Condition-Invariant and Compact Visual Place Description by Convolutional Autoencoder
This addresses the need for efficient and robust visual place recognition in robotics or autonomous systems, though it appears incremental as it builds on existing CNN-based descriptors.
The paper tackles the problem of visual place recognition in condition-varying environments by proposing a convolutional autoencoder to map high-dimensional CNN features to a low-dimensional space, achieving superior performance to state-of-the-art methods on three challenging datasets with illumination changes.
Visual place recognition (VPR) in condition-varying environments is still an open problem. Popular solutions are CNN-based image descriptors, which have been shown to outperform traditional image descriptors based on hand-crafted visual features. However, there are two drawbacks of current CNN-based descriptors: a) their high dimension and b) lack of generalization, leading to low efficiency and poor performance in applications. In this paper, we propose to use a convolutional autoencoder (CAE) to tackle this problem. We employ a high-level layer of a pre-trained CNN to generate features, and train a CAE to map the features to a low-dimensional space to improve the condition invariance property of the descriptor and reduce its dimension at the same time. We verify our method in three challenging datasets involving significant illumination changes, and our method is shown to be superior to the state-of-the-art. For the benefit of the community, we make public the source code.