YSYuan-He Shan

Yuan-He Shan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yuan-He Shan has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Vehicle Visual Perception Under Low Visibility Road Environments Based on AoP&DoP Multi-Polarization Parameter Characterization

    by Yuanhe Shan, Huifeng Wang, Hao Du, Haonan Peng, Yueyuan Guan, He Huang, Xiaowei Zhang, Yunmei Jiao, Chengyan Zhang, Zefeng Pan, et al.

    Vehicle visual perception is essential for safe autonomous driving, especially in challenging low-visibility conditions. Polarimetric imaging has shown enhanced perception by improving target-background contrast and reducing glare. However, current research in polarimetric imaging for autonomous driving largely focuses on singular use of polarimetric features. Exploiting polarimetric information to enhance vehicle visual perception in low-visibility scenarios remains a critical challenge. This paper addresses this challenge by integrating multiple polarimetric parameter characterization with a deep learning model for semantic segmentation visual perception task, which is called TransWNet. The model combines Convolutional Neural Networks (CNN) and Transformer architectures, extracting features and contextual information of both Degree of Polarization (DoP) and Angle of Polarization (AoP) comprehensively during the encoding phase. In the decoding phase, it incorporates skip connections to effectively retain multimodal polarimetric information across deep and shallow features, generating output through feature fusion. To the best of our knowledge, this is the first work that jointly exploits DoP and AoP for vehicle scene understanding in degraded visibility. Experimental results demonstrate that TransWNet, by effectively leveraging multimodal polarimetric information, achieves significantly better performance in semantic segmentation of low-visibility traffic scenes, with marked improvements in mIoU, mPA, and Accuracy over all single-feature baselines. Compared with the baseline method, TransWNet improves the Accuracy by 3.44%.


  • Automated Intelligent Detection of Defects on Bridge Piers Using a Climbing Operation Robot and Vision Mamba

    by Hao Du, Hui-Feng Wang, Yuan-He Shan, Ze-Feng Pan, Yun-Mei Jiao, Rong Gao, He Huang

    Superficial defect detection on bridge piers is crucial for assessing the health condition of bridges. A novel ring vision acquisition system based on a climbing operation robot is proposed to aim at the limitations of existing Unmanned Aerial Vehicles (UAVs) and wall-climbing robots. In addition, to address the quadratic computational complexity of the Transformer-based model, a Vision Mamba-based defects detection model, Piers Defects-Mamba (PD-Mamba), is proposed, which contributes to more efficient inferencing the high-resolution defects images. Finally, field experiments were performed at Shouchun Bridge in Anhui Province, China. The results demonstrated that the robotic system could automate acquiring high-precision visual images of bridge piers’ superficial defects. The proposed PD-Mamba achieves 77.97% mean Intersection over Union (mIoU), 88.81% mean Precision (mP), 85.42% mean Recall (mR), and 87.05% mean F1-score (mF1) on the multi-category bridge pier defect dataset, exhibiting state-of-the-art (SOTA) performance, and has global modelling capability and linear computational complexity, which achieves accurate and efficient detection of bridge piers’ superficial defects. It is important to assess the health condition of the bridge.


  • Low-Visibility Vehicle-Road Environment Perception Based on the Multi-Modal Visual Features Fusion of Polarization and Infrared

    by Hui-Feng Wang, Yun-Mei Jiao, Ting Hao, Yuan-He Shan, Shang-Zhen Song, He Huang

    As a key component of the automatic driving assistant system, vehicle-road environment perception technology is the basis of decision-making and the guarantee of safe driving. However, the existing vehicle-road environment perception technology based on vision mainly focus on the conditions of good illumination and weather and rely on visible light imaging equipment, which is not highly adaptable to special environments. In this paper, the key technologies of low-visibility vehicle-road environment perception are deeply studied by combining multi-mode visual imaging and deep learning, and a model of Multi-Branch Input Encoding-Decoding Network (MBINEDN) is proposed. In this model, the polarized degree image and infrared image of the same road scene are input simultaneously in the coding stage, and two branch networks are used to extract the multi-mode features. The lightweight network MobileNetV2 is used as the feature extractor to reduce the amount of model parameters, so as to retain the polarization and infrared feature of the image to the maximum extent. Finally, the two are combined and output in the decoding stage. Experiments show that using MBINEDN model to process two images can effectively improve the segmentation effect. At the same time, it shows that the effect of vehicle-road environment semantic segmentation based on multi-modal visual features is better than that of single modal features. Therefore, the application of multi-mode visual images to the segmentation of low-visibility vehicle-road scenes can provide a strong guarantee for the visual perception technology of vehicle safety driving assistance system.


  • Vehicle-Road Environment Perception Under Low-Visibility Condition Based on Polarization Features via Deep Learning

    by Hui-Feng Wang, Yuan-He Shan, Ting Hao, Xiang-Mo Zhao, Shang-Zhen Song, He Huang, Jia-Jia Zhang

    Visual perception system is the key component of safety driving assistance and unmanned driving systems, and the perceptive performance of which will directly affect the running safety. There are various perception algorithms for the visual system, especially in recent years, deep learning algorithms are adopted with increasing popularity among them. However, the majority of existing works mainly focuses on daytime scenes with favorable illumination and weather conditions, and relies on visible light with intensity imaging equipment. This paper is based on polarization features acquired by deep learning methods, attempting to address the problems about vehicle-road environment perception in Low-Visibility Condition. Polarization is one of the essential properties of matter, here we propose a new method by studying and analyzing the transmission characteristics of the target’s polarization information. In the proposed method, the polarization features of vehicle-road environment are first acquired by a kind of three-channel polarization imaging device, then, fused together with an intensity image, and finally followed by a semantic segmentation operation by deep networks. The experimental results clearly demonstrate that the effect of perception based on polarization features via deep learning are greatly improved compared with intensity imaging, especially in low illumination and severe weather conditions. It is of great value for environmental robustness of visual perception system and further traffic safety.