Papers by احمد اتحاد جليل محمد
AIP Conf. Proc. 2845, 030008, 2023
Motion detection and tracking systems used to quantify the mechanics of motion in many fields of ... more Motion detection and tracking systems used to quantify the mechanics of motion in many fields of research. Despite their high accuracy, industrial systems are expensive and sophisticated to use. However, it has shown imprecision in activity-delicate motions, to deal with the limitations. The Microsoft Kinect Sensor used as a practical and cheap device to access skeletal data, so it can be used to detect and track the body in different subjects such as, medical, sports, and analysis fields, because it has very good degrees of accuracy and its ability to track six people in real time. Sometimes research uses single or multiple Kinect devices based on different classification methods and approaches such as machine learning algorithms, neural networks, and others. Researches used global database like, CAD-60, MSRAction3D, 3D Action Pairs and others, while the others used their on database by collected them from different ages and genders. Some research connected a Kinect device to a robot to simulate movements, or the process done in virtual reality by using an avatar, where an unreal engine used to make it. In this research, we presents the related works in this subject, the used methods, database and applications.
Hand position recognition is very significant for human-computer interaction. Different kinds of ... more Hand position recognition is very significant for human-computer interaction. Different kinds of devices and technologies can be used for data acquisition; each has its specification and accuracy, one of these devices is Kinect V2 sensor. A three-dimensional location of the skeleton joints is taken from the Kinect device to create three types of data, the first is joint position raw data, the second is angles between joints, the third is combined of both types. These three types of data are used to train four classifiers, which are support vector machines, random forest, k nearest neighbors, and multilayer perceptron. The experiments are done on the datasets of 30,480 frames from 127 volunteers with saved trained models are used to predict and classify the eight positions of hand in a real-time system. The results show that our proposed approach performs well with highly efficient and accuracy reaching up to 99.07% in some cases and an average time spent on checking frame by frame sequentially very short period, and some cases, it reaches 0.59*10-3 seconds. This system can used in many applications such as controlling robots or devices, comparing physical exercises, or even monitoring elderly and patients, and more.
Uploads
Papers by احمد اتحاد جليل محمد