Yi Liu

Prof. Dr. Yi Liu

Xiangtan University, Xiangtan, Hunan, China
orcid

Research Focus & Metrics

Academic Career Length

29Years (1998-Present)

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

Representative Publications

View All Publications
6 February 2020 in Sensors
Verified
Journal Article
Open access
PDF file
SWSonglai Wang
Songlai Wang
WWWanrong Wu
Wanrong Wu
SYShen Yiping
Shen Yiping
YLYi Liu
Yi Liu
SJShuai Jiang
Shuai Jiang
The tomography technique is an effective way to quantitatively evaluate damage from reconstruction imaging in structure health monitoring (SHM). The reconstruction algorithm for the probabilistic inspection of damage (RAPID) algorithm based on the signal difference coefficient (SDC) feature is a promising approach due to its superior performance. This paper focuses on the influence of different patterns of PZT (Lead Zirconate Titanate) sensor array configurations, i.e., the circular, square, and parallel array, on reconstruction image qualities for evaluating hole and crack damage. Variable shape parameters are applied to account for the unequal damage distances of different actuator-sensor pairs. Considering the directionality scattering fields of cracks, the angular scattering pattern of the SDC values are studied by simulation. The SDC variations for different groups of sensing paths at the same actuator are applied to predict the crack orientation. An improved RAPID algorithm is proposed by defining an additional SDC value of 1 in the path along the predicted crack orientation, which is determined by the point of the actuator causing the minimal SDC variation and the center point of the initial reconstruction image of the crack. The results show that the improved RAPID algorithm is effective for the evaluation of crack damage. Reconstruction image qualities with three PZT sensor array configurations for both holes and cracks are compared. The research is significant for selecting the PZT sensor array configuration in SHM.

30 August 2014 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Closed access
PDF file
YLYi Liu
Yi Liu
SLShiQi Li
ShiQi Li
Junfeng WangJunfeng Wang
Junfeng Wang
HZHongmei Zeng
Hongmei Zeng
JLJiPing Lu
JiPing Lu

27 November 2020 in Sensors
Verified
Journal Article
Open access
PDF file
CXChi Xu
Chi Xu
JCJiale Chen
Jiale Chen
MYMengyang Yao
Mengyang Yao
JZJun Zhou
Jun Zhou
LZLijun Zhang
Lijun Zhang
YLYi Liu
Yi Liu
6DoF object pose estimation is a foundation for many important applications, such as robotic grasping, automatic driving, and so on. However, it is very challenging to estimate 6DoF pose of transparent object which is commonly seen in our daily life, because the optical characteristics of transparent material lead to significant depth error which results in false estimation. To solve this problem, a two-stage approach is proposed to estimate 6DoF pose of transparent object from a single RGB-D image. In the first stage, the influence of the depth error is eliminated by transparent segmentation, surface normal recovering, and RANSAC plane estimation. In the second stage, an extended point-cloud representation is presented to accurately and efficiently estimate object pose. As far as we know, it is the first deep learning based approach which focuses on 6DoF pose estimation of transparent objects from a single RGB-D image. Experimental results show that the proposed approach can effectively estimate 6DoF pose of transparent object, and it out-performs the state-of-the-art baselines by a large margin.

1 July 2020
Verified
Conference Paper
Closed access
JCJiale Chen
Jiale Chen
LZLijun Zhang
Lijun Zhang
YLYi Liu
Yi Liu
CXChi Xu
Chi Xu

5 November 2013 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Closed access
PDF file
SLShiQi Li
ShiQi Li
YLYi Liu
Yi Liu
JWJunFeng Wang
JunFeng Wang
HZHongMei Zeng
HongMei Zeng

7 November 2020 in Sensors
Verified
Journal Article
Open access
PDF file
CXChi Xu
Chi Xu
JZJun Zhou
Jun Zhou
WCWendi Cai
Wendi Cai
JYjiang yunkai
jiang yunkai
YLYongbo Li
Yongbo Li
YLYi Liu
Yi Liu
Three-dimensional hand detection from a single RGB-D image is an important technology which supports many useful applications. Practically, it is challenging to robustly detect human hands in unconstrained environments because the RGB-D channels can be affected by many uncontrollable factors, such as light changes. To tackle this problem, we propose a 3D hand detection approach which improves the robustness and accuracy by adaptively fusing the complementary features extracted from the RGB-D channels. Using the fused RGB-D feature, the 2D bounding boxes of hands are detected first, and then the 3D locations along the z-axis are estimated through a cascaded network. Furthermore, we represent a challenging RGB-D hand detection dataset collected in unconstrained environments. Different from previous works which primarily rely on either the RGB or D channel, we adaptively fuse the RGB-D channels for hand detection. Specifically, evaluation results show that the D-channel is crucial for hand detection in unconstrained environments. Our RGB-D fusion-based approach significantly improves the hand detection accuracy from 69.1 to 74.1 comparing to one of the most state-of-the-art RGB-based hand detectors. The existing RGB- or D-based methods are unstable in unseen lighting conditions: in dark conditions, the accuracy of the RGB-based method significantly drops to 48.9, and in back-light conditions, the accuracy of the D-based method dramatically drops to 28.3. Compared with these methods, our RGB-D fusion based approach is much more robust without accuracy degrading, and our detection results are 62.5 and 65.9, respectively, in these two extreme lighting conditions for accuracy.