Wenxi Chen, Ruiqi Yan, Yushen Chen, Zhikang Niu, Ziyang Ma, Xiquan Li, Yuzhe Liang, Wenhanlin, Shunshun Yin, Ming Tao, Xinsheng Wang, Xie Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Robot-assist laparoscopic surgery has been widely acknowledged in the minimally invasive surgery for its capability of operating within limited space and its robustness. Particularly, the vision-guided camera-holder system is suggested worldwide for it could track the instruments autonomously without additional equipment and its low cost, in which computer vision contributes a lot to the recognition and localization of the surgical instruments. This paper proposes vision-based real-time tracking of three basic surgical instruments in laparoscopic surgery. Two algorithms in computer vision are compared for instruments detection - Template Matching and Deep Learning, and the real-time tracking is completed based on the detection. Optimizations are made for both of algorithms. For Template Matching, three methods to enhance efficiency are applied. For Deep Learning, different loss functions and Attention Mechanisms are introduced and compared. Models are evaluated by the metrics of Precision, Recall and Detecting Time. The results reveal that despite the high precision of 0.83, the detection time of Template Matching reaches above 5000 ms, which is too slow to meet the real-time requirements in the surgery, while YOLOv5 models with CIoU and SENet performs best overall with the precision of 0.98 and the detection time of around 20 ms.