Addressing Reviewer Comments on Background Modelling Method Choice

Thank you for your insightful comments on our paper. We appreciate your suggestions regarding the use of deep learning frameworks for background modelling. While we agree that deep learning algorithms have shown great promise in various image processing tasks, we found that the limited availability of training samples and the instability of training due to the noisy nature of the radar data made it challenging to achieve reliable results using deep learning methods. However, we acknowledge that there are pre-trained deep learning algorithms that can be used as initial models for fine-tuning, and we will consider this approach in future work. Thank you again for your valuable feedback.