts, and achieved results showing that SD-DefSLAM outperforms DefSLAM in tracking, reconstruction accuracy, and scale drift, being the first system to robustly perform SLAM inside the human body.
Conventional SLAM techniques strongly rely on scene rigidity to solve data association, ignoring dynamic parts of the scene. In this work we present Semi-Direct DefSLAM (SD-DefSLAM), a novel monocular deformable SLAM method able to map highly deforming environments, built on top of DefSLAM. To robustly solve data association in challenging deforming scenes, SD-DefSLAM combines direct and indirect methods: an enhanced illumination-invariant Lucas-Kanade tracker for data association, geometric Bundle Adjustment for pose and deformable map estimation, and bag-of-words based on feature descriptors for camera relocation. Dynamic objects are detected and segmented-out using a CNN trained for the specific application domain. We thoroughly evaluate our system in two public datasets. The mandala dataset is a SLAM benchmark with increasingly aggressive deformations. The Hamlyn dataset contains intracorporeal sequences that pose serious real-life challenges beyond deformation like weak texture, specular reflections, surgical tools and occlusions. Our results show that SD-DefSLAM outperforms DefSLAM in point tracking, reconstruction accuracy and scale drift thanks to the improvement in all the data association steps, being the first system able to robustly perform SLAM inside the human body.