Existing shape from focus (SFF) techniques cannot preserve depth edges and fine structural details from a sequence of multi-focus images. Moreover, noise in the sequence of multi-focus images affects the accuracy of t...
详细信息
This paper presents a collaborative project between Jacobs University Bremen and University of Central Punjab, supported by the German Academic Exchange Agency - Deutscher Akademischer Austauschdienst (DAAD). It focus...
详细信息
ISBN:
(纸本)9781665427883
This paper presents a collaborative project between Jacobs University Bremen and University of Central Punjab, supported by the German Academic Exchange Agency - Deutscher Akademischer Austauschdienst (DAAD). It focuses on the partnership activities and how they have been pivotal to support education and research in marine robotics. This is an example of a successful international project, which has contributed to bring together scientists from different backgrounds working for a common goal.
The creation and use of ontologies has become increasingly relevant for complex systems in recent years. This is because of the growing number of use of cases that rely on real-world integration of disparate systems, ...
详细信息
To perform underwater navigation, a robot has to be designed and developed with multiple sensors and robust mapping and navigation algorithms that can withstand challenging underwater conditions. This paper discusses ...
详细信息
ISBN:
(纸本)9781665427883
To perform underwater navigation, a robot has to be designed and developed with multiple sensors and robust mapping and navigation algorithms that can withstand challenging underwater conditions. This paper discusses communication between Pixhawk and Jetson in the case of autonomous navigation and ground station in manual operation mode. The information from IMU and depth sensor is used to perceive the underwater environment by developing a map. The generated map is then used for path planning and autonomous navigation. Experiments performed in a swimming pool environment demonstrate the developed framework’s capabilities to be usable in shallow freshwater scenarios.
Catching high-speed targets in the flight is a complex and typical highly dynamic task. However, existing methods require manual setting of catching height or time, resulting in lacks of adaptability and flexibility a...
详细信息
Radiologists must utilize medical images of multiple modalities for tumor segmentation and diagnosis due to the limitations of medical imaging technology and the diversity of tumor signals. This has led to the develop...
详细信息
Radiologists must utilize medical images of multiple modalities for tumor segmentation and diagnosis due to the limitations of medical imaging technology and the diversity of tumor signals. This has led to the development of multimodal learning in medical image segmentation. However, the redundancy among modalities creates challenges for existing subtraction-based joint learning methods, such as misjudging the importance of modalities, ignoring specific modal information, and increasing cognitive load. These thorny issues ultimately decrease segmentation accuracy and increase the risk of overfitting. This paper presents the complementary information mutual learning (CIML) framework, which can mathematically model and address the negative impact of inter-modal redundant information. CIML adopts the idea of addition and removes inter-modal redundant information through inductive bias-driven task decomposition and message passing-based redundancy filtering. CIML first decomposes the multimodal segmentation task into multiple subtasks based on expert prior knowledge, minimizing the information dependence between modalities. Furthermore, CIML introduces a scheme in which each modality can extract information from other modalities additively through message passing. To achieve non-redundancy of extracted information, the redundant filtering is transformed into complementary information learning inspired by the variational information bottleneck. The complementary information learning procedure can be efficiently solved by variational inference and cross-modal spatial attention. Numerical results from the verification task and standard benchmarks indicate that CIML efficiently removes redundant information between modalities, outperforming SOTA methods regarding validation accuracy and segmentation effect. To emphasize, message-passing-based redundancy filtering allows neural network visualization techniques to visualize the knowledge relationship among different modalitie
Haptic feedback is critical for teleoperation in surgical robots, particularly in Natural Orifice Transluminal Endoscopic Surgery (NOTES). This paper introduces a haptic controller designed to enhance force generation...
详细信息
ISBN:
(数字)9798331509644
ISBN:
(纸本)9798331509651
Haptic feedback is critical for teleoperation in surgical robots, particularly in Natural Orifice Transluminal Endoscopic Surgery (NOTES). This paper introduces a haptic controller designed to enhance force generation efficiency and resolution, surpassing traditional motor control frameworks. We propose a Maximum Torque Per Ampere (MTPA)-based Field-Oriented Control (FoC) strategy for haptic kinesthetic feedback controller, optimizing the performance of a master manipulator's joint with a brushless DC (BLDC) motor under stalled and ultra-slow conditions. This approach enables a master manipulator with three degrees of freedom (DoF) for force feedback. Its effectiveness is validated through simulator and surgical trials, demonstrating improved haptic feedback in surgical applications.
Face anti-spoofing is crucial for ensuring the security and reliability of face recognition systems. Several existing face anti-spoofing methods utilize GAN-like networks to detect presentation attacks by estimating t...
详细信息
With the increasing emphasis on embedding advanced technology into system controls, the Direct Power Control (DPC) approach has garnered significant attention, owing to its straightforward and highly adaptable algorit...
详细信息
To solve the problem that early fault features of rotating machinery are difficult to extract, an adaptive k-value hierarchical variational mode decomposition (H-VMD) combined with optimized maximum second-order cyclo...
详细信息
ISBN:
(纸本)9781665478977
To solve the problem that early fault features of rotating machinery are difficult to extract, an adaptive k-value hierarchical variational mode decomposition (H-VMD) combined with optimized maximum second-order cyclostationarity blind deconvolution (CYCBD) fault feature extraction method is proposed in this paper. Mode decomposition of the vibration signal is performed with H-VMD. and then the noise dominant component is denoised by wavelet threshold denoising (WTD). Furthermore, the improved autocorrelation-weighted correlated kurtosis (ACK) when CYCBD enhances the periodic shock component of the denoised signal is the fitness function of ChOA, and the envelope demodulation analysis of the feature-enhanced signal is performed using the teager energy operator (TEO). Simulation analysis and experimental results show that the interference of background noise can be effectively removed and the periodic shock component of the vibration signal be enhanced by the proposed method, which is a new feature extraction method for the fault diagnosis of rotating machinery.
暂无评论