大規模学習による視覚的場所認識のための深層学習特徴量
Deep Learning Features at Scale for Visual Place Recognition
場所認識タスク専用に大規模CNNを学習し、多スケール特徴符号化で環境・視点変化に頑健な特徴を生成。数千地点の外観変化を含む大規模データセットSPEDを構築し、ベンチマークで平均10%の性能向上を達成した。
著者: Zetao Chen, Adam Jacobson, Niko Sunderhauf, Ben Upcroft, Lingqiao Liu, Chunhua Shen, Ian Reid, Michael Milford
分類: cs.CV, cs.RO
原文アブストラクト
The success of deep learning techniques in the computer vision domain has triggered a range of initial investigations into their utility for visual place recognition, all using generic features from networks that were trained for other types of recognition tasks. In this paper, we train, at large scale, two CNN architectures for the specific place recognition task and employ a multi-scale feature encoding method to generate condition- and viewpoint-invariant features. To enable this training to occur, we have developed a massive Specific PlacEs Dataset (SPED) with hundreds of examples of place appearance change at thousands of different places, as opposed to the semantic place type datasets currently available. This new dataset enables us to set up a training regime that interprets place recognition as a classification problem. We comprehensively evaluate our trained networks on several challenging benchmark place recognition datasets and demonstrate that they achieve an average 10% increase in performance over other place recognition algorithms and pre-trained CNNs. By analyzing the network responses and their differences from pre-trained networks, we provide insights into what a network learns when training for place recognition, and what these results signify for future research in this area.
