TY - JOUR
T1 - MAFNet: Segmentation of Road Potholes With Multimodal Attention Fusion Network for Autonomous Vehicles
AU - Feng, Zhen
AU - Guo, Yanning
AU - Liang, Qing
AU - Bhutta, M. Usman Maqbool
AU - Wang, Hengli
AU - Liu, Ming
AU - Sun, Yuxiang
N1 - Publisher Copyright:
© 1963-2012 IEEE.
PY - 2022
Y1 - 2022
N2 - Road potholes can cause discomforts to passengers and even traffic accidents to vehicles. Accurate segmentation of road potholes is an important capability for autonomous vehicles to ensure safe driving. Some methods on road-pothole segmentation use single-modal data (i.e., RGB images). The main challenge faced by these methods is that the visual appearance of road potholes is often close to road areas, making these networks difficult to distinguish them. Recent methods resort to fusing RGB images with depth/disparity images for pothole segmentation. However, their performance is still not satisfactory in real-world applications. To achieve superior results, this article proposes a novel data fusion network for road-pothole segmentation, where a channel attention fusion module and a dual attention fusion (DAF) module are designed to hierarchically fuse the RGB and disparity data. We evaluate our proposed network using a public dataset, and the experimental results demonstrate the superiority over the state-of-the-art networks.
AB - Road potholes can cause discomforts to passengers and even traffic accidents to vehicles. Accurate segmentation of road potholes is an important capability for autonomous vehicles to ensure safe driving. Some methods on road-pothole segmentation use single-modal data (i.e., RGB images). The main challenge faced by these methods is that the visual appearance of road potholes is often close to road areas, making these networks difficult to distinguish them. Recent methods resort to fusing RGB images with depth/disparity images for pothole segmentation. However, their performance is still not satisfactory in real-world applications. To achieve superior results, this article proposes a novel data fusion network for road-pothole segmentation, where a channel attention fusion module and a dual attention fusion (DAF) module are designed to hierarchically fuse the RGB and disparity data. We evaluate our proposed network using a public dataset, and the experimental results demonstrate the superiority over the state-of-the-art networks.
KW - Attention mechanism
KW - autonomous vehicles
KW - RGB-disparity fusion
KW - road potholes
KW - semantic segmentation
UR - http://www.scopus.com/inward/record.url?scp=85137589545&partnerID=8YFLogxK
U2 - 10.1109/TIM.2022.3200100
DO - 10.1109/TIM.2022.3200100
M3 - Journal article
AN - SCOPUS:85137589545
VL - 71
JO - IEEE Transactions on Instrumentation and Measurement
JF - IEEE Transactions on Instrumentation and Measurement
SN - 0018-9456
M1 - 3523712
ER -