EDENet: Echo Direction Encoding Network for Place Recognition Based on Ground Penetrating Radar

Pengyu Zhang, Xieyuanli Chen, Yuwei Chen, Beizhen Bi, Tian Jin, Xiaotao Huang, Liang Shen

Abstract:

Ground penetrating radar (GPR) based localization has
gained significant recognition in robotics due to its ability to
detect stable subsurface features, offering advantages in envi
ronments where traditional sensors like cameras and LiDAR
may struggle. However, existing methods are primarily fo
cused on small-scale place recognition (PR), leaving the chal
lenges of PR in large-scale maps unaddressed. These chal
lenges include the inherent sparsity of underground features
and the variability in underground dielectric constants, which
complicate robust localization. In this work, we investigate
the geometric relationship between GPR echo sequences and
underground scenes, leveraging the robustness of directional
features to inform our network design. We introduce learn
able Gabor filters for the precise extraction of directional re
sponses, coupled with a direction-aware attention mechanism
for effective geometric encoding. To further enhance perfor
mance, we incorporate a shift-invariant unit and a multi-scale
aggregation strategy to better accommodate variations in di
electric constants. Experiments conducted on public datasets
demonstrate that our proposed EDENet not only surpasses
existing solutions in terms of PR performance but also offers
advantages in model size and computational efficiency.