Drones and helicopters classification using point clouds features from radar

Habermann, Danilo; Dranka, Eloi; Cáceres, Yusef; Val, J.B.R. do

doi:10.1109/radar.2018.8378565

Cited by 6 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the discussed work has been undertaken within ideal scenarios and usually at close range (250 m furthest [19], 30 m furthest [16,24,25]), certainly having an effect on classification performance. A further complication to the research is that not all of the aforementioned works evaluate on original radar data with many conclusions being drawn on artificially created datasets trying to emulate a UAV signature [38,39]. However, this is because radar sensors specialized for small target detection, which usually operate at an X -band are not easily accessible to a university or a research centre, and currently there is no publicly available dataset on UAV detection and classification with radar data for researchers to develop and evaluate their methods.…”

Section: Discussion and Recommendationsmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning on Multi Sensor Data for Counter UAV Applications—A Systematic Review

Samaras

Diamantidou

Ataloglou

et al. 2019

Sensors

156

View full text Add to dashboard Cite

Usage of Unmanned Aerial Vehicles (UAVs) is growing rapidly in a wide range of consumer applications, as they prove to be both autonomous and flexible in a variety of environments and tasks. However, this versatility and ease of use also brings a rapid evolution of threats by malicious actors that can use UAVs for criminal activities, converting them to passive or active threats. The need to protect critical infrastructures and important events from such threats has brought advances in counter UAV (c-UAV) applications. Nowadays, c-UAV applications offer systems that comprise a multi-sensory arsenal often including electro-optical, thermal, acoustic, radar and radio frequency sensors, whose information can be fused to increase the confidence of threat’s identification. Nevertheless, real-time surveillance is a cumbersome process, but it is absolutely essential to detect promptly the occurrence of adverse events or conditions. To that end, many challenging tasks arise such as object detection, classification, multi-object tracking and multi-sensor information fusion. In recent years, researchers have utilized deep learning based methodologies to tackle these tasks for generic objects and made noteworthy progress, yet applying deep learning for UAV detection and classification is considered a novel concept. Therefore, the need to present a complete overview of deep learning technologies applied to c-UAV related tasks on multi-sensor data has emerged. The aim of this paper is to describe deep learning advances on c-UAV related tasks when applied to data originating from many different sensors as well as multi-sensor information fusion. This survey may help in making recommendations and improvements of c-UAV applications for the future.

show abstract

Section: Discussion and Recommendationsmentioning

confidence: 99%

“…In another body of work, Habermann et al [38] studied the task of UAV and helicopter classification by utilizing point cloud features from artificial radar measurements. The authors extracted 44 features based on geometrical differences between point clouds.…”

Section: Radar Sensormentioning

confidence: 99%

Deep Learning on Multi Sensor Data for Counter UAV Applications—A Systematic Review

Samaras

Diamantidou

Ataloglou

et al. 2019

Sensors

156

View full text Add to dashboard Cite

show abstract

“…Their research validated the practicality and future prospects of employing a digital multi-channel PBR system for this purpose. Further developments in classification were presented in 2018 in [6], who tackled the distinction between UAVs and helicopters in radar returns by using point cloud features. These features were extracted from point clouds and fed into Artificial Neural Networks (ANNs) to classify different models of helicopters and drones.…”

Section: A Radar Detectionmentioning

confidence: 99%

Intelligent Identification and Classification of Small UAV Remote Control Signals Based on Improved Yolov5-7.0

Li,

Hao,

Wang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

At present, an increasing number of small UAVs(Unmanned Aerial Vehicles) are commercialized and common, and the application of small UAVs has very good development prospects, such as UAV distribution services, UAV aerial photography services, and UAV formation performance. However, the misuse of small drones poses a significant threat. Lawbreakers use small drones equipped with various sensors to spy on personal privacy, steal corporate secrets, and threaten national conferences, which have had many adverse effects on society. In future wars, these small drones will perhaps be used on the battlefield along with high-end weapons. Therefore, it is necessary to find a solution for effectively identifying the basic information of UAV. For the existence of UAV and various small UAV types, this paper proposes a combination of RF sensing and target detection techniques with target detection algorithms to learn RF signal frequency frequency hopping features to detect UAV presence and identify the detected UAV. First, the RF signal of the UAV was obtained in real time by a software radio, and the time-frequency analysis of the short-time Fourier transform and wavelet transform is performed to generate frequency domain images with retained frequency hopping features. Then, the improved Yolov5-7.0 target detection model was employed for training, and finally, the trained model was used for identification and classification. The results showed that the method can effectively assist the detection and classification of UAVs that were obtained by identifying and classifying 5400 unlabeled images. The F1 score was 0.93, and the three assessment measures of P(Precision), R(Recall), and mAP(mean Average Precision) were 1.00, 1.00, and 0.967, respectively.INDEX TERMS Small UAV, RF sensing, object detection, frequency hopping feature, short-time Fourier transform, wavelet transform, software radio.

show abstract

Detection and recognition of UA targets with multiple sensors

Chen

Chen²,

Liu

et al. 2022

Aeronaut. j.

View full text Add to dashboard Cite

Modern low-altitude unmanned aircraft (UA) detection and surveillance systems mostly adopt the multi-sensor fusion technology scheme of radar, visible light, infrared, acoustic and radio detection. Firstly, this paper summarises the latest research progress of UA and bird target detection and recognition technology based on radar, and provides an effective way of detection and recognition from the aspects of echo modeling and micro motion characteristic cognition, manoeuver feature enhancement and extraction, motion trajectory difference, deep learning intelligent classification, etc. Furthermore, this paper also analyses the target feature extraction and recognition algorithms represented by deep learning for other kinds of sensor data. Finally, after a comparison of the detection ability of various detection technologies, a technical scheme for low-altitude UA surveillance system based on four types of sensors is proposed, with a detailed description of its main performance indicators.

show abstract

Drones and helicopters classification using point clouds features from radar

Cited by 6 publications

References 12 publications

Deep Learning on Multi Sensor Data for Counter UAV Applications—A Systematic Review

Deep Learning on Multi Sensor Data for Counter UAV Applications—A Systematic Review

Intelligent Identification and Classification of Small UAV Remote Control Signals Based on Improved Yolov5-7.0

Detection and recognition of UA targets with multiple sensors

Contact Info

Product

Resources

About