Eye center localization is one of the most crucial and basic requirements for some human-computer interaction applications such as eye gaze estimation and eye tracking. There is a large body of works on this topic in ...Eye center localization is one of the most crucial and basic requirements for some human-computer interaction applications such as eye gaze estimation and eye tracking. There is a large body of works on this topic in recent years, but the accuracy still needs to be improved due to challenges in appearance such as the high variability of shapes, lighting conditions, viewing angles and possible occlusions. To address these problems and limitations, we propose a novel approach in this paper for the eye center localization with a fully convolutional network(FCN),which is an end-to-end and pixels-to-pixels network and can locate the eye center accurately. The key idea is to apply the FCN from the object semantic segmentation task to the eye center localization task since the problem of eye center localization can be regarded as a special semantic segmentation problem. We adapt contemporary FCN into a shallow structure with a large kernel convolutional block and transfer their performance from semantic segmentation to the eye center localization task by fine-tuning.Extensive experiments show that the proposed method outperforms the state-of-the-art methods in both accuracy and reliability of eye center localization. The proposed method has achieved a large performance improvement on the most challenging database and it thus provides a promising solution to some challenging applications.展开更多
Based on domain specified language mechanism(DSLM),the architecture of the robotic training system for the rehabilitation of children with cerebral palsy(CP)is designed.Application of human-computer interaction(HCI)mo...Based on domain specified language mechanism(DSLM),the architecture of the robotic training system for the rehabilitation of children with cerebral palsy(CP)is designed.Application of human-computer interaction(HCI)motion recognition technology is combined with Kinect to improve the effect of cerebral palsy rehabilitation training.In this system,Kinect's bone recognition method is used to judge the patient's training movements,and the collected bone movement information is judged.The human-computer interaction function is based on the Microsoft foundation classes function of Visual Studio based on DSLM development,which can realize real-time interactive training and evaluation of people and actions,and record the training information of patients.The system combines the designed small game to train the upper limb movement ability and reaction ability of the cerebral palsy patient,and provides key technology for improving the cerebral palsy rehabilitation training system.展开更多
基金supported by National Natural Science Foundation of China(61533019,U1811463)Open Fund of the State Key Laboratory for Management and Control of Complex Systems,Institute of Automation,Chinese Academy of Sciences(Y6S9011F51)in part by the EPSRC Project(EP/N025849/1)
文摘Eye center localization is one of the most crucial and basic requirements for some human-computer interaction applications such as eye gaze estimation and eye tracking. There is a large body of works on this topic in recent years, but the accuracy still needs to be improved due to challenges in appearance such as the high variability of shapes, lighting conditions, viewing angles and possible occlusions. To address these problems and limitations, we propose a novel approach in this paper for the eye center localization with a fully convolutional network(FCN),which is an end-to-end and pixels-to-pixels network and can locate the eye center accurately. The key idea is to apply the FCN from the object semantic segmentation task to the eye center localization task since the problem of eye center localization can be regarded as a special semantic segmentation problem. We adapt contemporary FCN into a shallow structure with a large kernel convolutional block and transfer their performance from semantic segmentation to the eye center localization task by fine-tuning.Extensive experiments show that the proposed method outperforms the state-of-the-art methods in both accuracy and reliability of eye center localization. The proposed method has achieved a large performance improvement on the most challenging database and it thus provides a promising solution to some challenging applications.
基金Supported by the China-Slovenia Intergovernmental Science and Technology Cooperation and Exchange Project(2017-21-12-16)China-Serbia Intergovernmental Science and Technology Cooperation and Exchange Project(266-3-1).
文摘Based on domain specified language mechanism(DSLM),the architecture of the robotic training system for the rehabilitation of children with cerebral palsy(CP)is designed.Application of human-computer interaction(HCI)motion recognition technology is combined with Kinect to improve the effect of cerebral palsy rehabilitation training.In this system,Kinect's bone recognition method is used to judge the patient's training movements,and the collected bone movement information is judged.The human-computer interaction function is based on the Microsoft foundation classes function of Visual Studio based on DSLM development,which can realize real-time interactive training and evaluation of people and actions,and record the training information of patients.The system combines the designed small game to train the upper limb movement ability and reaction ability of the cerebral palsy patient,and provides key technology for improving the cerebral palsy rehabilitation training system.
