Zhongping Dong, Liming Chen, Mohand Tahar Kechadi
This study critically analyzes current methodologies in dynamic object tracking and trajectory prediction, highlighting their applications, challenges, and future research directions.
This research paper reviews the latest methods used for tracking moving objects and predicting their paths, which are crucial for technologies like self-driving cars, surveillance systems, and industrial robots. The paper discusses different approaches, such as using features of the objects, segmenting them, estimating their movements, or employing machine learning techniques. While these methods have improved safety and efficiency in various fields, there are still challenges like making the systems work well in different situations, reducing the need for large amounts of data, and addressing ethical concerns. The paper suggests that future research should focus on integrating different types of data, using semantic information, and creating systems that understand the context of their environment, while also considering privacy issues.
