Unsupervised Place Discovery for Visual Place Classification

12/21/2016
by   Fei Xiaoxiao, et al.
0

In this study, we explore the use of deep convolutional neural networks (DCNNs) in visual place classification for robotic mapping and localization. An open question is how to partition the robot's workspace into places to maximize the performance (e.g., accuracy, precision, recall) of potential DCNN classifiers. This is a chicken and egg problem: If we had a well-trained DCNN classifier, it is rather easy to partition the robot's workspace into places, but the training of a DCNN classifier requires a set of pre-defined place classes. In this study, we address this problem and present several strategies for unsupervised discovery of place classes ("time cue," "location cue," "time-appearance cue," and "location-appearance cue"). We also evaluate the efficacy of the proposed methods using the publicly available University of Michigan North Campus Long-Term (NCLT) Dataset.

READ FULL TEXT

page 2

page 4

research
06/07/2017

Unsupervised Place Discovery for Place-Specific Change Classifier

In this study, we address the problem of supervised change detection for...
research
09/16/2017

Long-Term Ensemble Learning of Visual Place Classifiers

This paper addresses the problem of cross-season visual place classifica...
research
09/15/2019

Mining Minimal Map-Segments for Visual Place Classifiers

In visual place recognition (VPR), map segmentation (MS) is a preprocess...
research
08/27/2018

Deep Stochastic Attraction and Repulsion Embedding for Image Based Localization

This paper tackles the problem of large-scale image-based localization w...
research
02/14/2020

How to cluster nearest unique nodes from different classes using JJCluster in Wisp application?

The work of finding the best place according to user preference is a ted...
research
12/29/2020

Learning a Dynamic Map of Visual Appearance

The appearance of the world varies dramatically not only from place to p...
research
01/08/2020

BD97 Places : Deep Convolutional Neural Networks for Places Detection

The geolocation services thanks to the precious tool called GPS, are now...

Please sign up or login with your details

Forgot password? Click here to reset