A monitoring video multi-target face detection method and system based on instance segmentation

• Main Authors: CHEN RONGJUN, LIN KAIHAN, ZHAO HUIMIN, ZHAN JIN, LYU JUJIAN
• Format: Patent
• Language: Chinese; English
• Published: 23.04.2019
• Subjects: CALCULATING; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses a monitoring video multi-target face detection method and system based on instance segmentation, and the method comprises the steps of collecting a to-be-trained face image data set, carrying out the marking of the face image data set based on a marking tool, and obtaining a training data set; setting model parameters for training the face detection system based on the monitoring equipment condition; training the face detection system based on the marked face image data set and the model parameters to obtain a trained face detection system; and inputting each frame of image in the monitoring video into the trained face detection system, carrying out multi-target face detection on each input frame of image, and obtaining a detection result. According to the embodiment of the invention, the recognition accuracy of the face target image is improved. 本发明公开了种基于实例分割的监控视频多目标人脸检测方法及系统，其中，所述方法包括：采集待训练的人脸图像数据集，基于标注工具对人脸图像数据集进行标注，获取训练数据集；基于监控设备条件设置用于训练人脸检测系统的模型参数；基于标记后的人脸图像数据集和模型参数对所述人脸检测系统进行训练，获