RHCrackNet: Refined Hierarchical Feature Fusion and Enhancement Network for Pixel-Level Pavement Anomaly Detection

RHCrackNet: Refined Hierarchical Feature Fusion and Enhancement Network for Pixel-Level Pavement Anomaly Detection

Accurate and automatic detection of pavement anomaly is critical for damage assessment and pavements maintainence. While existing Convolutional Neural Network (CNN) approaches have achieved high performance, their robustness to texture noise is limited, and the completeness of detected pixel-level c...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenjing Liu, Zhenhua Li, Ji Wang, Qingjie Lu
Format: Article
Language:English
Published: Tsinghua University Press 2025-06-01
Series:Big Data Mining and Analytics
Subjects:
convolutional neural network (cnn)
anomaly detection
feature fusion
feature enhancement
non-local attention
Online Access:https://www.sciopen.com/article/10.26599/BDMA.2024.9020051
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items

Similar Items