Ship and air target dataset based on self-reported location track data

The track of a target is a typical time series, which consists of the points in a period of time and is arranged in time order. The track data contains the movement characteristics of the target. In the research of target tracking, identification, correlation, etc., a large amount of track data is needed to support the experimental design. Based on the analysis of the actual environment and sensors, part of the current research explores and realizes the simulation process of data to build simulation data that is as consistent as possible with the real world, and uses the simulation data to verify the method. The other part of the study collected real data directly. By accumulating and preprocessing real data, they construct real data sets for experiments. The simulation data are not convincing, and it is difficult to test the performance of the proposed method in real environment. However, few real data are disclosed, which increases the difficulty for researchers to obtain real data and results in data blocking. Therefore, it is necessary to build and publish a professionally standardized track data set. In order to make up for the lack of track recognition data set, this paper constructed and disclosed a sea and air target data set based on self-reported location track data. The data set consisted of two parts: ship target track data and air target track data. The ship target track data came from automatic identification system data, and the air target track data came from automatic dependent surveillance-broadcast data. Through the long-term accumulation of two types of data, the data preprocessing and data set construction processes were constructed according to the characteristics of the data, providing data support for ship and air target tracking, identification, correlation and other algorithms.