Improving Worst Case Visual Localization Coverage via Place-Specific Sub-Selection in Multi-Camera Systems

Abstract

Can knowing where you are assist in perceiving objects in your surroundings, especially under adverse weather and lighting conditions? In this work we investigate whether a prior map can be leveraged to aid in the detection of dynamic objects in a scene without the need for a 3D map or pixel-level map-query correspondences. We contribute an algorithm which refines an initial set of candidate object detections and produces a refined subset of highly accurate detections using a prior map. We begin by using visual place recognition (VPR) to retrieve a reference map image for a given query image, then use a binary classification neural network that compares the query and mapping image regions to validate the query detection. Once our classification network is trained, on approximately 1000 query-map image pairs, it is able to improve the performance of vehicle detection when combined with an existing off-the-shelf vehicle detector. We demonstrate our approach using standard datasets across two cities (Oxford and Zurich) under different settings of train-test separation of map-query traverse pairs. We further emphasize the performance gains of our approach against alternative design choices and show that VPR suffices for the task, eliminating the need for precise ground truth localization.

Deterministic Localization for Fully Automatic Operation: A Survey and Experiments

“…Besides, with the popularization of fully automatic operation (FAO), high accuracy and deterministic localization are allimportant (e.g., 95% localization error within 0.48 m on freeways and higher accuracy demands on local street) [4]. To address these issues, multiple localization methods have been gradually emerging as the complement of GNSS, such as wireless localization [5,6], visual localization [7], inertial navigation system (INS) [8] and so on. Alternatively, some researches utilize sensor fusion, map-matching and other methods to achieve localization enhancement [?…”

A Review of Recurrent Neural Network Based Camera Localization for Indoor Environments

“…In many applications such as indoor mobile robot, cameras capture image sequences rather than recording individual images. Substantial research has been conducted on image sequences for visual localization [5]. Mobile robot navigation [7], [8], and image-based indoor positioning are essential aspects that have recently attracted significant interest from academia and industry.…”