A Geometric Approach to Obtain a Bird's Eye View from an Image

Abstract

The objective of this paper is to rectify any monocular image by computing a homography matrix that transforms it to a bird's eye (overhead) view. We make the following contributions: (i) we show that the homography matrix can be parameterised with only four parameters that specify the horizon line and the vertical vanishing point, or only two if the field of view or focal length is known; (ii) We introduce a novel representation for the geometry of a line or point (which can be at infinity) that is suitable for regression with a convolutional neural network (CNN); (iii) We introduce a large synthetic image dataset with ground truth for the orthogonal vanishing points, that can be used for training a CNN to predict these geometric entities; and finally (iv) We achieve state-of-the-art results on horizon detection, with 74.52% AUC on the Horizon Lines in the Wild dataset. Our method is fast and robust, and can be used to remove perspective distortion from videos in real time.

arXiv commentICCV Workshop "Geometry Meets Deep Learning" 2019

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Learning Depth from Single Images with Deep Neural Network Embedding Focal Length
• Vanishing point detection with convolutional neural networks
• Detecting Vanishing Points using Global Image Context in a Non-Manhattan World
• Geometry-aware Deep Network for Single-Image Novel View Synthesis

Cited by in corpus (3)

• BEV-Seg: Bird's Eye View Semantic Segmentation Using Geometry and Semantic Point Cloud
• Single Image Human Proxemics Estimation for Visual Social Distancing
• Car Pose in Context: Accurate Pose Estimation with Ground Plane Constraints