Home
Uni-Logo
 

ISOO_DL^V2 - Semantic Instance Segmentation of Touching and Overlapping Objects

IEEE International Symposium on Biomedical Imaging (ISBI), 2019
Abstract: We present ISOO_DL^V2 - a method for semantic instance segmentation of touching and overlapping objects. We introduce a series of design modifications to the prior framework, including a novel mixed 2D-3D segmentation network and a simplified post-processing procedure which enables segmentation of touching objects without relying on object detection. For the case of overlapping objects where detection is required, we upgrade the bounding box parametrization and allow for smaller reference point distances. All these novelties lead to substantial performance improvements and enable the method to deal with a wider range of challenging practical situations. Additionally, our framework can handle object sub-part segmentation. We evaluate our approach on both real-world and synthetically generated biological datasets and report state-of-the-art performance.
Paper Publisher's link

Images and movies

 

See also

  • Slides (oral presentation at ISBI 2019, 8-11 April 2019, Venice, Italy):

BibTex reference

@InProceedings{BTF19,
  author       = "A. B{\"o}hm and M. Tatarchenko and T. Falk",
  title        = "ISOO_DL^V2 - Semantic Instance Segmentation of Touching and Overlapping Objects",
  booktitle    = "IEEE International Symposium on Biomedical Imaging (ISBI)",
  month        = " ",
  year         = "2019",
  organization = "IEEE",
  url          = "http://lmbweb.informatik.uni-freiburg.de/Publications/2019/BTF19"
}

Other publications in the database