{
  "id": "1806.05620",
  "version": "v1",
  "published": "2018-06-14T15:52:07.000Z",
  "updated": "2018-06-14T15:52:07.000Z",
  "title": "DynSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes",
  "authors": [
    "Berta Bescós",
    "José M. Fácil",
    "Javier Civera",
    "José Neira"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "The assumption of scene rigidity is typical in SLAM algorithms. Such a strong assumption limits the use of most visual SLAM systems in populated real-world environments, which are the target of several relevant applications like service robotics or autonomous vehicles. In this paper we present DynSLAM, a visual SLAM system that, building over ORB-SLAM2 [1], adds the capabilities of dynamic object detection and background inpainting. DynSLAM is robust in dynamic scenarios for monocular, stereo and RGB-D configurations. We are capable of detecting the moving objects either by multi-view geometry, deep learning or both. Having a static map of the scene allows inpainting the frame background that has been occluded by such dynamic objects. We evaluate our system in public monocular, stereo and RGB-D datasets. We study the impact of several accuracy/speed trade-offs to assess the limits of the proposed methodology. DynSLAM outperforms the accuracy of standard visual SLAM baselines in highly dynamic scenarios. And it also estimates a map of the static parts of the scene, which is a must for long-term applications in real-world environments.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-06-14T15:52:07.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "dynamic scenes",
      "visual slam system",
      "inpainting",
      "standard visual slam baselines",
      "real-world environments"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}