{
  "id": "1611.04144",
  "version": "v1",
  "published": "2016-11-13T15:31:31.000Z",
  "updated": "2016-11-13T15:31:31.000Z",
  "title": "Semi-Dense 3D Semantic Mapping from Monocular SLAM",
  "authors": [
    "Xuanpeng Li",
    "Rachid Belaroussi"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "The bundle of geometry and appearance in computer vision has proven to be a promising solution for robots across a wide variety of applications. Stereo cameras and RGB-D sensors are widely used to realise fast 3D reconstruction and trajectory tracking in a dense way. However, they lack flexibility of seamless switch between different scaled environments, i.e., indoor and outdoor scenes. In addition, semantic information are still hard to acquire in a 3D mapping. We address this challenge by combining the state-of-art deep learning method and semi-dense Simultaneous Localisation and Mapping (SLAM) based on video stream from a monocular camera. In our approach, 2D semantic information are transferred to 3D mapping via correspondence between connective Keyframes with spatial consistency. There is no need to obtain a semantic segmentation for each frame in a sequence, so that it could achieve a reasonable computation time. We evaluate our method on indoor/outdoor datasets and lead to an improvement in the 2D semantic labelling over baseline single frame predictions.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2016-11-13T15:31:31.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "semi-dense 3d semantic mapping",
      "monocular slam",
      "baseline single frame predictions",
      "realise fast 3d reconstruction",
      "state-of-art deep learning method"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}