Bin Wang

Dr. Bin Wang


Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
17 August 2018 in Sensors
Verified
Journal Article
Open access
PDF file
WNWEI NIE
WEI NIE
ZXZhenyu Xu
Zhenyu Xu
RKRuiFeng Kan
RuiFeng Kan
JRJun Ruan
Jun Ruan
LYLu Yao
Lu Yao
YHYabai He
Yabai He
We have proposed a sensor for real-time and online measurement of dew/frost point temperature using tunable diode laser absorption spectroscopy (TDLAS) technique. Initial experiments have demonstrated its feasibility and technical advantages in comparison to a chilled mirror hygrometer (CMH). The TDLAS sensor we developed has a dew/frost point temperature range from −93 °C to + 14.5 °C, with a measurement uncertainly of less than 2%, and a response time of about 0.8 s, which is much faster than that of the chilled mirror hygrometer (ranging from several minutes to several hours). A TDLAS-based dew/frost point sensor has many advantages, such as rapid and continuous measurements, low frost point temperature sensing, high accuracy, and non-intrusiveness. Such a sensor would be useful for dew/frost point temperature determinations in various applications. In a cryogenic wind tunnel, real-time dew/frost point temperature measurements are helpful in preventing the formation of condensed liquid and ice, which can affect the model geometry and lead to unreliable test data.

1 January 2012 in Robot
Verified
Journal Article
Closed access
BWBin Wang
Bin Wang
YWYuanyuan Wang
Yuanyuan Wang
WXWenhua Xiao
Wenhua Xiao
WWWei Wang
Wei Wang
MZMaojun Zhang
Maojun Zhang

1 January 2013 in The Scientific World Journal
Verified
Journal Article
Open access
PDF file
BWBin Wang
Bin Wang
YLYu Liu
Yu Liu
WWWei Wang
Wei Wang
WXWei Xu
Wei Xu
MZMaojun Zhang
Maojun Zhang
We propose a Multiscale Locality‐Constrained Spatiotemporal Coding (MLSC) method to improve the traditional bag of features (BoF) algorithm which ignores the spatiotemporal relationship of local features for human action recognition in video. To model this spatiotemporal relationship, MLSC involves the spatiotemporal position of local feature into feature coding processing. It projects local features into a sub space‐time‐volume (sub‐STV) and encodes them with a locality‐constrained linear coding. A group of sub‐STV features obtained from one video with MLSC and max‐pooling are used to classify this video. In classification stage, the Locality‐Constrained Group Sparse Representation (LGSR) is adopted to utilize the intrinsic group information of these sub‐STV features. The experimental results on KTH, Weizmann, and UCF sports datasets show that our method achieves better performance than the competing local spatiotemporal feature‐based human action recognition methods.

13 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
RQRui Qin
Rui Qin
BWBin Wang
Bin Wang
YTYu-Wing Tai
Yu-Wing Tai
Text image super-resolution is a unique and important task to enhance readability of text images to humans. It is widely used as pre-processing in scene text recognition. However, due to the complex degradation in natural scenes, recovering high-resolution texts from the low-resolution inputs is ambiguous and challenging. Existing methods mainly leverage deep neural networks trained with pixel-wise losses designed for natural image reconstruction, which ignore the unique character characteristics of texts. A few works proposed content-based losses. However, they only focus on text recognizers' accuracy, while the reconstructed images may still be ambiguous to humans. Further, they often have weak generalizability to handle cross languages. To this end, we present TATSR, a Text-Aware Text Super-Resolution framework, which effectively learns the unique text characteristics using Criss-Cross Transformer Blocks (CCTBs) and a novel Content Perceptual (CP) Loss. The CCTB extracts vertical and horizontal content information from text images by two orthogonal transformers, respectively. The CP Loss supervises the text reconstruction with content semantics by multi-scale text recognition features, which effectively incorporates content awareness into the framework. Extensive experiments on various language datasets demonstrate that TATSR outperforms state-of-the-art methods in terms of both recognition accuracy and human perception.

8 October 2023
Verified
Conference Paper
Closed access
HYHaidong Yu
Haidong Yu
YLYang Liu
Yang Liu
YZYuhang Zhang
Yuhang Zhang
BWBin Wang
Bin Wang
SZShidong Zhang
Shidong Zhang
MHMin Huang
Min Huang
The existing symmetric component analysis methods cannot provide accurate results and cannot model networks under unbalanced conditions. This article proposes an improved algorithm for calculating the power flow of unbalanced distribution networks containing photovoltaic power based on the forward and backward sweep method. This algorithm has good adaptability to the power flow calculation of distribution networks containing photovoltaic systems. This paper comprehensively analyzes the power flow calculation in three-phase unbalanced distribution networks containing photovoltaic power generation, and points out that the forward and backward sweep method has significant advantages in calculating power flow in distribution networks based on the essential characteristics of each method. A power flow calculation method for unbalanced distribution networks containing new energy sources such as photovoltaic is proposed based on the forward and backward sweep algorithm. The effectiveness of the proposed method is demonstrated through numerical simulations on a test distribution network that includes distributed generation. Results show the improved accuracy and efficiency of the proposed method.

1 January 2026 in Journal of Applied Optics
Verified
Journal Article
Closed access
PDF file
BHBaolin Hou
Baolin Hou
西南西南科技大学信息与控制工程学院,四川绵阳621010
西南科技大学信息与控制工程学院,四川绵阳621010
CWChuandiao Wang
Chuandiao Wang
HYHongjun Yan
Hongjun Yan
DHDubo He
Dubo He
MPMianyang 622652 No. 63823 Unit Of Pla
Mianyang 622652 No. 63823 Unit Of Pla

狙击瞄准点轨迹视觉测量系统是一种应用于现代化狙击训练领域的高精度光学测量装置,针对该系统高分辨率图像处理延迟与户外强光导致的轨迹定位困难问题,提出一种基于自适应阈值感兴趣区域(region of interest, ROI)投影法的瞄准点质心快速定位算法,并基于现场可编程门阵列(field programmable gate array, FPGA)平台硬件实现。该算法通过分析光斑像素个数在图像中的占比,结合相关场景参数动态计算ROI提取的自适应阈值,实现了ROI区域的高效精准提取,大幅减少了计算量。实验结果表明,对于2 448×2 048分辨率的图像,所提算法将处理数据量减少了98.7%。同时,自适应阈值机制有效克服了户外环境光照变化的影响,在不同射击场景下均能稳定提取质心,显著提升了系统的实时性与鲁棒性。