Gang Yang

Prof. Gang Yang

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
11 October 2018 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
YZYunzhi Zhuge
Yunzhi Zhuge
GYGang Yang
Gang Yang
PZPingping Zhang
Pingping Zhang
HLHuchuan Lu
Huchuan Lu
Fully convolutional networks (FCN) has significantly improved the performance of many pixel-labeling tasks, such as semantic segmentation and depth estimation. However, it still remains non-trivial to thoroughly utilize the multi-level convolutional feature maps and boundary information for salient object detection. In this paper, we propose a novel FCN framework to integrate multi-level convolutional features recurrently with the guidance of object boundary information. First, a deep convolutional network is used to extract multi-level feature maps and separately aggregate them into multiple resolutions, which can be used to generate coarse saliency maps. Meanwhile, another boundary information extraction branch is proposed to generate boundary features. Finally, an attention-based feature fusion module is designed to fuse boundary information into salient regions to achieve accurate boundary inference and semantic enhancement. The final saliency maps are the combination of the predicted boundary maps and integrated saliency maps, which are more closer to the ground truths. Experiments and analysis on four large-scale benchmarks verify that our framework achieves new state-of-the-art results.

30 May 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
QHQing He
Qing He
XZXingze Zhang
Xingze Zhang
ZJZhiwen Ji
Zhiwen Ji
HGHan Gao
Han Gao
GYGang Yang
Gang Yang
Structured light vision fails to detect the high-temperature objects up to 1700 °C because the projected light patterns are drowned by the strong self-emitted radiation of the high-temperature objects. For this problem, signal enhancement and extraction of the projected laser light patterns are carried out in this article. Signal enhancement consists of two steps. The first step involves physical enhancement of the laser light signal by spectrum selective of the laser light source and filtering of the radiation by the optical filter. Theoretical analysis finds that, the working wavelength of the laser light source should be short, and the pass-bandwidth and the transmittance in the stopband of the optical filter should be small. The second step involves modulation of the projected light patterns. A novel modulation method is derived mathematically with optimal solutions. Based on the modulation method, strong radiations of the high-temperature objects are transformed into radiation noise with zero mean while half of the intensities of the structured light patterns are preserved. Interfered with the radiation noise, signal distribution of the structured light patterns is uncoupled from that of the radiation noise to extract the structured light patterns with desired confidence. The signal enhancement and extraction methods are applied and validated for slag level measurement in the converter in the steelmaking industry.

23 May 2023 in The Visual Computer
Verified
Journal Article
Closed access
PDF file
YZYunhua Zhang
Yunhua Zhang
HWHangxu Wang
Hangxu Wang
GYGang Yang
Gang Yang
JZJianhao Zhang
Jianhao Zhang
CGCongjin Gong
Congjin Gong
YWYutao Wang
Yutao Wang

25 November 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
DWDayang Wang
Dayang Wang
JSJiuxiang Sun
Jiuxiang Sun
YWYutao Wang
Yutao Wang
GYGang Yang
Gang Yang
ZZZengyan Zhu
Zengyan Zhu
ZXZhi Xie
Zhi Xie
In gas-solid two-phase flow, the situation that the moisture in the solid changes is often encountered. The varying and unknown moisture brings new challenges to the solid concentration measurement if the used measurement method is sensitive to the moisture. In this study, a new method which can eliminate the influence of moisture on the measurement of solid concentration in gas-solid flows is proposed. Firstly, the new combined sensors consisting of the microwave transmission sensor and the capacitance sensor are proposed and the measurement systems are designed. The microwave transmission sensor and the capacitance sensor are both sensitive to the moisture and the solid concentration, and they can acquire the information of the solid concentration and the moisture simultaneously. Then an effective decoupling method is proposed to derive the moisture and the solid concentration from the information acquired by the microwave transmission sensor and the capacitance sensor. Experiments are carried out to simulate the flow structure of roping flow to verify the proposed method. The results indicate that the influence of moisture on the measurement of solid concentration can be eliminated, and moisture independent measurement of solid concentration in gas-solid flows can be realized.

22 October 2021
Verified
Book Chapter
Closed access
PDF file
BZBoyi Zhou
Boyi Zhou
GYGang Yang
Gang Yang
XWXin Wan
Xin Wan
YWYutao Wang
Yutao Wang
CLChang Liu
Chang Liu
HWHangxu Wang
Hangxu Wang

26 March 2024 in Physics in Medicine & Biology
Verified
Journal Article
Closed access
YZYunhua Zhang
Yunhua Zhang
GYGang Yang
Gang Yang
CGCongjin Gong
Congjin Gong
JZJianhao Zhang
Jianhao Zhang
SWShuo Wang
Shuo Wang
YWYutao Wang
Yutao Wang
Objective. Accurate polyp segmentation from colo-noscopy images plays a crucial role in the early diagnosis and treatment of colorectal cancer. However, existing polyp segmentation methods are inevitably affected by various image noises, such as reflections, motion blur, and feces, which significantly affect the performance and generalization of the model. In addition, coupled with ambiguous boundaries between polyps and surrounding tissue, i.e. small inter-class differences, accurate polyp segmentation remains a challenging problem. Approach. To address these issues, we propose a novel two-stage polyp segmentation method that leverages a preprocessing sub-network (Pre-Net) and a dynamic uncertainty mining network (DUMNet) to improve the accuracy of polyp segmentation. Pre-Net identifies and filters out interference regions before feeding the colonoscopy images to the polyp segmentation network DUMNet. Considering the confusing polyp boundaries, DUMNet employs the uncertainty mining module (UMM) to dynamically focus on foreground, background, and uncertain regions based on different pixel confidences. UMM helps to mine and enhance more detailed context, leading to coarse-to-fine polyp segmentation and precise localization of polyp regions. Main results. We conduct experiments on five popular polyp segmentation benchmarks: ETIS, CVC-ClinicDB, CVC-ColonDB, EndoScene, and Kvasir. Our method achieves state-of-the-art performance. Furthermore, the proposed Pre-Net has strong portability and can improve the accuracy of existing polyp segmentation models. Significance. The proposed method improves polyp segmentation performance by eliminating interference and mining uncertain regions. This aids doctors in making precise and reduces the risk of colorectal cancer. Our code will be released at https://github.com/zyh5119232/DUMNet .