On the Performance of ConvNet Features for Place Recognition

TL;DR

This paper evaluates ConvNet features for robotic place recognition, demonstrating that with optimization techniques, real-time performance is achievable with minimal accuracy loss, and that semantic training improves robustness to appearance changes.

Contribution

It provides a comprehensive comparison of ConvNet features for place recognition, introduces optimization methods for real-time performance, and analyzes network training effects on robustness.

Findings

Two orders of magnitude speed-up with minimal accuracy loss

Semantic place categorization improves recognition under appearance changes

Identifies optimal networks and layers for different recognition aspects

Abstract

After the incredible success of deep learning in the computer vision domain, there has been much interest in applying Convolutional Network (ConvNet) features in robotic fields such as visual navigation and SLAM. Unfortunately, there are fundamental differences and challenges involved. Computer vision datasets are very different in character to robotic camera data, real-time performance is essential, and performance priorities can be different. This paper comprehensively evaluates and compares the utility of three state-of-the-art ConvNets on the problems of particular relevance to navigation for robots; viewpoint-invariance and condition-invariance, and for the first time enables real-time place recognition performance using ConvNets with large maps by integrating a variety of existing (locality-sensitive hashing) and novel (semantic search space partitioning) optimization techniques. We present extensive experiments on four real world datasets cultivated to evaluate each of the specific challenges in place recognition. The results demonstrate that speed-ups of two orders of magnitude can be achieved with minimal accuracy degradation, enabling real-time performance. We confirm that networks trained for semantic place categorization also perform better at (specific) place recognition when faced with severe appearance changes and provide a reference for which networks and layers are optimal for different aspects of the place recognition problem.