In the field of Unmanned Aerial Vehicle(UAV) target tracking, accurately distinguishing changes in the target and background has always been a critical challenge. To address this issue, our study proposes a Gaussian function-based masking method, which is applied to process the residuals between the current and previous frame features. The generated Gaussian mask significantly improves the model’s ability to detect changes in the target area while also capturing dynamic variations in the background. More importantly, this innovation allows the model to allocate greater attention to changes in the target area’s features. The experimental results demonstrate that the discriminative correlation filter tracker, augmented with a Gaussian mask, achieves significant performance improvements on the DTB70 dataset and enhances its robustness in complex environments.