A Decade of UAV Docking Stations: A Brief Overview of Mobile and Fixed Landing Platforms

Unmanned Aerial Vehicles have advanced rapidly in the last two decades with the advances in microelectromechanical systems (MEMS) technology. It is crucial, however, to design better power supply technologies. In the last decade, lithium polymer and lithium-ion batteries have mainly been used to power multirotor UAVs. Even though batteries have been improved and are constantly being improved, they provide fairly low energy density, which limits multirotors’ UAV flight endurance. This problem is addressed and is being partially solved by using docking stations which provide an aircraft to land safely, charge (or change) the batteries and to take-off as well as being safely stored. This paper focuses on the work carried out in the last decade. Different docking stations are presented with a focus on their movement abilities. Rapid advances in computer vision systems gave birth to precise landing systems. These algorithms are the main reason that docking stations became a viable solution. The authors concluded that the docking station solution to short ranges is a viable option, and numerous extensive studies have been carried out that offer different solutions, but only some types, mainly fixed stations with storage systems, have been implemented and are being used today. This can be seen from the commercially available list of docking stations at the end of this paper. Nevertheless, it is important to be aware of the technologies being developed and implemented, which can offer solutions to a vast number of different problems.

The image description reduction in the set of descriptors on informativeness metric criteria base

The subject of the research is the methods of image classification on a set of key point descriptors in computer vision systems. The goal is to improve the performance of structural classification methods by introducing indexed hash structures on the set of the dataset reference images descriptors and a consistent chain combination of several stages of data analysis in the classification process. Applied methods: BRISK detector and descriptors, data hashing tools, search methods in large data arrays, metric models for the vector relevance estimation, software modeling. The obtained results: developed an effective method of image classification based on the introduction of high-speed search using indexed hash structures, that speeds up the calculation dozens of times; the gain in computing time increases with an increase of the number of reference images and descriptors in descriptions; the peculiarity of the classifier is that not an exact search is performed, but taking into account the permissible deviation of data from the reference; experimentally verified the effectiveness of the classification, which indicates the efficiency and effectiveness of the proposed method. The practical significance of the work is the construction of classification models in the transformed space of the hash data representation, the efficiency confirmation of the proposed classifiers modifications on image examples, development of applied software models implementing the proposed classification methods in computer vision systems.

Internet of Things IoT Edge Computer Vision Systems on Drilling Rigs

This study focuses on the design and infrastructure development of Internet-of-Things (IoT) edge platforms on drilling rigs and the testing of pilot IoT-Edge Computer Vision Systems (ECVS) for the optimization of drilling processes. The pilot technology presented in this study, Well Control Space Out System (WC-SOS), reduces the risks associated with hydrocarbon release during drilling by significantly increasing the success and time response for shut-in a well. Current shut-in methods that require manual steps are prone to errors and may take minutes to perform, which is enough time for an irreversible escalation in the well control incident. Consequently, the WC-SOS enables the drilling rig crew to shut-in a well in seconds. The IoT-ECVS deployed for the WC-SOS can be seamlessly expanded to analyze drillstring dynamics and drilling fluid cuttings/solids/flow analysis at the shale shakers in real-time. When IoT-ECVSs communicate with each other, their value is multiplied, which makes interoperability essential for maximizing benefits in drilling operations.

Control of a transport robot in extreme weather based on computer vision systems

This article presents a new way to use special computer vision techniques to aim with assisting in controlling a transport robot in a dynamic environment under exceptional and difficult environmental conditions. An analysis and development of algorithm for obstacle detection in the robot’s environment proposed based on data from an RGB-D video camera using computer vision methods. Contour analysis was the base method to detecting objects featured fragment taking into account difficult vision conditions. Based on open-source library (Open CV), we adopted methods program implementation which confirmed its applicability to detect objects in mobile robot environment.

Comparative Analysis of Deep Neural Networks Architectures for Visual Recognition in the Autonomous Transport Systems

This paper analyses and presents an experimental investigation of the efficiency of modern models for object recognition in computer vision systems of robotic complexes. In this article, the applicability of transformers for experimental classification problems has been investigated. The comparison results are presented taking into account various limitations specific to robotics. Based on the results of the undertaken studies, recommendations on the use of models in the marine vessels classification problem are proposed

Anomaly event detection and localization of video clips using global and local outliers

The automatic detection of anomaly events in video sequence has become a critical issue and essential demand for the extensive deployment of computer vision systems such as video surveillance applications. An anomaly event in video can be denoted as outlier behavior within video frames which formulated by a deviation from the stable scene. In this paper, an anomaly event detection and localization method in video sequence is presented including multilevel strategy as temporal frames differences estimation, modelling of normal and abnormal behavior using regression model and finally density–based clustering to detect the outliers (abnormal event) at clips level. Hence, outlier score is obtained at the segment or clip level along video frames sequences. The proposed method seplits video frames into nonoverlapped clips using global outlier detection process. Afterward, at each clip, the local outliers are determined based on density of each clip. Extensive experiments were conducted upon two public video datasets which include dense and scattered outliers along video sequence. The experiments were performed on two common public datasets (Avenue) and University of California, San Diego (UCSD). The experimental results exhibited that the proposed method detects well outlier frames at clip level with lower computational complexity comparing to the state-of-the-art methods.

Evaluation of Deep Learning for Automatic Multi-View Face Detection in Cattle

Individual identification plays an important part in disease prevention and control, traceability of meat products, and improvement of agricultural false insurance claims. Automatic and accurate detection of cattle face is prior to individual identification and facial expression recognition based on image analysis technology. This paper evaluated the possibility of the cutting-edge object detection algorithm, RetinaNet, performing multi-view cattle face detection in housing farms with fluctuating illumination, overlapping, and occlusion. Seven different pretrained CNN models (ResNet 50, ResNet 101, ResNet 152, VGG 16, VGG 19, Densenet 121 and Densenet 169) were fine-tuned by transfer learning and re-trained on the dataset in the paper. Experimental results showed that RetinaNet incorporating the ResNet 50 was superior in accuracy and speed through performance evaluation, which yielded an average precision score of 99.8% and an average processing time of 0.0438 s per image. Compared with the typical competing algorithms, the proposed method was preferable for cattle face detection, especially in particularly challenging scenarios. This research work demonstrated the potential of artificial intelligence towards the incorporation of computer vision systems for individual identification and other animal welfare improvements.

Combination method of accelerated metric data search in image classification problems

The subject of research of the paper is the methods of image classification on a set of key point descriptors in computer vision systems. The goal is to improve the performance of structural classification methods by introducing indexed hash structures on the set of the dataset reference images descriptors and a consistent chain combination of several stages of data analysis in the classification process. Applied methods: BRISK detector and descriptors, data hashing tools, search methods in large data arrays, metric models for the vector relevance estimation, software modeling. The obtained results: developed an effective method of image classification based on the introduction of high-speed search using indexed hash structures, that speeds up the calculation dozens of times; the gain in computing time increases with an increase of the number of reference images and descriptors in descriptions; the peculiarity of the classifier is that not an exact search is performed, but taking into account the permissible deviation of data from the reference; experimentally verified the effectiveness of the classification, which indicates the efficiency and effectiveness of the proposed method. The practical significance of the work is the construction of classification models in the transformed space of the hash data representation, the efficiency confirmation of the proposed classifiers modifications on image examples, development of applied software models implementing the proposed classification methods in computer vision systems.