Gaussian Distribution-Based Dynamic Optimization for Capsule Robot Pose Estimation in Ultrasound Images

Harnessing the full potential of capsule robots requires highly precise and reliable pose estimation. This paper presents a dynamic bounding box optimization strategy based on Gaussian similarity for accurately estimating the pose of capsule robots in ultrasound images. Specifically, a robot-adaptive label assignment strategy is developed to effectively extract features through learning the geometric properties of capsule robots. Subsequently, a novel bounding box representation is presented to accommodate variations in position and orientation. Additionally, a predicted boxes similarity metric, based on the elliptical Gaussian distributions, is proposed to achieve optimal bounding box similarity beyond the conventional IoU metric. This metric not only mitigates the limitations of IoU in non-overlapping cases but also provides a more refined basis for network optimization. Finally, a dynamic and adaptive optimization strategy is introduced to enhance estimation accuracy. A localization error of 0.11 mm and an angle error of 1.00° were achieved by the proposed model, demonstrating superior estimation accuracy. To evaluate the model’s generalizability, a private dataset reflecting real-world clinical scenarios more closely was constructed. Without any fine-tuning, the model trained solely on the public dataset yielded a localization error of 0.39 mm and an angle estimation error of 2.60° on the private dataset, confirming the robustness and generalization capability of the proposed model.