No abstract

Realtime object security and vehicle tracking have not been successfully implemented in commercial vehicles due to limitations in processing large amount of data and hardware capabilities. This paper aimed to improve the object security, processing power and data storage in a distributed environment. The proposed system (HLAiUE) consists of a threelayer architecture, first layer is used to collect data, second layer distributes the data processing and the last layer stores the processed data. The designed architecture improves the performance and security by applying data compression algorithms in a real time and removes the hardware dependency by processing the data in a distributed environment using Hadoop and Spark framework. The results demonstrate that the proposed architecture improves processing time by 80% compared to other algorithms and provides more reliability, security and flexibility due to ubiquity and the absence of hardware dependency in comparison with other existing architectures which are hardware dependent. Also, using an NOSQL database server in a distributed environment optimizes data storage by up to 80% and is flexible because all the infrastructure is in a distributed environment. The proposed architecture improves the object tracking by implementing compression technique in a distributed architecture. Thus, this system improves the accuracy up to 80% without depending on hardware resources.

The use of Augmented Reality (AR) for visualising blood vessels in surgery is still at the experimental stage and has not been implemented due to limitations in terms of accuracy and processing time. The AR also hasn't applied in breast surgeries yet. As there is a need for a plastic surgeon to see the blood vessels before he cuts the breast and before putting the implant, this paper aims to improve the accuracy of augmented videos in visualising blood vessels during Breast Implant Surgery. The proposed system consists of a Weighted Integral Energy Functional (WIFE) algorithm to increase the accuracy of the augmented view in visualising the occluded blood vessels that covered by fat in the operating room. The results on breast area shows that the proposed algorithm improves video accuracy in terms of registration error to 0.32 mm and processing time to 23 sec compared to the state-of-the-art method. The proposed system focuses on increasing the accuracy in augmented view in visualising blood vessels during Breast Implant Surgery as it reduces the registration error. Thus, this study concentrates on looking at the feasibility of the use of Augmented Reality technology in Breast Augmentation surgeries.

Hazard detection and avoidance at construction sites working with heavy equipment and moving vehicles is one of the biggest issues in modern surveillance. Background subtraction using a Gaussian Mixture Model (GMM) is widely utilized for identification of moving objects with most existing methods leading to improvements but lacking accuracy of object detection. This paper aims to improve accuracy and processing time for object detection. The proposed algorithm consists of a correlation coefficient to reduce the existing geometric error and provide more accurate detection of moving objects by comparing foreground and background pixels in every frame. A Kalman filter is used for keeping track of the object. The results demonstrate that the proposed algorithm outperforms existing applications in terms of accuracy of object detection. On this basis, it is recommended that object detection with a correlation coefficient of background and foreground pixels of objects can be used for hazard detection in real-time monitoring systems such as traffic monitoring and detection and tracking of humans.