Learning Geocentric Object Pose in Oblique Monocular Images

Gordon Christie, Rodrigo Rene Rai Munoz Abujder, Kevin Foster, Shea Hagstrom, Gregory D. Hager, Myron Z. Brown

Research output: Contribution to journalConference articlepeer-review

Abstract

An object's geocentric pose. defined as the height above ground and orientation with respect to gravity, is a powerful representation of real-world structure for object detection, segmentation, and localization tasks using RGBD images. For close-range vision tasks, height and orientation have been derived directly from stereo-computed depth and more recently from monocular depth predicted by deep networks. For long-range vision tasks such as Earth observation, depth cannot be reliably estimated with monocular images. Inspired by recent work in monocular height above ground prediction and optical flow prediction from static images, we develop an encoding of geocentric pose to address this challenge and train a deep network to compute the representation densely, supervised by publicly available airborne lidar. We exploit these attributes to rectify oblique images and remove observed object parallax to dramatically improve the accuracy of localization and to enable accurate alignment of multiple images taken from very different oblique viewpoints. We demonstrate the value of our approach by extending two large-scale public datasets for semantic segmentation in oblique satellite images. All of our data and code are publicly available.

Original languageEnglish (US)
Article number9157635
Pages (from-to)14500-14508
Number of pages9
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs
StatePublished - 2020
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 - Virtual, Online, United States
Duration: Jun 14 2020Jun 19 2020

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Learning Geocentric Object Pose in Oblique Monocular Images'. Together they form a unique fingerprint.

Cite this