Image-Based Place Recognition on Bucolic Environment Across Seasons From Semantic Edge Description
This addresses place recognition for natural, low-texture environments, which is an incremental improvement over urban-focused methods.
The paper tackled the problem of image-based place recognition in bucolic environments with low texture and semantic content, handling variations across seasons, and introduced a global descriptor from semantic edges that achieved state-of-the-art performance on multi-season datasets like CMU-Seasons and Symphony Lake, with results competitive on urban scenes.
Most of the research effort on image-based place recognition is designed for urban environments. In bucolic environments such as natural scenes with low texture and little semantic content, the main challenge is to handle the variations in visual appearance across time such as illumination, weather, vegetation state or viewpoints. The nature of the variations is different and this leads to a different approach to describing a bucolic scene. We introduce a global image descriptor computed from its semantic and topological information. It is built from the wavelet transforms of the image semantic edges. Matching two images is then equivalent to matching their semantic edge descriptors. We show that this method reaches state-of-the-art image retrieval performance on two multi-season environment-monitoring datasets: the CMU-Seasons and the Symphony Lake dataset. It also generalises to urban scenes on which it is on par with the current baselines NetVLAD and DELF.