Road extraction based on high-resolution remote sensing images has become a major research hotspot. However, the traditional pixel-level semantic segmentation method lacks road continuity details, resulting in road extractions containing many fragmented road segments and, thus, incorrect segmentation results. To address these problems, we propose the EfficientUNet multitask joint learning (EUNetMTL) model – an end-to-end model based on semantic segmentation and orientation learning. Firstly, EUNetMTL uses an encoder–decoder network structure based on EfficientNet-B4 for feature extraction, which provides it with superior feature extraction accuracy. Secondly, the decoder is modified by adding dilated convolution to enlarge the receptive field. Finally, the model incorporates an orientation learning decoding branch, which solves the discontinuity problem in road extraction by sharing the encoding with the segmentation task branch. The results of experiments conducted on the DeepGlobe and SpaceNet road datasets show that the proposed model achieves high-quality segmentation results that are superior to those of current state-of-the-art methods. [ABSTRACT FROM AUTHOR]