.png){kind=icon}
.png){kind=icon}
Return
Image Patch-Matching With Graph-Based Learning in Street Scenes
.png){kind=icon}
OA
AI
DOI：10.1109/TIP.2023.3281171.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Matching landmark patches from a real-time image captured by an on-vehicle camera with landmark patches in an image database plays an important role in various computer perception tasks for autonomous driving. Current methods focus on local matching for regions of interest and do not take into account spatial neighborhood relationships among the image patches, which typically correspond to objects in the environment. In this paper, we construct a spatial graph with the graph vertices corresponding to patches and edges capturing the spatial neighborhood information. We propose a joint feature and metric learning model with graph-based learning. We provide a theoretical basis for the graph-based loss by showing that the information distance between the distributions conditioned on matched and unmatched pairs is maximized under our framework. We evaluate our model using several street-scene datasets and demonstrate that our approach achieves state-of-the-art matching results.
Keywords:
Image patch-matching
graph neural network
Kullback-Leibler divergence
information distance maximization
visual place recognition
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W