Small object detection (SOD) in optical images and videos is a challenging problem that even state-of-the-art generic object detection methods fail to accurately localize and identify such objects. Typically, small objects appear in real-world due to large camera-object distance. Because small objects occupy only a small area in the input image (e.g., less than 10%), the information extracted from such a small area is not always rich enough to support decision making. Multidisciplinary strategies are being developed by researchers working at the interface of deep learning and computer vision to enhance the performance of SOD deep learning based methods. In this paper, we provide a comprehensive review of over 160 research papers published between 2017 and 2022 in order to survey this growing subject. This paper summarizes the existing literature and provide a taxonomy that illustrates the broad picture of current research. We investigate how to improve the performance of small object detection in maritime environments, where increasing performance is critical. By establishing a connection between generic and maritime SOD research, future directions have been identified. In addition, the popular datasets that have been used for SOD for generic and maritime applications are discussed, and also well-known evaluation metrics for the state-of-the-art methods on some of the datasets are provided.

A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance

Intelligent transportation systems (ITS) are a newer trend in technology that improve the safety and performance in transportation systems. The exchange of information is considered as one of the key elements for ITS since it involves communication between vehicles and other components of ITS on road. On other hand, the data collections via Internet of Things (IoT) sensors play a major role for data collection and transmission between the vehicles and road segments in ITS. The data collection provides the current traffic and weather conditions that is considered necessary for driving in traffic. However, energy savings is one of the predominant objectives of electric vehicle (EV) while it is connected with ITS. In this research, we propose an ontology-based architecture for EVs using the data collected from IoT sensor network, which is intended to improve the overall driving experience. The system uses IoT sensor data to execute a range of activities in order to ensure the driver safety and comfort while on the road. The simulation is conducted on an Eclipse SUMO simulator, and the performance is reported. The results of simulation shows that the proposed intelligent model on making decisions along with weather and traffic conditions is reported efficient than existing ITS models.

/pdf/internet-of-things-based-intelligent-ontology-model-for-3s8isnv3.pdf

Internet of Things-Based Intelligent Ontology Model for Safety Purpose Using Wireless Networks

Optical, structural, electrical and photocatalytic properties of aluminum doped zinc oxide nanostructures

Currently, cloud computing has become a new educational model, which not only solves the problem of resource access for teachers and students in the traditional teaching process, but also promotes the sharing and optimization of educational resources. Currently, cloud computing technology has been accepted and deeply used by more and more universities. The adaptive learning platform based on OBE teaching mode is designed and formed in this context. The main purpose of this paper is to study the design of adaptive learning platform based on OBE teaching and learning from the perspective of cloud computing. This paper combines the “OBE” concept with various learning models that are currently popular. The platform can be used for teaching without the need for teachers to design teaching programs and change the way teachers teach and learn. The adaptive learning platform can dynamically adjust the learning program, content and resources according to the actual situation and learning of the students, and the students can exit the system interface at any time after completing their assigned learning tasks and continue learning after self-modification of the current learning content. This platform enables students to learn each knowledge area more independently by dynamically adjusting the management of classroom progress and course schedule through independent selection of learning content, adjustment of learning time and learning plan. At the same time, teachers can use the platform to provide personalized guidance and supervision, as well as comparative analysis and summary of learning results.

Designing an Adaptive Learning Platform Based on OBE Teaching in Cloud Computing

Stirring Effect of Cus Deposition Over Cotton Thread for Photocatalysis and Electrical Application

Machine learning driven intelligent and self adaptive system for traffic management in smart cities

In the present work, ZnS thin film was deposited onto a p-type Si-substrate using the chemical bath deposition method, and subsequently Ag/n-ZnS/p-Si/Ag heterojunction device was fabricated to investigate its diode parameters in the temperature range of 0–60 °C. Cubic zinc blende phase of the prepared ZnS thin film was confirmed using grazing incidence X-ray diffraction (GIXRD); Scherrer analysis revealed a lower limit of crystallite size as 2.4 nm. Scanning electron microscopy (SEM) revealed the surface morphology of the prepared ZnS thin film, which exhibited good homogeneity and density. UV–Visible absorption spectroscopy revealed the good UV-region absorbance and visible-region transmittance of the deposited ZnS thin film. The corresponding energy band gap was obtained from Tauc analysis and found to be 3.88eV. Photoluminescent emission (PLE) spectroscopy showed the defect mediated radiative transitions in the deposited ZnS thin film. Current-voltage (I–V) measurements of the fabricated heterojunction device exhibited Schottky diode behaviour. Diode parameters of reverse saturation current, Schottky barrier height, ideality factor and series resistance were obtained from the I–V measurements in the temperature range of 0–60 °C; barrier height was obtained in the range of 0.87–0.74eV, and ideality factor was obtained close to unity for I–V measurements made at 30 °C and 60 °C. 

Sujeet K. Mahobia

Papers

Machine learning driven intelligent and self adaptive system for traffic management in smart cities

Temperature-dependent study of the fabricated ZnS/p-Si heterojunction