Indoor Environment Drone Detection through DBSCAN and Deep Learning
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In an era marked by the increasing use of drones and the growing demand for indoor surveillance, thedevelopment of a robust application for detecting and tracking both drones and humans within indoor spacesbecomes imperative. This study presents an innovative application that uses FMCW radar to detect human anddrone motions from the cloud point. At the outset, the DBSCAN (Density-based Spatial Clustering of Applicationswith Noise) algorithm is utilized to categorize cloud points into distinct groups, each representing the objectspresent in the tracking area. Notably, this algorithm demonstrates remarkable efficiency, particularly in clusteringdrone point clouds, achieving an impressive accuracy of up to 92.8%. Subsequently, the clusters are discerned andclassified into either humans or drones by employing a deep learning model. A trio of models, including DeepNeural Network (DNN), Residual Network (ResNet), and Long Short-Term Memory (LSTM), are applied, and theoutcomes reveal that the ResNet model achieves the highest accuracy. It attains an impressive 98.62% accuracy foridentifying drone clusters and a noteworthy 96.75% accuracy for human clusters.
Abstract
In an era marked by the increasing use of drones and the growing demand for indoor surveillance, thedevelopment of a robust application for detecting and tracking both drones and humans within indoor spacesbecomes imperative. This study presents an innovative application that uses FMCW radar to detect human anddrone motions from the cloud point. At the outset, the DBSCAN (Density-based Spatial Clustering of Applicationswith Noise) algorithm is utilized to categorize cloud points into distinct groups, each representing the objectspresent in the tracking area. Notably, this algorithm demonstrates remarkable efficiency, particularly in clusteringdrone point clouds, achieving an impressive accuracy of up to 92.8%. Subsequently, the clusters are discerned andclassified into either humans or drones by employing a deep learning model. A trio of models, including DeepNeural Network (DNN), Residual Network (ResNet), and Long Short-Term Memory (LSTM), are applied, and theoutcomes reveal that the ResNet model achieves the highest accuracy. It attains an impressive 98.62% accuracy foridentifying drone clusters and a noteworthy 96.75% accuracy for human clusters.
참고문헌 (11)
- S. Ahirwar, "Application of Drone in Agriculture", International Journal of Current Microbiology and Applied Sciences, 8(01), pp.2500~2505 (2019), Excellent Publishers[DOI]
- 손승우, "Applications of Drones for Environmental Monitoring of Pollutant-Emitting Facilities", 국립생태원회보, 2(4), pp.298~304 (2021), 국립생태원[DOI]
- Fan, Jin, "Applications of drones in infrastructures: Challenges and opportunities", International Journal of Mechanical and Mechatronics Engineering, 13(10), pp.649~655 (2019)[DOI]
- Björklund, S, "Target detection and classification of small drones by boosting on radar micro-Doppler", Proc. of 2018 15th European Radar Conference (EuRAD), pp.182~185 (2018)
- Jian, Michael, "Drone detection and tracking based on phase-interferometric Doppler radar", Proc. of 2018 IEEE Radar Conference (RadarConf18), pp.1146~1149 (2018)
- Junhyeong Park, "Range-Doppler Map Improvement in FMCW Radar for Small Moving Drone Detection Using the Stationary Point Concentration Technique", IEEE Transactions on Microwave Theory and Techniques, 68(5), pp.1858~1871 (2020), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Edward Companik, "Feasibility of warehouse drone adoption and implementation", Journal of Transportation Management, 28(2), pp.31~48 (2018), Wayne State University Library System[DOI]
- Applications of drones in warehouse operations, "Wawrla, L.", ETH Zurich, D-MTEC, 212~ (2019)
- Ester, Martin, "A density-based algorithm for discovering clusters in large spatial databases with noise", kdd, 96(34), pp.226~231 (1996)
- He, Kaiming, "Deep residual learning for image recognition", Proc. of the IEEE conference on computer vision and pattern recognition, pp.770~778 (2016)
- Sepp Hochreiter, "Long Short-Term Memory", Neural Computation, 9(8), pp.1735~1780 (1997), MIT Press - Journals[DOI]