1 June 2018 in Ocean Engineering
15 December 2022 in IEEE Transactions on Instrumentation and Measurement
Defect detection is an essential part of quality management for bare PCB production. Existing vision-based methods are not effective in detecting PCB defects when uncertainty exists. This paper proposes a multiscale convolution-based detection methodology to classify bare PCB defects under uncertainty. First, a novel window-based loss function is designed to tackle the inter-class imbalance and uncertainty. Then, a multiscale convolution network is constructed to process the defects with intra-class variance, and large scale extraction features are fused on the small scale to guide the extraction process. After that, the classification probability is extracted and assembled into a multiscale probability matrix, on which entropy-based probabilistic decisions are integrated for the final decision. Finally, experimental studies indicate that the proposed methodology can achieve satisfactory detection performance and demonstrate visual interpretability compared to baseline methods.
6 July 2020 in IEEE Access
Using high-speed on-off valves (HSVs) with small size, low cost, and high switching accuracy instead of expensive proportional/servo valves, and researching high-performance vacuum servo system can further enhance the competitiveness of vacuum servo technology. However, due to the delay characteristics of high-speed on-off valve (HSV), the average gas mass flow rate of the output has dead zone, saturated zone and nonlinear zone. A linear compensation method for flow output is designed, so that the average gas mass flow rate of the output is approximately positively correlated with the duty cycle of the pulse width modulation (PWM) signal. Furthermore, because of the air compression and the leakage of the system, there exist parametric uncertainties, unmodeled dynamics and disturbances in the vacuum servo system. An adaptive backstepping control (ABC) strategy based on discontinuous projection mapping is designed. The adaptive backstepping control strategy inhibit the influence of system’s parametric uncertainties through on-line update of the uncertain parameters, and uses its own robustness to eliminate the effects of unmodeled dynamics and disturbances. Compared with the sliding mode control (SMC) strategy, the experimental results show that when the tracking frequency reaches 3–4Hz, the adaptive backstepping control strategy can ensure good tracking performance.
1 January 2022 in Ocean Engineering
19 May 2025 in IEEE Transactions on Instrumentation and Measurement
Visual inspection remains essential for inspecting infrastructure surfaces. While there are cornerstones in developing intelligent inspection systems, most existing solutions are limited to small-scale infrastructures and components, making them challenging to scale up for real-world applications. Leveraging deep learning and unmanned aerial vehicles, this paper proposes Det-Recon-Reg, an intelligent framework born for large-scale infrastructure inspection by decomposing it into three complementary stages: Detect for defect detection, Reconstruct for infrastructure reconstruction, and Register for defect registration. In the Detect stage, we introduce the first highresolution dataset designed for defect detection on large-scale infrastructure surfaces. State-of-the-art real-time object detectors are evaluated on this dataset and the CUBIT-Net1 is proposed to strike a better balance between accuracy and efficiency. In the Reconstruct stage, we present a scalable multi-view stereo (MVS) network to reconstruct dense point cloud representation of the infrastructure from multi-view images. Extensive experiments on benchmark datasets, including DTU, Tanks and Temples, and BlendedMVS, demonstrate the superior performance of our method over existing approaches. In the Register stage, we propose a novel defect registration method that leverages the geographic information system to accurately map the detected defects onto the infrastructure model while preserving their geometric and visual properties, thereby enabling global defect localization and more informed maintenance decision-making. The proposed framework can serve as a reference for effective and efficient infrastructure maintenance as consolidated in real-world experiments. Codes, datasets, and pre-trained models for each stage will be released at: https://github.com/YANG-SOBER/Det-Recon-Reg. The supplementary video is available at: https://youtu.be/MVMp7k9qB84.
1 January 2026 in IEEE Journal of Oceanic Engineering
Underwater environments present significant challenges, such as image degradation and domain discrepancies, that severely impact object detection performance. Traditional approaches often use image enhancement as a preprocessing step, but this adds computational overhead, latency, and can even degrade detection accuracy. To address these issues, we propose a novel underwater object detection framework that jointly trains image enhancement within a multitask architecture. This framework employs a progressive training strategy to iteratively improve detection performance through enhancement and introduces a domain-adaptation mechanism to align features across domains at both image and object levels. Experimental results demonstrate that our method achieves state-of-the-art performance across diverse data sets, with real-time detection at 105.93 frames per second and over +15$\%$ mean average precision absolute improvement in unseen environments, underscoring its potential for real-world underwater applications.