Computer Vision -- ECCV 2016 Workshops, Springer International Publishing

Single-Image Insect Pose Estimation by Graph Based Geometric Models and Random Forests

M. Shen, L. Duan, O. Deussen

Material

Abstract

We propose a new method for detailed insect pose estimation, which aims to detect landmarks as the tips of an insect's antennae and mouthparts from a single image. In this paper, we formulate this problem as inferring a mapping from the appearance of an insect to its corresponding pose. We present a unified framework that jointly learns a mapping from the local appearance (image patch) and the global anatomical structure (silhouette) of an insect to its corresponding pose. Our main contribution is that we propose a data driven approach to learn the geometric prior for modeling various insect appearance. Combined with the discriminative power of Random Forests (RF) model, our method achieves high precision of landmark localization. This approach is evaluated using three challenging datasets of insects which we make publicly available. Experiments show that it achieves improvement over the traditional RF regression method, and comparably precision to human annotators.

BibTeX

@inbook{Shen2016SingleImageInsect,
  abstract   = {We propose a new method for detailed insect pose estimation, which aims to detect landmarks as the tips of an insectś antennae and mouthparts from a single image. In this paper, we formulate this problem as inferring a mapping from the appearance of an insect to its corresponding pose. We present a unified framework that jointly learns a mapping from the local appearance (image patch) and the global anatomical structure (silhouette) of an insect to its corresponding pose. Our main contribution is that we propose a data driven approach to learn the geometric prior for modeling various insect appearance. Combined with the discriminative power of Random Forests (RF) model, our method achieves high precision of landmark localization. This approach is evaluated using three challenging datasets of insects which we make publicly available. Experiments show that it achieves improvement over the traditional RF regression method, and comparably precision to human annotators.},
  address    = {Cham},
  author     = {M. Shen and L. Duan and O. Deussen},
  booktitle  = {Computer Vision -- ECCV 2016 Workshops},
  doi        = {10.1007/978-3-319-46604-0_16},
  editor     = {Hua, Gang and Jégou, Hervé},
  isbn       = {978-3-319-46604-0},
  pages      = {217--230},
  publisher  = {Springer International Publishing},
  title      = {Single-Image Insect Pose Estimation by Graph Based Geometric Models and Random Forests},
  year       = {2016},
  url        = {http://graphics.uni-konstanz.de/publikationen/Shen2016SingleImageInsect},
}