{
  "id": "2011.13669",
  "version": "v1",
  "published": "2020-11-27T11:10:46.000Z",
  "updated": "2020-11-27T11:10:46.000Z",
  "title": "Towards real-time object recognition and pose estimation in point clouds",
  "authors": [
    "Marlon Marcon",
    "Olga Regina Pereira Bellon",
    "Luciano Silva"
  ],
  "comment": "Accepted as Full paper at VISAPP2021",
  "categories": [
    "cs.CV"
  ],
  "abstract": "Object recognition and 6DoF pose estimation are quite challenging tasks in computer vision applications. Despite efficiency in such tasks, standard methods deliver far from real-time processing rates. This paper presents a novel pipeline to estimate a fine 6DoF pose of objects, applied to realistic scenarios in real-time. We split our proposal into three main parts. Firstly, a Color feature classification leverages the use of pre-trained CNN color features trained on the ImageNet for object detection. A Feature-based registration module conducts a coarse pose estimation, and finally, a Fine-adjustment step performs an ICP-based dense registration. Our proposal achieves, in the best case, an accuracy performance of almost 83\\% on the RGB-D Scenes dataset. Regarding processing time, the object detection task is done at a frame processing rate up to 90 FPS, and the pose estimation at almost 14 FPS in a full execution strategy. We discuss that due to the proposal's modularity, we could let the full execution occurs only when necessary and perform a scheduled execution that unlocks real-time processing, even for multitask situations.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-11-27T11:10:46.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "pose estimation",
      "real-time object recognition",
      "point clouds",
      "cnn color features",
      "standard methods deliver far"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}