Predicting the pose parameters during the hand pose estimation (HPE) process is an ill-posed challenge. This is due to severe self-occluded joints of the hand. The existing approaches for predicting pose parameters of the hand, utilize a single-value mapping of an input image to generate final pose output. This way makes it difficult to handle occlusion especially when it comes from the multimodal pose hypothesis. This paper introduces an effective method of handling multimodal joint occlusion using the negative log-likelihood of a multimodal mixture-of-Gaussians through a hybrid hierarchical mixture density network (HHMDN). The proposed approach generates multiple feasible hypotheses of 3D poses with visibility, unimodal and multimodal distribution units to locate joint visibility. The visible features are extracted and fed into the Convolutional Neural Networks (CNN) layer of the HHMDN for feature learning. Finally, the effectiveness of the proposed method is proved on ICVL, NYU, and BigHand public hand pose datasets. The imperative results show that the proposed method in this paper is effective as it achieves a visibility error of 30.3mm, which is less error compared to many state-of-the-art approaches that use different distributions of visible and occluded joints.

No abstract

Health monitoring is an essential task in managing both the daily routine progress of a patient/outpatient during and after the medication period. It plays not only a significant role in the overall well-being of the patient/outpatient but also as the measure of quality and effective healthcare services deliverance. However, achieving this is very challenging in areas with limited infrastructure to support a myriad of current social services, including advanced healthcare services. For instance, instead of relying only on the outpatient's physical visitations to the healthcare center as a feedback mechanism in case of any complications during medications, continuously remote monitoring of the outpatients' health can improve the deliverance of healthcare services. This paper presents a simplified system model for remote monitoring of the outpatients well-being that has been designed to work in the limited Internet of Things (IoT) infrastructure to address the challenge above. The design is cheap and easily deployable for health remote monitoring purposes as the outpatient's well-being can be monitored in real-time so that to facilitate detection of the subtle changes and avoid drug intoxication. The system advises and alerts in real-time the doctors/medical assistants about the changing of vital parameters in order to take preventive measures.