基于改进Mask R-CNN模型的工厂化养蚕蚕体识别与计数

何锐敏, 郑可锋, 尉钦洋, 张小斌, 张俊, 朱怡航, 赵懿滢, 顾清

Identification and Counting of Silkworms in Factory Farm Using Improved Mask R-CNN Model

HE Ruimin, ZHENG Kefeng, WEI Qinyang, ZHANG Xiaobin, ZHANG Jun, ZHU Yihang, ZHAO Yiying, GU Qing

表2 两种蚕体与残余饲料检测模型的性能

Table 2 The performance of the silkworm and residual feed detection models

模型 目标 准确率/% 检测 AP50 分割AP50 Mask R-CNN 蚕 95.23 0.764 0.768 饲料 85.35 0.602 0.611 改进Mask R-CNN 蚕 96.83 0.790 0.795 饲料 87.71 0.641 0.653