Visual Looming from Motion Field and Surface Normals

TL;DR

This paper introduces new methods to quantitatively estimate visual looming from 2D motion fields and surface normals, enabling collision avoidance without range data, with validation on simulated and real KITTI data.

Contribution

It provides novel solutions for deriving visual looming from optical flow derivatives and relates looming to surface normals, advancing collision detection techniques.

Findings

Estimations closely match ground truth in simulations

Methods work effectively on real KITTI data

Advantages and limitations are discussed

Abstract

Looming, traditionally defined as the relative expansion of objects in the observer's retina, is a fundamental visual cue for perception of threat and can be used to accomplish collision free navigation. In this paper we derive novel solutions for obtaining visual looming quantitatively from the 2D motion field resulting from a six-degree-of-freedom motion of an observer relative to a local surface in 3D. We also show the relationship between visual looming and surface normals. We present novel methods to estimate visual looming from spatial derivatives of optical flow without the need for knowing range. Simulation results show that estimations of looming are very close to ground truth looming under some assumptions of surface orientations. In addition, we present results of visual looming using real data from the KITTI dataset. Advantages and limitations of the methods are discussed as well.