Long-term visual place recognition is challenging as the environment is subject to drastic appearance changes across different temporal resolutions such as time of the day, month, and season. A wide variety of existing methods address the problem by means of feature disentangling or image style transfer, but ignore the structural information which often remains stable even under environmental condition changes. To overcome this limitation, this paper presents a novel Structure-aware Feature Disentanglement Network (SF-DNet) based on knowledge transfer and adversarial learning. Explicitly, probabilistic knowledge transfer (PKT) is employed to transfer knowledge obtained from the Canny edge detector to the structure encoder. An appearance teacher module is then designed to ensure the learning of appearance encoder does not only rely on metric learning. The generated content features with structural information are used to measure the similarity of images. We finally evaluate the proposed approach, and compare it to state-of-the-art place recognition methods using six datasets with extreme environmental changes. Experimental results demonstrate the effectiveness and improvements achieved using the proposed framework.
|Journal||IEEE Transactions on Neural Networks and Learning Systems|
|Publication status||Accepted/In press - 11 Aug 2021|
- Changing environment
- Knowledge transfer
- Visual place recognition