Qinghua Sheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Qinghua Sheng has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Haibing Yin
Hangzhou Dianzi University
5 shared publications - Ruiqi Ma
The School of Electronics and Information, Hangzhou Dianzi University, Hangzhou 310018, China
3 shared publications - Zehao Tao
Hangzhou Dianzi University
3 shared publications - Changcai Lai
School of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou, China
2 shared publications - Jian Huang
School of Electronics and Information, Hangzhou Dianzi University, Hangzhou, China
2 shared publications - Jiawang Chen
Institute of Ocean Engineering and Technology, Ocean College, Zhejiang University, Zhoushan 316021, China
2 shared publications
Latest Publications
- Open Access
- 29 May 2026
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 14 (11) , 1011
Design of an Integrated Online Testing System for Pressure-Core Characteristics Using an Improved EMD–Wavelet Denoising Algorithm
Natural gas hydrates are regarded as a vital strategic energy resource for the future owing to their high energy density and clean combustion characteristics. To facilitate research into the physical and mechanical properties of pressure-maintained hydrate samples, this paper presents an integrated multi-parameter online analysis system capable of rapidly measuring the P-wave velocity, electrical resistivity, thermal conductivity, and shear strength of core samples under pressure-maintaining conditions. The system comprises hardware acquisition boards based on ZYNQ and ARM platforms, specialized measurement probes, and comprehensive data acquisition and analysis software. To mitigate the susceptibility of P-wave signals to noise interference, an improved denoising algorithm combining Empirical Mode Decomposition (EMD) and wavelet thresholding is proposed. By employing autocorrelation function analysis, the algorithm identifies the transition boundary between noise-dominated and signal-dominated Intrinsic Mode Functions (IMFs), subsequently applying wavelet soft-thresholding to the noise-dominant components. Experimental results demonstrate that the proposed algorithm achieves a superior signal-to-noise ratio (SNR) compared to traditional EMD methods, particularly under low SNR conditions. System validation indicates measurement accuracies of 3.2% for P-wave velocity at 20 °C, 1.76% for electrical resistivity at 25 °C, and within 7% for both thermal conductivity and shear strength. Furthermore, sea trials conducted aboard the “HAIYANG SHIYOU 708” drilling vessel confirm that the system operates stably and effectively fulfills the requirements for deep-sea core parameter characterization.
- 29 May 2026
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 14 (11) , 1011
Open AccessDesign of an Integrated Online Testing System for Pressure-Core Characteristics Using an Improved EMD–Wavelet Denoising Algorithm
Natural gas hydrates are regarded as a vital strategic energy resource for the future owing to their high energy density and clean combustion characteristics. To facilitate research into the physical and mechanical properties of pressure-maintained hydrate samples, this paper presents an integrated multi-parameter online analysis system capable of rapidly measuring the P-wave velocity, electrical resistivity, thermal conductivity, and shear strength of core samples under pressure-maintaining conditions. The system comprises hardware acquisition boards based on ZYNQ and ARM platforms, specialized measurement probes, and comprehensive data acquisition and analysis software. To mitigate the susceptibility of P-wave signals to noise interference, an improved denoising algorithm combining Empirical Mode Decomposition (EMD) and wavelet thresholding is proposed. By employing autocorrelation function analysis, the algorithm identifies the transition boundary between noise-dominated and signal-dominated Intrinsic Mode Functions (IMFs), subsequently applying wavelet soft-thresholding to the noise-dominant components. Experimental results demonstrate that the proposed algorithm achieves a superior signal-to-noise ratio (SNR) compared to traditional EMD methods, particularly under low SNR conditions. System validation indicates measurement accuracies of 3.2% for P-wave velocity at 20 °C, 1.76% for electrical resistivity at 25 °C, and within 7% for both thermal conductivity and shear strength. Furthermore, sea trials conducted aboard the “HAIYANG SHIYOU 708” drilling vessel confirm that the system operates stably and effectively fulfills the requirements for deep-sea core parameter characterization.
- Open Access
- 11 February 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (4) , 561
TASONet: A Spatial Enhancement and Temporal Modeling Framework for UAV Small Object Tracking
Multi object tracking (MOT) in UAV imagery is challenged by weak feature representation of small objects due to limited resolution, which leads to frequent missed detections. However, enhancing small object features often amplifies background noise and increases false positives. To address this contradiction, we propose the Temporal Aware Small Object Enhancement Network (TASONet), which integrates spatial enhancement and temporal modeling for robust tracking. The Small Object Enhancement (SOE) module combines depthwise separable convolutions with contrast-aware attention mechanisms (SimAM and LCDAttn) to improve local discriminability. It further incorporates the Small Target Enhancement Path (STEP), which uses motion-difference cues and a confidence adaptive suppression strategy to strengthen spatial features while mitigating noise. The Temporal Enhancement Module (TEM), consisting of Temporal Feature Alignment (TFA) and a Target Memory Unit (TMU), aggregates multi-frame information through adaptive inter-frame fusion and memory of high confidence historical features, improving temporal consistency and reducing false positives potentially introduced by SOE. Experiments show that TASONet achieves significant gains over state-of-the-art methods: on UAVDT, MOTA increases from 68.33 to 75.97 and IDF1 from 83.50 to 88.51; on VisDrone-MOT, MOTA rises from 61.15 to 73.52 with an IDF1 of 88.83. These results validate the effectiveness of jointly enhancing spatial features and temporal coherence for UAV small-object MOT.
- 11 February 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (4) , 561
Open AccessTASONet: A Spatial Enhancement and Temporal Modeling Framework for UAV Small Object Tracking
Multi object tracking (MOT) in UAV imagery is challenged by weak feature representation of small objects due to limited resolution, which leads to frequent missed detections. However, enhancing small object features often amplifies background noise and increases false positives. To address this contradiction, we propose the Temporal Aware Small Object Enhancement Network (TASONet), which integrates spatial enhancement and temporal modeling for robust tracking. The Small Object Enhancement (SOE) module combines depthwise separable convolutions with contrast-aware attention mechanisms (SimAM and LCDAttn) to improve local discriminability. It further incorporates the Small Target Enhancement Path (STEP), which uses motion-difference cues and a confidence adaptive suppression strategy to strengthen spatial features while mitigating noise. The Temporal Enhancement Module (TEM), consisting of Temporal Feature Alignment (TFA) and a Target Memory Unit (TMU), aggregates multi-frame information through adaptive inter-frame fusion and memory of high confidence historical features, improving temporal consistency and reducing false positives potentially introduced by SOE. Experiments show that TASONet achieves significant gains over state-of-the-art methods: on UAVDT, MOTA increases from 68.33 to 75.97 and IDF1 from 83.50 to 88.51; on VisDrone-MOT, MOTA rises from 61.15 to 73.52 with an IDF1 of 88.83. These results validate the effectiveness of jointly enhancing spatial features and temporal coherence for UAV small-object MOT.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 73 (2) , 193-197
A Power-Efficient Hardware Accelerator for Real-Time Hashmap Construction in VVC Intra Block Copy
Intra Block Copy (IBC) is a key coding tool in the Versatile Video Coding (VVC) standard for exploiting redundancy in screen content video. However, its hardware implementation suffers from high computational complexity, incomplete pipelining, and significant power consumption. To address these challenges, we propose a power-efficient hardware accelerator for real-time hashmap construction. First, a sliding window reuse mechanism and parallel CRC32 computation are proposed, organized in a six-lane processing manner. Next, a pre-segmentation method is proposed to enable processing of different bit depths. Finally, a low-power single-bit content-addressable memory (CAM) is designed to support fast and efficient storage and matching. Experimental results show that the proposed architecture achieves a 32× improvement in hash construction speed and approximately 42.02% reduction in power consumption during hash retrieval, enabling 4K@50fps real-time processing at 415MHz. To the best of our knowledge, this is the first dedicated hardware design for hashmap construction in VVC IBC.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 73 (2) , 193-197
A Power-Efficient Hardware Accelerator for Real-Time Hashmap Construction in VVC Intra Block Copy
Intra Block Copy (IBC) is a key coding tool in the Versatile Video Coding (VVC) standard for exploiting redundancy in screen content video. However, its hardware implementation suffers from high computational complexity, incomplete pipelining, and significant power consumption. To address these challenges, we propose a power-efficient hardware accelerator for real-time hashmap construction. First, a sliding window reuse mechanism and parallel CRC32 computation are proposed, organized in a six-lane processing manner. Next, a pre-segmentation method is proposed to enable processing of different bit depths. Finally, a low-power single-bit content-addressable memory (CAM) is designed to support fast and efficient storage and matching. Experimental results show that the proposed architecture achieves a 32× improvement in hash construction speed and approximately 42.02% reduction in power consumption during hash retrieval, enabling 4K@50fps real-time processing at 415MHz. To the best of our knowledge, this is the first dedicated hardware design for hashmap construction in VVC IBC.
- Open Access
Multi-Feature Re-Identification Enhanced Dual Motion Modeling for Multi Small-Object Tracking
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.
Open AccessMulti-Feature Re-Identification Enhanced Dual Motion Modeling for Multi Small-Object Tracking
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.
- 14 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (11) , 11229-11240
Fast Linear Equation Solving Algorithm and its Pipelined Hardware Architecture Design for VVC Affine Motion Estimation
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.
- 14 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (11) , 11229-11240
Fast Linear Equation Solving Algorithm and its Pipelined Hardware Architecture Design for VVC Affine Motion Estimation
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
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 102
Efficient 2D transform hardware architecture for the versatile video coding standard
- 12 June 2024
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 102
Efficient 2D transform hardware architecture for the versatile video coding standard
- 9 June 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (1) , 681-701
SiamDAG: Siamese dynamic receptive field and global context modeling network for visual tracking
- 9 June 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (1) , 681-701
SiamDAG: Siamese dynamic receptive field and global context modeling network for visual tracking
- Open Access
Real-Time Detection of Cook Assistant Overalls Based on Embedded Reasoning
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.
Open AccessReal-Time Detection of Cook Assistant Overalls Based on Embedded Reasoning
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.
- Open Access
- 17 March 2021
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 9 (3) , 332
Visible Fidelity Collector of a Zooplankton Sample from the Near-Bottom of the Deep Sea
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.
- 17 March 2021
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 9 (3) , 332
Open AccessVisible Fidelity Collector of a Zooplankton Sample from the Near-Bottom of the Deep Sea
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.
- Open Access
A High-Robust Automatic Reading Algorithm of Pointer Meters Based on Text Detection
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.
Open AccessA High-Robust Automatic Reading Algorithm of Pointer Meters Based on Text Detection
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.