Visual Place Recognition with Repetitive Structures

We detect groups of repeated features (shown in different colors), and use the number of the repetitions to adapt the weights of the features in the bag-of-visual words model: (1) repetitive features implicitly provide soft-assignment and (2) truncating their weights prevents them from dominating the matching score.
Authors: Akihiko Torii, Josef Sivic, Tomas Pajdla,
Masatoshi Okutomi
Abstract: Repeated structures such as building facades, fences or road markings often represent a significant challenge for place recognition. Repeated structures are notoriously hard for establishing correspondences using multi-view geometry. Even more importantly, they violate the feature independence assumed in the bag-of-visual-words representation which often leads to over-counting evidence and significant degradation of retrieval performance. In this work we show that repeated structures are not a nuisance but, when appropriately represented, they form an important distinguishing feature for many places. We describe a representation of repeated structures suitable for scalable retrieval. It is based on robust detection of repeated image structures and a simple modification of weights in the bag-of-visual-word model. Place recognition results are shown on datasets of street-level imagery from Pittsburgh and San Francisco demonstrating significant gains in recognition performance compared to the standard bag-of-visual-words baseline and more recently proposed burstiness weighting.
Code:
Repttile detection and BoVW with adaptive assignment (ver03)
Repttile detection and BoVW with adaptive assignment (ver04 with yael_v438)
Data: Available on request.