Abstract:

The target detection model of anesthesia resuscitation is often used to help medical staff to perform resuscitation detection on anesthetized patients. The targets of facial actions during patient resuscitation are small and are not obvious， and the existing Single Shot multibox Detector （SSD） is difficult to accurately detect the facial micro-action features of patients in real time. Aiming at the problem that the original model has low detection speed and is easy to have missed detection， an anesthesia resuscitation object detection method based on improved SSD was proposed. Firstly， the backbone network VGG （Visual Geometry Group）16 of the original SSD was replaced by the lightweight backbone network MobileNetV2， and the standard convolutions were replaced by the depthwise separable convolutions. At the same time， the calculation method of first increasing and then reducing the dimension of the extracted features from patient photos was used to reduce computational cost， thereby improving detection speed of the model. Secondly， the Coordinate Attention （CA） mechanism was integrated into the feature layers with different scales extracted by the SSD， and the ability of the feature map to extract key information was improved by weighting the channel and location information， so that the network positioning and classification performance was optimized. Finally， comparative experiments were carried out on three datasets： CEW（Closed Eyes in the Wild）， LFW（Labeled Faces in the Wild）， and HAPF（Hospital Anesthesia Patient Facial）. Experimental results show that the mean Average Precision （AP） of the proposed model reaches 95.23%， and the detection rate of photos is 24 frames per second， which are 1.39 percentage points higher and 140% higher than those of the original SSD model respectively. Therefore， the improved model has the effect of real-time accurate detection in anesthesia resuscitation detection， and can assist medical staff in resuscitation detection.

Key words: anesthesia resuscitation, facial feature recognition, Single Shot multibox Detector (SSD), MobileNetV2, attention mechanism

摘要：

麻醉复苏目标检测模型常被用于帮助医护人员检测麻醉病人的复苏。病人复苏时面部动作的目标较小且幅度不明显，而现有的单点多盒检测器（SSD）难以准确实时地检测病人的面部微动作特征。针对原有模型检测速度低、容易出现漏检的问题，提出一种基于改进SSD的麻醉复苏目标检测方法。首先，将原始SSD的主干网络VGG（Visual Geometry Group）16更换为轻量级的主干网络MobileNetV2，并把标准卷积替换成深度可分离卷积；同时，通过对病人照片的特征提取采用先升维再降维的计算方式减少计算量，从而提高模型的检测速度；其次，将SSD提取的不同尺度特征层中融入坐标注意力（CA）机制，并通过对通道和位置信息加权的方式提升特征图提取关键信息的能力，优化网络的定位分类表现；最后，闭眼数据集CEW（Closed Eyes in the Wild）、自然标记人脸数据集LFW（Labeled Faces in the Wild）和医院麻醉病患面部数据集HAPF（Hospital Anesthesia Patient Facial）这3个数据集上进行对比实验。实验结果表明，所提模型的平均精度均值（mAP）达到了95.23%，检测照片的速度为每秒24帧，相较于原始SSD模型的mAP提升了1.39个百分点，检测速度提升了140%。因此，所提模型在麻醉复苏检测中具有实时准确检测的效果，能够辅助医护人员进行苏醒判定。

关键词: 麻醉复苏, 面部特征识别, 单点多盒检测器, MobileNetV2, 注意力机制