Tracking and segmenting small targets in remote sensing videos on edge devices carries significant engineering implications. However, many semi-supervised video object segmentation (S-VOS) methods heavily rely on extensive video random-access memory (VRAM) resources, making deployment on edge devices challenging. Our goal is to develop an edge-deployable S-VOS method that can achieve high-precision tracking and segmentation by selecting a bounding box for the target object. First, a tracker is introduced to pinpoint the position of the tracked object in different frames, thereby eliminating the need to save the results of the split as other S-VOS methods do, thus avoiding an increase in VRAM usage. Second, we use two key lightweight components, correlation filters (CFs) and the Mobile Segment Anything Model (MobileSAM), to ensure the inference speed of our model. Third, a mask diffusion module is proposed that improves the accuracy and robustness of segmentation without increasing VRAM usage. We use our self-built dataset containing airplanes and vehicles to evaluate our method. The results show that on the GTX 1080 Ti, our model achieves a J&F score of 66.4% under the condition that the VRAM usage is less than 500 MB, while maintaining a processing speed of 12 frames per second (FPS). The model we propose exhibits good performance in tracking and segmenting small targets on edge devices, providing a solution for fields such as aircraft monitoring and vehicle tracking that require executing S-VOS tasks on edge devices.

This paper reports a novel four degree-of-freedom (DOF) MEMS vibratory gyroscope. A MEMS gyroscope array is then presented using the novel gyroscope unit. In the design of the proposed 4-DOF MEMS vibratory gyroscope, the elements of the drive-mode are set inside the whole gyroscope architecture, and the elements of sense-mode are set around the drive-mode, which thus makes it possible to combine several gyroscope units into a gyroscope array through sense-modes of all the units. The complete 2-DOF vibratory structure is utilized in both the drive-mode and sense-mode of the gyroscope unit, thereby providing the desired bandwidth and inherent robustness. The gyroscope array combines several gyroscope units by using the unique detection mass, which will increase the gain of sense-mode and improve the sensitivity of the system. The simulation results demonstrate that, compared to a single gyroscope unit, the gain of gyroscope array (n = 6) is increased by about 8 dB; a 3 dB bandwidth of 100 Hz in sense-mode and 190 Hz in drive-mode are also provided. The bandwidths of both modes are highly matched with each other, providing a bandwidth of 100 Hz for the entire system, thus illustrating that it could satisfy the requirements in practical applications.