Yi An

Prof. Yi An

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2022 in Information Fusion
Verified
Journal Article
Closed access
SQSen Qiu
Sen Qiu
HZHongkai Zhao
Hongkai Zhao
NJNan Jiang
Nan Jiang
ZWZhelong Wang
Zhelong Wang
LLLong Liu
Long Liu
GFGiancarlo Fortino
Giancarlo Fortino

10 August 2023 in Expert Systems with Applications
Verified
Journal Article
Closed access
XLXin Li
Xin Li
LWLei Wang
Lei Wang
YAYi An
Yi An
QHQi-Li Huang
Qi-Li Huang
YCYunhao Cui
Yunhao Cui
Huosheng HuHuosheng Hu
Huosheng Hu

28 April 2022 in Cognitive Computation
Verified
Journal Article
Open access
PDF file
YAYi An
Yi An
JSJin Shi
Jin Shi
DGDongbing Gu
Dongbing Gu
QLQiang Liu
Qiang Liu
Recently, deep learning techniques have been applied to solve visual or light detection and ranging (LiDAR) simultaneous localization and mapping (SLAM) problems. Supervised deep learning SLAM methods need ground truth data for training, but collecting such data is costly and labour-intensive. Unsupervised training strategies have been adopted by some visual or LiDAR SLAM methods. However, these methods only exploit the potential of single-sensor modalities, which do not take the complementary advantages of LiDAR and visual data. In this paper, we propose a novel unsupervised multi-channel visual-LiDAR SLAM method (MVL-SLAM) which can fuse visual and LiDAR data together. Our SLAM system consists of an unsupervised multi-channel visual-LiDAR odometry (MVLO) component, a deep learning–based loop closure detection component, and a 3D mapping component. The visual-LiDAR odometry component adopts a multi-channel recurrent convolutional neural network (RCNN). Its input consists of front, left, and right view depth images generated from $$360^{\circ }$$ 360 ∘ 3D LiDAR data and RGB images. We use the features from a deep convolutional neural network (CNN) for the loop closure detection component. Our SLAM method does not require ground truth data for training and can directly construct environmental 3D maps from the 3D mapping component. Experiments conducted on the KITTI odometry dataset have shown the rotation and translation errors are lower than some of the other unsupervised methods, including UnMono, SfmLearner, DeepSLAM, and UnDeepVO. Experimental results show that our methods have good performance. By fusing visual and LiDAR data, MVL-SLAM has higher accuracy and robustness of the pose estimation compared with other single-modal SLAM systems.

30 July 2020 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YCYunhao Cui
Yunhao Cui
YAYi An
Yi An
WSWei Sun
Wei Sun
Huosheng HuHuosheng Hu
Huosheng Hu
XSXueguan Song
Xueguan Song
Research on classification and segmentation of 3D point clouds using deep learning methods has become a hot topic in emerging applications such as autonomous driving, augmented reality, and indoor navigation. However, as the complexity of the network structures increases, the computational efficiency reduces, which affects the practical applications of these methods. In addition, prior researchers mostly seek to enhance the quality of spatial encodings while the channel relationships are ignored. It makes the feature learning of point clouds insufficient, which will reduce the accuracy of classification and segmentation. In this paper, a lightweight attention module (LAM) is proposed to improve the computational efficiency and accuracy at the same time by adopting a novel convolution mode and introducing a new attention mechanism based on channel-wise statistical features. As the submodules of LAM, the lightweight module and attention module can also be used independently to focus on improving the computational efficiency and accuracy respectively according to the actual applications. LAM and its submodules can be easily integrated into state-of-the-art deep learning methods on classification and segmentation of 3D point clouds. The experimental results show that the proposed modules have good performance on benchmark datasets.

3 January 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
XHXing Hu
Xing Hu
YAYi An
Yi An
CSCheng Shao
Cheng Shao
Huosheng HuHuosheng Hu
Huosheng Hu
Semantic segmentation of panoramic images plays a key role in many applications, such as security monitoring and autonomous driving. With the rapid development of deep learning, some deep networks are developed to segment panoramic images semantically. However, these networks don’t have the special modules to correct the image distortion of panoramic images according to the distortion principle, which makes feature extraction unreasonable during the convolution because of the image distortion. This article proposes a novel semantic segmentation network for panoramic images of outdoor scenes based on the distortion convolution. The network contains an encoder and a decoder. The encoder consists of a distortion convolutional module (DCM), a residual network, and an atrous spatial pyramid pooling (ASPP). The DCM is developed to correct the image distortion according to the image-forming principle. In the decoder, a deep feature aggregation network (DFAN) is designed to fully fuse low-level features with high-level features. The proposed network introduces the DCM and DFAN into the semantic segmentation of panoramic images, which improves the segmentation accuracy. The experiments demonstrate that the proposed network has good performance for different outdoor scenes and plays an important role in measurement applications.

25 February 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YAYi An
Yi An
WLWusong Liu
Wusong Liu
YCYunhao Cui
Yunhao Cui
JWJinyu Wang
Jinyu Wang
XLXiusheng Li
Xiusheng Li
Huosheng HuHuosheng Hu
Huosheng Hu
Ground segmentation of 3-D point clouds acquired by laser sensors plays a crucial role in many applications, such as environment perception, scene understanding, and environment modeling. This article proposes a novel multilevel framework of the ground segmentation for 3-D point clouds of outdoor scenes based on shape analysis. The local shape of the 3-D point cloud of an outdoor scene is captured by principal component analysis. Then, the 3-D point cloud is classified into scattered points, linear points, and surface points. The unit normal vectors of the surface points are calculated and mapped into a unit ball. On the normal ball, the normal vectors are clustered, which segments the surface points into some surface regions correspondingly. Each surface region is further divided into several surface fragments according to point positions. The surface fragment that meets the ground conditions is regarded as a part of the initial ground. Finally, the ground is obtained by using the 2-D Gaussian process regression. The proposed method explores both local shapes and multilevel structures of outdoor scenes and constructs a probabilistic ground model in order to improve the accuracy and adaptivity of ground segmentation. Experiment results demonstrate that the proposed method has good performance.