Search

Objective. The goal is to develop a web service for detecting aerial objects that detects a flying object, highlights it in an image and classifies it as a threat, since modern aerial object detection systems do not always cope with the task of detecting unmanned aerial vehicles due to their small size, low flight altitude and the use of materials that are barely noticeable to radar stations. Unmanned aerial vehicles that operate without operator control make it difficult to detect by radio signals. To detect UAVs, it is proposed to use a system based on optical scanning of the sky around protected objects. The system should be capable of autonomous operation and include aerial object detectors created on the basis of computer vision and artificial intelligence technologies. Method. The research and development of the airspace monitoring web service are based on the methods of system analysis, synthesis, and deduction. Result. The visual part of the web interface has been designed and developed; a dataset has been formed from open sources for the correct detection of flying objects; a neural network detector has been developed for classifying flying objects that pose a danger; a software module has been developed that allows for the automatic detection of identification flags of dangerous air objects with subsequent provision of reports in txt files in yolo format (coordinates are normalized). Conclusion. Separation of the visual part of the service will allow for distributed deployment of the server part, increasing flexibility and scalability. Development of the administrator control panel will allow for effective control of the service, management of settings and users. As a result, the web service will be able to: monitor the sky around protected objects, automatically detecting and classifying air objects and identifying air objects by threat level, providing information for taking necessary measures.

An analysis of the experience of reasoned use of drones in various fields of human activity and a study of approaches to reduce the time of the end user to control the end devices of the system (drones). The expediency of using the IoT architecture to increase the flight time of each end device is proved. In addition, the analysis of energy consumption in solving the problem of tracking the domain domain object, which shows the inexpediency of using two analysis algorithms, and the proposed approach "sensor cloud", which solves the problem of reducing energy consumption on end devices of architecture and increases continuous video logging. Ref. 5, pic. 5.

The paper presents a description of the developed APC and implemented the algorithm of EyeTracking (based on convolutional neural networks and morphological analysis), which allows people suffering from motor dysfunction and neuroparalytic syndromes to carry out the process of communication with the outside world through computer control and text printing by eye movement

Face detection is one of the most popular computer vision tasks. There are a lot of face detection approaches proposed including different CNN-based techniques, but the problem of optimal balancing between detection quality and computational speed is still relevant. In this paper we propose new CNN-based solution for face detection called FaceDetectNet. Our CNN architecture is based on ideas of YOLO/DetectNet and GoogleNet architecture supported with some new tools and implementation details created especially for our face detection application. We propose: original iterative proposal clustering (IPC) algorithm for aggregation of output face proposals formed by CNN and the 2-level “weak pyramid” providing better detection quality on the testing sets containing both small and huge images. Our face detection approach is close to previously proposed SSD-based face detection, but the principal difference is that we use the deep features of top hidden CNN layer for forming the face proposals of any size. Thus we utilize the global semantic and context information for improving the detection quality for small faces. Our FaceDetectNet is trained and tested on the most challenging WIDER FACE detection benchmark. Our algorithm achieves the average precision (AP) 0.69 on the WIDER FACE hard level, and thus outperforms all competitive detectors on the Hard level besides the HR state-of-the-art solution. Note that HR solution is based on essentially deeper and slower CNN, while our FaceDetectNet can work in real-time on the NVIDIA GeForce 1080 GPU. On the other hand, SSD-based face detector with comparable CNN parameters provides AP 0.625 only on the WIDER FACE hard level. So, our approach provides the best quality with reasonable computational speed.