This paper presents ORB-SLAM3, the first system able to perform visual, visual-inertial and multi-map SLAM with monocular, stereo and RGB-D cameras, using pin-hole and fisheye lens models. The first main novelty is a feature-based tightly-integrated visual-inertial SLAM system that fully relies on Maximum-a-Posteriori (MAP) estimation, even during the IMU initialization phase. The result is a system that operates robustly in real-time, in small and large, indoor and outdoor environments, and is 2 to 5 times more accurate than previous approaches. The second main novelty is a multiple map system that relies on a new place recognition method with improved recall. Thanks to it, ORB-SLAM3 is able to survive to long periods of poor visual information: when it gets lost, it starts a new map that will be seamlessly merged with previous maps when revisiting mapped areas. Compared with visual odometry systems that only use information from the last few seconds, ORB-SLAM3 is the first system able to reuse in all the algorithm stages all previous information. This allows to include in bundle adjustment co-visible keyframes, that provide high parallax observations boosting accuracy, even if they are widely separated in time or if they come from a previous mapping session. Our experiments show that, in all sensor configurations, ORB-SLAM3 is as robust as the best systems available in the literature, and significantly more accurate. Notably, our stereo-inertial SLAM achieves an average accuracy of 3.6 cm on the EuRoC drone and 9 mm under quick hand-held motions in the room of TUM-VI dataset, a setting representative of AR/VR scenarios. For the benefit of the community we make public the source code.

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

More particularly, calculations are developed and examined to reduce the entire quantity of Wireless access points as well as their locations in almost any given atmosphere while with the throughput needs and the necessity to ensure every place in the area can achieve a minimum of k APs. This paper concentrates on using Wireless for interacting with and localizing the robot. We've carried out thorough studies of Wireless signal propagation qualities both in indoor and outside conditions, which forms the foundation for Wireless AP deployment and communication to be able to augment how human operators communicate with this atmosphere, a mobile automatic platform is developed. Gas and oil refineries could be a harmful atmosphere for various reasons, including heat, toxic gasses, and unpredicted catastrophic failures. When multiple Wireless APs are close together, there's a possible for interference. A graph-coloring heuristic can be used to find out AP funnel allocation. Additionally, Wireless fingerprinting based localization is developed. All of the calculations implemented are examined in real life situations using the robot developed and answers are promising. For example, within the gas and oil industry, during inspection, maintenance, or repair of facilities inside a refinery, people might be uncovered to seriously high temps to have a long time, to toxic gasses including methane and H2S, and also to unpredicted catastrophic failures.

/pdf/internet-of-vehicles-from-intelligent-grid-to-autonomous-pma0tn3ofd.pdf

Internet of Vehicles: From Intelligent Grid to Autonomous Cars and Vehicular Clouds

Deep Learning has pushed the limits of what was possible in the domain of Digital Image Processing. However, that is not to say that the traditional computer vision techniques which had been undergoing progressive development in years prior to the rise of DL have become obsolete. This paper will analyse the benefits and drawbacks of each approach. The aim of this paper is to promote a discussion on whether knowledge of classical computer vision techniques should be maintained. The paper will also explore how the two sides of computer vision can be combined. Several recent hybrid methodologies are reviewed which have demonstrated the ability to improve computer vision performance and to tackle problems not suited to Deep Learning. For example, combining traditional computer vision techniques with Deep Learning has been popular in emerging domains such as Panoramic Vision and 3D vision for which Deep Learning models have not yet been fully optimised.

Deep Learning vs. Traditional Computer Vision

Deep Learning has pushed the limits of what was possible in the domain of Digital Image Processing. However, that is not to say that the traditional computer vision techniques which had been undergoing progressive development in years prior to the rise of DL have become obsolete. This paper will analyse the benefits and drawbacks of each approach. The aim of this paper is to promote a discussion on whether knowledge of classical computer vision techniques should be maintained. The paper will also explore how the two sides of computer vision can be combined. Several recent hybrid methodologies are reviewed which have demonstrated the ability to improve computer vision performance and to tackle problems not suited to Deep Learning. For example, combining traditional computer vision techniques with Deep Learning has been popular in emerging domains such as Panoramic Vision and 3D vision for which Deep Learning models have not yet been fully optimised

The Internet of Things (IoT) is rapidly becoming an integral part of our life and also multiple industries. We expect to see the number of IoT connected devices explosively grows and will reach hundreds of billions during the next few years. To support such a massive connectivity, various wireless technologies are investigated. In this survey, we provide a broad view of the existing wireless IoT connectivity technologies and discuss several new emerging technologies and solutions that can be effectively used to enable massive connectivity for IoT. In particular, we categorize the existing wireless IoT connectivity technologies based on coverage range and review diverse types of connectivity technologies with different specifications. We also point out key technical challenges of the existing connectivity technologies for enabling massive IoT connectivity. To address the challenges, we further review and discuss some examples of promising technologies such as compressive sensing (CS) random access, non-orthogonal multiple access (NOMA), and massive multiple input multiple output (mMIMO) based random access that could be employed in future standards for supporting IoT connectivity. Finally, a classification of IoT applications is considered in terms of various service requirements. For each group of classified applications, we outline its suitable IoT connectivity options.

IoT Connectivity Technologies and Applications: A Survey

A novel cell-selection optimization handover for long-term evolution (LTE) macrocellusing fuzzy TOPSIS

The machine-type communication (MTC) plays an essential role in the mobile network society and it has demonstrated its effectiveness to generate significant revenues for mobile network operators. The MTC has become the main communication paradigm for several emerging smart services, such as public safety, health care, industrial automation, drones/robotics, utilities, and transportation. The MTC requires a major model change to cope with the improvement in 5G and imposes various requirements on the enabling technology, such as ultra-reliability, low latency, and availability. The scheme that fulfills such requirements are called a mission-critical MTC (mcMTC). However, the mcMTC is still in the early-standardization phase of 5G new radio and it needs a lot of research efforts to be improved. This paper presents an extensive review and evaluations to highlight diverse challenges and future aspects of mcMTC on 5G-enabling technologies. A number of research opportunities from both academic communities and industrial partners are given as examples for encouragement purposes.

/pdf/mission-critical-machine-type-communication-an-overview-and-t7ba6ikqyt.pdf

Mission-Critical Machine-Type Communication: An Overview and Perspectives Towards 5G

C-RAN is a promising new design for the next generation, an important aspect of it in the energy efficiency consideration. Hence, it is considering an innovative candidate to use it as an alternative cellular network instead of the traditional. Investigation green transmission of mobile cloud radio access networks based on SWIPT for 5G cellular networks. Especially, with considering SWIPT as a future solution for increasing the lifetime of end-user battery’s, that’s mean this technique will improving energy efficiency (EE). Addressing SWIPT into C-RAN is a challenging and it is needed to developing a new algorithm to use it on the cellular network with many trying to ensure the success of the system performance. C-RAN as a network and SWIPT as a promising technique with the suggesting green wireless network are discussed besides the importance of energy efficiency for the next generation. Furthermore, there was a study on fifth enabling technologies that can be used for 5G with emphasis on two of them (C-RAN and energy efficiency). Lastly, research challenges and future direction that require substantial research efforts are summarized.

Green transmission for C-RAN based on SWIPT in 5G: a review

Human detection in videos plays an important role in various real life applications. Most of traditional approaches depend on utilizing handcrafted features which are problem-dependent and optimal for specific tasks. Moreover, they are highly susceptible to dynamical events such as illumination changes, camera jitter, and variations in object sizes. On the other hand, the proposed feature learning approaches are cheaper and easier because highly abstract and discriminative features can be produced automatically without the need of expert knowledge. In this paper, we utilize automatic feature learning methods which combine optical flow and three different deep models (i.e., supervised convolutional neural network (S-CNN), pretrained CNN feature extractor, and hierarchical extreme learning machine) for human detection in videos captured using a nonstatic camera on an aerial platform with varying altitudes. The models are trained and tested on the publicly available and highly challenging UCF-ARG aerial dataset. The comparison between these models in terms of training, testing accuracy, and learning speed is analyzed. The performance evaluation considers five human actions (digging, waving, throwing, walking, and running). Experimental results demonstrated that the proposed methods are successful for human detection task. Pretrained CNN produces an average accuracy of 98.09%. S-CNN produces an average accuracy of 95.6% with soft-max and 91.7% with Support Vector Machines (SVM). H-ELM has an average accuracy of 95.9%. Using a normal Central Processing Unit (CPU), H-ELM’s training time takes 445 seconds. Learning in S-CNN takes 770 seconds with a high performance Graphical Processing Unit (GPU).

/pdf/real-time-human-detection-for-aerial-captured-video-30rl99v2v0.pdf

Real-Time Human Detection for Aerial Captured Video Sequences via Deep Models

Early diagnosis of Breast Cancer is significantly important to treat the disease easily therefore it is necessary to develop techniques that can help physicians to get accurate diagnosis. This study suggests a hybrid classification algorithm which is based upon Genetic Algorithm (GA) and k Nearest neighbor algorithm (kNN). GA algorithm has been used for its primary purpose as an optimization technique for kNN by selecting best features as well as optimization of the k value, while the kNN is used for classification purpose. The planned algorithm is tested by applying it on Wisconsin Breast Cancer Dataset from UCI Repository of Machine Learning Databases using different datasets in which the first is Wisconsin Breast Cancer Database (WBCD) and the second one is Wisconsin Diagnosis Breast Cancer (WDBC) which has changes in the number of attributes and number of instances. The proposed algorithm was measured against different classifier algorithms on the same database. The evaluation results of the algorithm proposed have achieved 99% accuracy.

Ali Mohammed Mansoor

Papers

A novel cell-selection optimization handover for long-term evolution (LTE) macrocellusing fuzzy TOPSIS

Mission-Critical Machine-Type Communication: An Overview and Perspectives Towards 5G

Green transmission for C-RAN based on SWIPT in 5G: a review

Real-Time Human Detection for Aerial Captured Video Sequences via Deep Models

A hybrid classification algorithm approach for breast cancer diagnosis