中文摘要：

基于深度学习方法,运用Faster R-CNN目标检测架构和ZFNet卷积神经网络,针对微装配系统目标的特点对网络进行训练,在此基础上设计了一个网络对识别目标进行姿态检测.实验结果表明：采用深度学习方法可以有效地对部分遮挡的目标进行识别并检测其姿态,相比于传统方法,该方法对环境适应性更强且速度更快,具有实际应用价值.

英文摘要：

Aiming at the characteristics of micro-assembly system target,a network was trained based on deep learning method and the faster region-based convolutional neural network（faster R-CNN）object detection architecture and Zeiler and Fergus′s network（ZFNet）convolutional neural network were used.A pose detection network was designed for recognizing targets.The experimental results show that the proposed deep learning method can effectively identify and detect the partially occluded objects,and compared with the traditional method,this method has strong adaptability to environment and speediness with practical application value.