Transforming morning to afternoon using linear regression techniques

Abstract

Visual localization in outdoor environments is often hampered by the natural variation in appearance caused by such things as weather phenomena, diurnal fluctuations in lighting, and seasonal changes. Such changes are global across an environment and, in the case of global li seasonal variation, the change in appearance occurs in a regular, cyclic manner. Visual localization could be greatly improved if it were possible to predict the appearance of a particular location at a particular time appearance of the location in the past and knowledge of the nature of appearance change over time.In this paper, we investigate whether global changes in an environment can be learned improve visual localization performance. We a test case, and generate transformations between morning and afternoon using sample images from a training set. We demonstrate the learned transformation can be generalized from training data and show the resulting visual a test set is improved relative to raw image compar improvement in localization remains when the area is revisited several weeks later.

Automatic image scaling for place recognition in changing environments

“…Existing condition-invariant approaches either attempt to represent places in lighting-invariant forms [13], [14]; use a training approach to dynamically model or predict changes in appearance [10], [15]- [18]; build a database of scenes under differing conditions [19]; or attempt to learn invariant place-dependent features [20]. The drawbacks of these techniques are their requirement of multiple visits to a place, and limited applicability to previously-unseen environmental conditions.…”

Look No Deeper: Recognizing Places from Opposing Viewpoints under Varying Scene Appearance using Single-View Depth Estimation

“…In visual place recognition, changing environments are a major challenge due to perceptual aliasing between the representations of places under severe appearance variations. A number of techniques have been proposed to improve the localization ability, including: leveraging temporal information [6], [23], [24], learning the appearance change over time [25], [26], [27], and extracting geometric and spatial information out of an image [28], [29], [30].…”

Compact Environment-Invariant Codes for Robust Visual Place Recognition

“…Milford et al [4] proposed to use the video sequence instead of independent images, thereby utilising the continuity constraint of consecutive images in-order to remove outliers. Lowry et al [6] employed linear regression techniques to predict the temporal appearance of a place based on the time of the day. Neubert et al [7] uses a vocabulary of superpixels to predict the change in appearance of the scene.…”