As Internet of Things (IoT) develops, IoT technologies are starting to integrate intelligent cameras for managing safety within mental health hospital wards and relevant spaces, seeking out specified individuals from these surveillance videos filmed by the various cameras. Because monitoring is one of the important application of IoT based on distributed video cameras. In order to fine-grained re-identification of patients and their activities against the very low resolution, occlusions and pose, viewpoint and illumination changes, we propose a novel data-driven model to infer multi-cameras logical topology and re-identify patients captured by different cameras. In our model, we employ a Time-Delayed Mutual Information (TDMI) model in order to address multi-cameras logical topology inference. Additionally, we use a welltrained Deep Convolutional Neural Network (DCNN) to extract characteristics. Moreover, we employ a name-ability model to discover deep attributes and a classifier based on a structural output of attributes is designed to tackle the re-identification of patients, especially who possess psychiatric behaviour. In order to improve the present model’s performance, we resort to the parallelized implementations. Experimental results show that our model possesses the best performance as compared to state-of-the-art model,especially, when the semantic restrictions are imposed onto the production of patients’ specific attributes with structural output. Further, the deep learning model is used to produce characteristics when there is no supervision on the learning model of attributes.

Introduction

From last two decades, videos surveillance systems have been used for managing safety within healthcare industry especially in mental health hospital, asylum, seclusion room, and wards for controlling the suspicious activities of psychotic patients. Such as spotting suspicious behavior, violence, hyperactivity, and safety issues. Further, these issues lead to treatment-related harms caused by medical care of patient and staff. Additionally, those adverse events also lead to harm caused by errors, medical treatment errors, potential for harm. further, multi-cameras monitoring surveillance system can sort the problems related to managing medical care protocols [1]–[۳]. Health monitoring research leads to significant focus to improve and achieve good healthcare environment. The analytical evaluation of mentioned issues and analyzing their causes can help in healthcare planning and design advance smart health care system too. Unfortunately, most hospitals and health systems have rudimentary methods to identify this issues or activities. These rudimentary methods mostly depend on the use of voluntary help, chart-reports results, and scanning of manually observed behavior of patient. These methods face challenges and limitations those lead them to accidents. Further, these methods required human resources as well. Detecting these events is especially challenging because of the unpredictable nature of patients. Along with powerful re-identification features, this paper proposes a model to improve patient safety in hospitals through the usage of Multi-Cameras IoT.