At present, uncrewed aircraft (UA) are widely used around the world, in fields including aerial photography, express transportation, emergency rescue, electric power inspection, agricultural plant protection, border monitoring, mapping, fire monitoring and environmental protection. However, the rapid popularisation of UA also brings serious security problems. In recent years, the media have reported dozens of public security incidents caused by UA intrusion, whose main targets are airports, prisons, public buildings and other sensitive places.

UA detection systems generally use radar as the core, supplemented by photoelectric (visible and infrared), acoustic, radio detection and other sensors, aimed at achieving all-round situation awareness in the guarantee of major events and the defense of important places. When multiple sensors are deployed, both visible and infrared devices have some classification ability, and have more accurate positioning and ranging functions. Visible-light cameras are usually cheap, while infrared cameras are expensive, but both are sensitive to environmental conditions. In addition, although an acoustic sensor is not as sensitive to the environments, its limited detection range limits its application. Radio detection technology is sensitive to complex electromagnetic environments and is ineffective to electromagnetically silent UA. Therefore, in view of radar’s accurate positioning ability and large detection range, as well as its better target classification ability and environmental adaptability, it has become the most common UA detection means.

In this paper, “Detection and recognition of UA targets with multiple sensors”, the research work of UA detection and recognition methods based on radar, photoelectric, acoustic, radio detection sensors and multi-sensor information fusion algorithm is reviewed. The m-D feature reflects the micro-motion of the target body and components, which shows a promising ability of detection and classification. Photoelectric detection is still an important means of UA target detection and recognition. In the UA detection mission, the deployment cost of microphone arrays is low, which will help to form a complementary and robust system framework when combined with other sensors. The radio detection and positioning technology represented by TDOA can lock the position of the UA operator, which plays an irreplaceable role in multi-sensor UA detection. In addition, the application of deep learning may lead to major breakthroughs in this field in the next few years.

Due to the advantages and disadvantages of various kinds of sensors, it is almost impossible to provide the required situation awareness by using a single sensor for UA detection and identification. However, if all kinds of technologies can be mixed and complemented, it is possible to find an effective solution. In this paper, recommends a construction scheme of UA detection system is recommended, which realises all-round situation awareness in a robust way by fusing the information of four types of sensors. A long-range radar is placed in the center of the sensor coverage area. Radar is a reliable early warning method, among which the holographic radar, which can obtain all-round target fine features with high data rate, is the best, so as to provide data support for extracting target m-D features. To further correct the range and azimuth information of the detected target, multiple panoramic infrared cameras need to form complementary and cross validation at the edge of the coverage area to reduce the false alarm rate. Due to the sensitivity of infrared cameras in bad weather conditions, a visible light camera with rotation and zoom functions is placed near the radar to further improve the recognition ability. In addition, to avoid ground object occlusion, microphone arrays or TDOA stations can be distributed around the protected area to provide another complementary and alternative solution. In addition, the deployment of the TDOA array will help to complement other sensors and help trace the UA operator. Based on the deep learning method, the deep learning network for UA detection and recognition can utilise the recorded data of each sensor. Finally, the single source warning signals and features generated by each single source deep learning network are integrated with the deep learning network of multi-sensor fusion to improve the target recognition ability of the invading UA. The heterogeneity of multi-sensor data requires deep learning methods to construct joint representation data by using its internal relationship to effectively deal with the diversity of data representation. The simultaneous interpreting of different signals from different sensors can provide important knowledge aggregation compared with single sensors, which is the advantage of this scheme using multi-sensor fusion deep learning.

Read the full article online: Detection and recognition of UA targets with multiple sensors, Chen, W., Chen, X., Liu, J., Wang, Q., Lu, X., & Huang, Y. (2023),  The Aeronautical Journal, Volume 127 Issue 1308

The Royal Aeronautical Society is the world’s only professional body dedicated to the entire aerospace community. Established in 1866 to further the art, science and engineering of aeronautics, the Society has been at the forefront of developments ever since.

www.aerosociety.com | National Aerospace Library catalogue & e-books

Book reviews covering academic, scientific and technical books covering aeronautical engineering and topics relating to it can be found here. www.aerosociety.com/news-expertise/national-aerospace-library/book-reviews