Flexibility-Residual BiSeNetV2 for GPR Image Decluttering

The acquisition of ground-penetrating radar (GPR) data is often impeded by clutter, which poses a significant obstacle to the effectiveness of target detection algorithms. This article presents a novel approach to address this challenge by developing a flexibility-residual BiSeNetV2 for clutter suppression of GPR images. Our proposed network incorporates the flexibility-residual block into BiSeNetV2, allowing for adaptively selected convolutional kernel sizes based on the number of channels and network parameters required for different tasks, thereby ensuring effective mitigation of network degradation while minimizing the impact on time complexity. Moreover, we integrate an efficient channel attention (ECA) attention mechanism into the network, which employs 1-D convolutional local cross-channel interaction to extract interchannel dependencies efficiently. As a result, the size of the 1-D convolutional kernel can be adaptively selected according to the number of channels, determining the coverage of cross-channel interactions. In addition, we adjust the ratio of multiple output losses in the network to optimize its suitability for our task. Experimental results demonstrate the effectiveness of our network for clutter suppression of cluttered images, and the network trained with the simulated dataset also performs better when processing measured GPR data.