Kernel Inversed Pyramidal Resizing Network for Efficient Pavement Distress Recognition

TL;DR

This paper introduces KIPRN, a novel image resizing network that enhances pavement distress recognition by preserving discriminative features across scales, leading to improved accuracy and efficiency in CNN-based pavement inspection.

Contribution

The paper proposes KIPRN, a lightweight, plug-in image resizing module with pyramidal and inverse convolution, improving CNN performance in pavement distress detection.

Findings

KIPRN improves CNN accuracy on pavement datasets.

Combining KIPRN with EfficientNet-B3 outperforms existing methods.

The method enhances both recognition performance and computational efficiency.

Abstract

Pavement Distress Recognition (PDR) is an important step in pavement inspection and can be powered by image-based automation to expedite the process and reduce labor costs. Pavement images are often in high-resolution with a low ratio of distressed to non-distressed areas. Advanced approaches leverage these properties via dividing images into patches and explore discriminative features in the scale space. However, these approaches usually suffer from information loss during image resizing and low efficiency due to complex learning frameworks. In this paper, we propose a novel and efficient method for PDR. A light network named the Kernel Inversed Pyramidal Resizing Network (KIPRN) is introduced for image resizing, and can be flexibly plugged into the image classification network as a pre-network to exploit resolution and scale information. In KIPRN, pyramidal convolution and kernel inversed convolution are specifically designed to mine discriminative information across different feature granularities and scales. The mined information is passed along to the resized images to yield an informative image pyramid to assist the image classification network for PDR. We applied our method to three well-known Convolutional Neural Networks (CNNs), and conducted an evaluation on a large-scale pavement image dataset named CQU-BPDD. Extensive results demonstrate that KIPRN can generally improve the pavement distress recognition of these CNN models and show that the simple combination of KIPRN and EfficientNet-B3 significantly outperforms the state-of-the-art patch-based method in both performance and efficiency.