Activity level measurement and fusion rules are the two key factors of image fusion. In the fusion method based on neural networks, the activity level measurements are realized by dividing the image into small blocks and predicting the sharpness of each block; then, the global decision graph guiding fusion is generated according to the predicted results. However, these two tasks are serial in nature, which makes it difficult to complete them simultaneously while achieving satisfactory fusion performance. Therefore, a new multi-focus microscopic image fusion method is proposed in this paper to quickly fuse multiple histological microscopic images from different focusing planes to generate full-focus images. The improved SegNet network was used to detect the unfocused regions. Considering that two or more images are needed for fusion, a parallel fusion strategy is proposed herein to generate clear fusion images based on multiple images instead of pairwise decision graphs. Compared with the convolutional neural network, the proposed network has better representation ability and can extract and fuse the most ideal features to provide a more accurate fusion decision. Compared with the traditional Segnet network, it is lightweight, which greatly improves computing speed and achieves real-time fusion.

A six degrees-of-freedom parallel platform in a 6-RR-RP-RR configuration with high accuracy, high stiffness and a large working stroke is studied for application to the sub-mirror adjustment system of a large-aperture telescope. To meet the performance requirements, the parallel platform adopts a self-centering and well-designed offset universal hinge. The two hinge axes of the offset hinge do not intersect but have a specific offset in space, which makes the kinematics more complex than that with a common universal hinge. Therefore, to solve this complex kinematics problem, this paper innovatively introduces the Denavit–Hartenberg (D-H) parameter method that is used for series mechanisms. The method has a simple modeling process, strong applicability and continuity, providing a new tool for the analysis and application of the parallel mechanisms. A kinematics model of the parallel platform can be constructed and solved using a numerical iteration method. The accuracy of the numerical kinematics solution is verified using a co-simulation method. This paper analyses the passive derivative motion and the leg length error is compensated. Finally, test studies of the motion resolution, the repetitive positioning accuracy, the motion stroke, the static stiffness of the legs, and the static stiffness and dynamic stiffness of the entire machine were also carried out to verify the platform’s performance.

The inevitable vibration caused by the normal operation of the spacecraft in orbit will interfere with sensitive instruments, such as space telescopes, reconnaissance cameras, and spatial interferometers. Severe vibrations can impact the accuracy and reliability of these sensitive instruments, potentially leading to mission failure. To address this issue, active–passive integrated six-dimensional orthogonal vibration isolation (APIVI) platform has been proposed for vibration isolation in spaceborne sensitive instruments. The APIVI platform is composed of three orthogonal isolation modules, each made up of an active piezoelectric actuator and passive rubber isolator. Taking into account the parameter uncertainties of the actual system, the H_∞ controller was designed, and the μ-synthesis method was proposed to establish a parameter uncertainty model for the APIVI platform. Finally, experimental studies were conducted on the APIVI platform. The results demonstrated the excellent vibration isolation performance of the APIVI platform, with the vibration isolation frequency band above 18 Hz. With the addition of active control, it was able to fully attenuate the first-order resonance peak of the system, with a maximum attenuation of 18 dB.