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.

To accurately recognize ordinary handwritten Chinese characters, it is necessary to recognize the normative level of these characters. This study proposes methods to quantitatively evaluate and recognize these characters based on their similarities. Three different types of similarities, including correlation coefficient, pixel coincidence degree, and cosine similarity, are calculated between handwritten and printed Song typeface Chinese characters. Eight features are derived from the similarities and used to verify the evaluation performance and an artificial neural network is used to recognize the character content. The results demonstrate that our proposed methods deliver satisfactory evaluation effectiveness and recognition accuracy (up to 98%~100%). This indicates that it is possible to improve the accuracy in recognition of ordinary handwritten Chinese characters by evaluating the normative level of these characters and standardizing writing actions in advance. Our study can offer some enlightenment for developing methods for the identification of handwritten Chinese characters used in transaction processing activities.

Basketball has become one of the most popular sports and is generally popular in international sports events. However, how to effectively achieve shooting prediction and then guide shooting has become a major challenge. Different from the classical manual observation method, this paper proposes a real-time shooting prediction method based on vision sensors and trajectory learning. In the research, we first extracted the basketball trajectory information on template matching and centroid calculation and then obtained a smooth trajectory curve through interpolation. Taking the change of x, y coordinate position, height Y, and distance D from the shooting point during the instantaneous movement as basic features, four machine learning algorithms were used to analyze the impact of different feature combinations on the shooting prediction. Finally, we analyzed the minimum trajectory point requirements predicted when making a shot. The experimental results show that our method can effectively predict the effect of shooting when the feature combination is basketball height and time. When the interpolation density is high (the total number of trajectory points is 116), the overall accuracy can reach more than 90%, and only one-third of the effective trajectory length is required, which effectively helps athletes improve their shooting percentage and assist referees in daily training.