Qinghua Sheng

Mr. Qinghua Sheng

School of Electronic and Information, Hangzhou Dianzi University, No.2 Avenue, Baiyang Street, Jianggan District, Hangzhou City, Zhejiang
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
21 October 2020 in Sensors
Verified
Journal Article
Open access
PDF file
Zhu LiZhu Li
Zhu Li
Yisha ZhouYisha Zhou
Yisha Zhou
Qinghua ShengQinghua Sheng
Qinghua Sheng
Kunjian ChenKunjian Chen
Kunjian Chen
JHJian Huang
Jian Huang
Automatic reading of pointer meters is of great significance for efficient measurement of industrial meters. However, existing algorithms are defective in the accuracy and robustness to illumination shooting angle when detecting various pointer meters. Hence, a novel algorithm for adaptive detection of different pointer meters was presented. Above all, deep learning was introduced to detect and recognize scale value text in the meter dial. Then, the image was rectified and meter center was determined based on text coordinate. Next, the circular arc scale region was transformed into a linear scale region by polar transform, and the horizontal positions of pointer and scale line were obtained based on secondary search in the expanded graph. Finally, the distance method was used to read the scale region where the pointer is located. Test results showed that the algorithm proposed in this paper has higher accuracy and robustness in detecting different types of meters.

14 June 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
Qinghua ShengQinghua Sheng
Qinghua Sheng
Hongzhao ChenHongzhao Chen
Hongzhao Chen
CLChangcai Lai
Changcai Lai
YLYuanyuan Liu
Yuanyuan Liu
XHXiaofeng Huang
Xiaofeng Huang
HYHaibing Yin
Haibing Yin
The latest video coding standard, versatile video coding (VVC), was developed to achieve higher video compression efficiency and support more media applications than its predecessor, high-efficiency video coding (HEVC). To address nontranslational motion, such as rotation and zooming, affine motion compensation has been employed in VVC during interframe prediction. However, the complexity increases significantly due to a large number of linear equation solving steps during affine motion estimation (AME). To address the problem, this paper proposes a fast linear equation solving algorithm and an accompanying pipelined hardware architecture design. To the best of our knowledge, our work is the first attempt to address the hardware architecture design of the linear equation solving algorithm in affine mode. First, an integer-based division-free algorithm (I-DFA) is proposed to achieve fast equation solving. Then, a novel dynamic scaling algorithm is proposed to compensate for integer computation errors due to overflow problems. Finally, a pipelined and interleaved hardware architecture is proposed to minimize the number of iteration clock cycles and improve the throughput. The proposed algorithm achieves average time savings of 5.3% and 5.7% with only 0.03% and 0.07% increase in the Bjøntegaard delta bit rate (BD-BR) under low-delay P (LDP) and random access (RA) configurations, respectively. The proposed hardware architecture can solve 16.7M six-parameter affine systems of linear equations per second under a working frequency of 100MHz, which represents a 21x improvement compared to the existing methods.

12 June 2024 in Journal of Visual Communication and Image Representation
Verified
Journal Article
Closed access
Qinghua ShengQinghua Sheng
Qinghua Sheng
RPRui Pan
Rui Pan
JCJunyu Chen
Junyu Chen
CLChangcai Lai
Changcai Lai
YLYuanyuan Liu
Yuanyuan Liu
CYChenggang Yan
Chenggang Yan

2 December 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Qinghua ShengQinghua Sheng
Qinghua Sheng
HSHaixiang Sheng
Haixiang Sheng
鹏高鹏 高
鹏 高
Zhu LiZhu Li
Zhu Li
HYHaibing Yin
Haibing Yin
Currently, the target detection based on convolutional neural network plays an important role in image recognition, speech recognition and other fields. However, the current network model features a complex structure, a huge number of parameters and resources. These conditions make it difficult to apply in embedded devices with limited computational capabilities and extreme sensitivity to power consumption. In this regard, the application scenarios of deep learning are limited. This paper proposes a real-time detection scheme for cook assistant overalls based on the Hi3559A embedded processor. With YOLOv3 as the benchmark network, this scheme fully mobilizes the hardware acceleration resources through the network model optimization and the parallel processing technology of the processor, and improves the network reasoning speed, so that the embedded device can complete the task of real-time detection on the local device. The experimental results show that through the purposeful cropping, segmentation and in-depth optimization of the neural network according to the specific processor, the neural network can recognize the image accurately. In an application environment where the power consumption is only 5.5 W, the recognition speed of the neural network on the embedded end is increased to about 28 frames (the design requirement was to achieve a recognition speed of 25 frames or more), so that the optimized network can be effectively applied in the back kitchen overalls identification scene.

14 September 2025 in Sensors
Verified
Journal Article
Open access
PDF file
RMRuiqi Ma
Ruiqi Ma
Qinghua ShengQinghua Sheng
Qinghua Sheng
YCYulu Chen
Yulu Chen
ZTZehao Tao
Zehao Tao
SWSheng Wang
Sheng Wang
Shuhan ChenShuhan Chen
Shuhan Chen
Multi Small-Object Tracking (MSOT) is crucial for drone inspection and intelligent monitoring, yet traditional Multiple-object Tracking (MOT) methods perform poorly in such scenarios. The reasons include the following: small targets have low resolution and sparse features, leading to high missed detection rates; frequent occlusion and motion blur in dense scenes cause trajectory interruption and identity switches. To address these issues, an MSOT method combining dual motion modeling and dynamic Region of Interest (ROI) detection is proposed. The dual motion framework integrates Kalman filtering and optical flow through dynamic weighting to optimize target state estimation. The Kalman filter-guided dynamic ROI mechanism, combined with multi-feature fusion, enables trajectory recovery when targets are lost. Experiments on the VisDrone-MOT and UAVDT datasets show that this method outperforms mainstream algorithms in core metrics such as MOTA and HOTA, with better trajectory continuity and identity consistency while maintaining good real-time performance.

Verified
Journal Article
Open access
PDF file
JXJing Xiao
Jing Xiao
Jiawang ChenJiawang Chen
Jiawang Chen
ZTZhenwei Tian
Zhenwei Tian
HZHai Zhu
Hai Zhu
CWChunsheng Wang
Chunsheng Wang
JFJiasong Fang
Jiasong Fang
The multi-net visible fidelity zooplankton collector is designed to obtain near-bottom fidelity zooplankton. The collector is sent to the designated sampling location based on the information provided by the camera and altimeter. The host computer sends instructions to control the opening of the net port for sample collection and closing of the sampling cylinder cover after sampling. The collector contains three trawls so that three samples can be collected for each test, and environmental parameters can be collected simultaneously. After sampling, The sample maintains its fidelity, that is, maintaining the temperature and pressure of the seabed sample after sampling. Two experiments were carried out in the Western Pacific, and six bottles of zooplankton samples were successfully obtained. The development of a multi-net visible zooplankton collector is of great significance for the collection of near-bottom zooplankton.