Visual place recognition (VPR) is a robots ability to determine whether a place was visited before using visual data. While conventional hand-crafted methods for VPR fail under extreme environmental appearance changes, those based on convolutional neural networks (CNNs) achieve state-of-the-art performance but result in model sizes that demand a large amount of memory. Hence, CNN-based approaches are unsuitable for memory-constrained platforms, such as small robots and drones. In this paper, we take a multi-step approach of decreasing the precision of model parameters, combining it with network depth reduction and fewer neurons in the classifier stage to propose a new class of highly compact models that drastically reduce the memory requirements while maintaining state-of-the-art VPR performance, and can be tuned to various platforms and application scenarios. To the best of our knowledge, this is the first attempt to propose binary neural networks for solving the visual place recognition problem effectively under changing conditions and with significantly reduced memory requirements. Our best-performing binary neural network with a minimum number of layers, dubbed FloppyNet, achieves comparable VPR performance when considered against its full precision and deeper counterparts while consuming 99% less memory.
Download