Tilt Correction of Panoramic Images for a Holistic Visual Homing Method with Planar-Motion Assumption

Abstract

Holistic local visual homing based on warping of panoramic images relies on some simplifying assumptions about the images and the environment to make the problem more tractable. One of these assumptions is that images are captured on flat ground without tilt. While this might be true in some environments, it poses a problem for a wider real-world application of warping. An extension of the warping framework is proposed where tilt-corrected images are used as inputs. The method combines the tilt correction of panoramic images with a systematic search through hypothetical tilt parameters, using an image distance measure produced by warping as the optimization criterion. This method not only improves the homing performance of warping on tilted images, but also allows for a good estimation of the tilt without requiring additional sensors or external image alignment. Experiments on two newly collected tilted panoramic image databases confirm the improved homing performance and the viability of the proposed tilt-estimation scheme. Approximations of the tilt-correction image transformations and multiple direct search strategies for the tilt estimation are evaluated with respect to their runtime vs. estimation quality trade-offs to find a variant of the proposed methods which best fulfills the requirements of practical applications.

Visual homing for coordinated robot team missions

“…Real world visual homing applications require that homing be integrated with obstacle avoidance and that the image comparisons be robust with respect to platform tilt and roll. 20,21 However, robotic work in visual homing has tended to stick closely to the insect inspiration: Control a single robot to return to a location it has visited before and is within its field of view. In our WAVN 4 work, we deploy visual homing for a wider variety of navigation tasks.…”

A Multilayer Perceptron-Based Spherical Visual Compass Using Global Features

“…Depending on the used sensors, visual compasses can be classified as monocular cameras [1][2][3], stereo cameras [4][5][6], RGB-D camera [7][8][9], polarized light camera [10][11][12], omnidirectional cameras [3,13,14], or a combination of sensors [15,16]. Meanwhile, visual compasses have different estimation methods by focusing on various types of information, such as 2D-3D correspondence [17][18][19], virtual visual servoing (VVS) [20][21][22], holistic method [23][24][25], extended Kalman filter (EKF) [26][27][28], and appearance-based method [3,13,29].…”