Optical remote sensing videos, as a new source of remote sensing data that has emerged in recent years, have significant potential in remote sensing applications, especially national defense. In this paper, a tracking pipeline named TDNet (tracking while detecting based on a neural network) is proposed for optical remote sensing videos based on a correlation filter and deep neural networks. The pipeline is used to simultaneously track ships and planes in videos. There are many target tracking methods for general video data, but they suffer some difficulties in remote sensing videos with low resolution and those influenced by weather conditions. The tracked targets are usually misty. Therefore, in TDNet, we propose a new multi-target tracking method called MT-KCF and a detecting-assisted tracking (i.e., DAT) module to improve tracking accuracy and precision. Meanwhile, we also design a new target recognition (i.e., NTR) module to recognise newly emerged targets. In order to verify the performance of TDNet, we compare our method with several state-of-the-art tracking methods on optical video remote sensing data sets acquired from the Jilin No. 1 satellite. The experimental results demonstrate the effectiveness and the state-of-the-art performance of the proposed method. The proposed method can achieve more than 90% performance in terms of precision for single-target tracking tasks and more than 85% performance in terms of MOTA for multi-object tracking tasks.

In this paper, we focus on the multi-target tracking (MOT) task in satellite videos. To achieve efficient and accurate tracking, we propose a transformer-distillation-based end-to-end joint detection and tracking (JDT) method. Specifically, (1) considering that targets in satellite videos usually have small scales and are shot from a bird’s-eye view, we propose a pixel-wise transformer-based feature distillation module through which useful object representations are learned via pixel-wise distillation using a strong teacher detection network; (2) targets in satellite videos, such as airplanes, ships, and vehicles, usually have similar appearances, so we propose a temperature-controllable key feature learning objective function, and by highlighting the learning of similar features during distilling, the tracking accuracy for such objects can be further improved; (3) we propose a method that is based on an end-to-end network but simultaneously learns from a highly precise teacher network and tracking head during training so that the tracking accuracy of the end-to-end network can be improved via distillation without compromising efficiency. The experimental results on three recently released publicly available datasets demonstrated the superior performance of the proposed method for satellite videos. The proposed method achieved over 90% overall tracking performance on the AIR-MOT dataset.

As the world has become increasingly digitalized in recent years, high-dimensional data with geographical location coordinate attributes, mainly referring to latitude and longitude, have been accumulated and spread to many disciplines. It is challenging to analyze such data. The map-in-parallel-coordinates plot (MPCP) is an incorporate visual analysis method that can express, filter, and highlight high-dimensional geographical data to facilitate data exploration and comprehension. In this paper, the MPCP underwent a series of field trial studies to verify its applicability, adaptability, and high efficacy in the real-world. The results of the evaluation were positive, which provides reasonable proof and new insights into the benefits of using MPCP to visually analyze high-dimensional geographical datasets.

Automatic visual encoding is frequently employed in automatic visualization tools to automatically map data to visual elements. This paper proposed an automatic visual encoding approach based on deep learning. This approach constructs visual encoding dataset in a more comprehensive and reliable manner to extract and label widely available visualization graphics on the Internet in accordance with three essentials of visualization. The deep learning model is then trained to create a visual encoding model with powerful generalization performance, enabling automated effective visual encoding recommendations for visual designers. The results demonstrated that our approach extends the automatic visual encoding techniques used by existing visualization tools, enhances the functionality and performance of visualization tools, uncovers previously undiscovered data, and increases the coverage of data variables.