Anti-drone systems: An attention based improved YOLOv7 model for a real-time detection and identification of multi-airborne target
•The paper has been revised according the reviewers ‘comments. Yellow and blue highlights indications show the new edited corrections.•For security issues, it becomes highly urgent to use anti-drone system able to identify drones from non-drone objects.•The main objective is to detect and locate the...
Saved in:
Published in | Intelligent systems with applications Vol. 20; p. 200296 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Elsevier Ltd
01.11.2023
Elsevier |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | •The paper has been revised according the reviewers ‘comments. Yellow and blue highlights indications show the new edited corrections.•For security issues, it becomes highly urgent to use anti-drone system able to identify drones from non-drone objects.•The main objective is to detect and locate the airborne target properly and in real-time.•Developing a model with the best compromise between high performance and fast speed.•Incorporating a series of improvement with CSPResNeXt module in the backbone, transformer block with C3TR and decoupled heads to enhance the performance of the model.•Using a proper methodology to retain the maximum information from the learned features.
Recently, with the significant rise of drones, reinforcing and securing aerial security and privacy has become an urgent task. Their malicious use takes benefit from the malevolent deployment which leverages some existing gaps in Artificial Intelligence (AI) and cybersecurity. Anti-drone systems are the spotlighted security solution developed to ensure aerial safety and security against rogue drones. However, the anti-drone systems are constraints to accurate airborne target identification and real-time detection to neutralize the target properly without causing damages. In this paper, we have developed a real-time multi-target detection model based on Yolov7 aiming to detect, identify and locate the airborne target properly and rapidly using a varied dataset which is biased and imbalanced due to the differences between the targets. In order to develop a model with the best compromise between a high performance and fast speed, we have used a series of improvements by incorporating the CSPResNeXt module in the backbone, a transformer block with the C3TR attention mechanism and decoupled head structure to enhance the performance of the model. The comparative and ablation experiments confirm the effectiveness of the proposed ensemble learning-based model. The experiments have shown that the improved model has reached high performance, with 0.97 precision, 0.961 recall, 0.979 map@0.50 and 0.732 and 0.979 map@0.50–0.95. Additionally, the real-time detection condition is satisfied with 92 FPS and an inference speed equal to 0.02 ms per image. The results show that the model succeeds in achieving an optimal balance between inference speed and detection performance. The proposed model achieves competitive results compared with the existing state-of-the-art models. |
---|---|
AbstractList | Recently, with the significant rise of drones, reinforcing and securing aerial security and privacy has become an urgent task. Their malicious use takes benefit from the malevolent deployment which leverages some existing gaps in Artificial Intelligence (AI) and cybersecurity. Anti-drone systems are the spotlighted security solution developed to ensure aerial safety and security against rogue drones. However, the anti-drone systems are constraints to accurate airborne target identification and real-time detection to neutralize the target properly without causing damages. In this paper, we have developed a real-time multi-target detection model based on Yolov7 aiming to detect, identify and locate the airborne target properly and rapidly using a varied dataset which is biased and imbalanced due to the differences between the targets. In order to develop a model with the best compromise between a high performance and fast speed, we have used a series of improvements by incorporating the CSPResNeXt module in the backbone, a transformer block with the C3TR attention mechanism and decoupled head structure to enhance the performance of the model. The comparative and ablation experiments confirm the effectiveness of the proposed ensemble learning-based model. The experiments have shown that the improved model has reached high performance, with 0.97 precision, 0.961 recall, 0.979 map@0.50 and 0.732 and 0.979 map@0.50–0.95. Additionally, the real-time detection condition is satisfied with 92 FPS and an inference speed equal to 0.02 ms per image. The results show that the model succeeds in achieving an optimal balance between inference speed and detection performance. The proposed model achieves competitive results compared with the existing state-of-the-art models. •The paper has been revised according the reviewers ‘comments. Yellow and blue highlights indications show the new edited corrections.•For security issues, it becomes highly urgent to use anti-drone system able to identify drones from non-drone objects.•The main objective is to detect and locate the airborne target properly and in real-time.•Developing a model with the best compromise between high performance and fast speed.•Incorporating a series of improvement with CSPResNeXt module in the backbone, transformer block with C3TR and decoupled heads to enhance the performance of the model.•Using a proper methodology to retain the maximum information from the learned features. Recently, with the significant rise of drones, reinforcing and securing aerial security and privacy has become an urgent task. Their malicious use takes benefit from the malevolent deployment which leverages some existing gaps in Artificial Intelligence (AI) and cybersecurity. Anti-drone systems are the spotlighted security solution developed to ensure aerial safety and security against rogue drones. However, the anti-drone systems are constraints to accurate airborne target identification and real-time detection to neutralize the target properly without causing damages. In this paper, we have developed a real-time multi-target detection model based on Yolov7 aiming to detect, identify and locate the airborne target properly and rapidly using a varied dataset which is biased and imbalanced due to the differences between the targets. In order to develop a model with the best compromise between a high performance and fast speed, we have used a series of improvements by incorporating the CSPResNeXt module in the backbone, a transformer block with the C3TR attention mechanism and decoupled head structure to enhance the performance of the model. The comparative and ablation experiments confirm the effectiveness of the proposed ensemble learning-based model. The experiments have shown that the improved model has reached high performance, with 0.97 precision, 0.961 recall, 0.979 map@0.50 and 0.732 and 0.979 map@0.50–0.95. Additionally, the real-time detection condition is satisfied with 92 FPS and an inference speed equal to 0.02 ms per image. The results show that the model succeeds in achieving an optimal balance between inference speed and detection performance. The proposed model achieves competitive results compared with the existing state-of-the-art models. |
ArticleNumber | 200296 |
Author | Yasmine, Ghazlane Maha, Gmira Hicham, Medromi |
Author_xml | – sequence: 1 givenname: Ghazlane orcidid: 0000-0002-9665-1005 surname: Yasmine fullname: Yasmine, Ghazlane email: y.ghazlane@ueuromed.org organization: School of Digital Engineering and Artificial Intelligence, Euromed Research Center, Euromed University, Fes, 30110, Morocco – sequence: 2 givenname: Gmira surname: Maha fullname: Maha, Gmira organization: School of Digital Engineering and Artificial Intelligence, Euromed Research Center, Euromed University, Fes, 30110, Morocco – sequence: 3 givenname: Medromi surname: Hicham fullname: Hicham, Medromi organization: Research Foundation for Development and Innovation in Science and Engineering (FRDISI), Casablanca, 16469, Morocco |
BookMark | eNp9kU1vGyEQhlGVSk2T_IGe-APr8rWwjnKxon5EsuRLLjmhAWYjrN0lAuIo1_7yYruqeuoFRjO8z8zwfiYXS1qQkC-crTjj-ut-FcsbrAQTsh1MrPUHcim0Np1kvbz4J_5EbkrZs_Zm4FwqdUl-bZYau5AbkZb3UnEut3SzUKgVWyUt1EHBQOP8ktOhBU-77e5g6JwCTnRMmQLNCFNX44w0YEV_UsHSNOGIGKOHUyqNdH6dWjeI2aXcGlbIz1ivyccRpoI3f-4r8vj92-P9z267-_Fwv9l2Xopedw70WjHEIQQnmRsc44NA7Z00PeMjQ6MH4xQfAHsUXgnj5VpoIaUCr4y8Ig9nbEiwty85zpDfbYJoT4mUny3kGv2E1qFUPWdu7QNTQYEzCvrApHGmH3s5NJY4s3xOpWQc__I4s0dP7N4ePbFHT-zZkya6O4uwLXmImG3xERePIeb2a22M-D_5b9qCl50 |
CitedBy_id | crossref_primary_10_1007_s12198_024_00280_w crossref_primary_10_1080_08839514_2024_2318672 |
Cites_doi | 10.1109/ACCESS.2022.3210182 10.1109/MCOM.2018.1700430 10.3390/aerospace9010031 10.1007/s00521-022-08077-5 10.1109/TPAMI.2015.2389824 10.1109/IRC55401.2022.00024 10.1109/ICCVW54120.2021.00142 10.1109/CVPR52729.2023.00721 10.1109/ACCESS.2021.3065926 10.1504/IJSSE.2022.125947 10.1109/SYNASC.2018.00041 10.3390/jimaging8080218 10.3390/electronics11152330 10.1109/CVPR.2017.634 10.1109/ICCV.2019.00612 10.1002/widm.1255 10.3390/drones6020046 10.1109/ICCVW54120.2021.00312 10.3390/drones5030095 10.3390/s20123537 10.1109/ACCESS.2020.3026192 10.1155/2022/8929437 10.1007/978-3-030-01234-2_1 10.1109/IWCMC58020.2023.10182423 10.1007/s11704-019-8208-z |
ContentType | Journal Article |
Copyright | 2023 The Author(s) |
Copyright_xml | – notice: 2023 The Author(s) |
DBID | 6I. AAFTH AAYXX CITATION DOA |
DOI | 10.1016/j.iswa.2023.200296 |
DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef DOAJ Directory of Open Access Journals |
DatabaseTitle | CrossRef |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Computer Science |
EISSN | 2667-3053 |
ExternalDocumentID | oai_doaj_org_article_be34510b9cd04d4ab74a5d037b75f538 10_1016_j_iswa_2023_200296 S2667305323001217 |
GroupedDBID | 6I. AAFTH AAXUO ALMA_UNASSIGNED_HOLDINGS AMRAJ FDB GROUPED_DOAJ M41 M~E ROL 0R~ 0SF AALRI AAYXX ADVLN AITUG CITATION |
ID | FETCH-LOGICAL-c3256-ba6940ee8ddb30b8b0182e6cb37501f0e7687b418ae5e2c427c39262334ac473 |
IEDL.DBID | DOA |
ISSN | 2667-3053 |
IngestDate | Thu Jul 04 21:04:55 EDT 2024 Fri Aug 23 04:02:05 EDT 2024 Sat Feb 24 15:48:24 EST 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Keywords | Deep learning Airspace safety Real-time detection Drone identification |
Language | English |
License | This is an open access article under the CC BY license. |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c3256-ba6940ee8ddb30b8b0182e6cb37501f0e7687b418ae5e2c427c39262334ac473 |
ORCID | 0000-0002-9665-1005 |
OpenAccessLink | https://doaj.org/article/be34510b9cd04d4ab74a5d037b75f538 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_be34510b9cd04d4ab74a5d037b75f538 crossref_primary_10_1016_j_iswa_2023_200296 elsevier_sciencedirect_doi_10_1016_j_iswa_2023_200296 |
PublicationCentury | 2000 |
PublicationDate | November 2023 2023-11-00 2023-11-01 |
PublicationDateYYYYMMDD | 2023-11-01 |
PublicationDate_xml | – month: 11 year: 2023 text: November 2023 |
PublicationDecade | 2020 |
PublicationTitle | Intelligent systems with applications |
PublicationYear | 2023 |
Publisher | Elsevier Ltd Elsevier |
Publisher_xml | – name: Elsevier Ltd – name: Elsevier |
References | Wang, Chen, Dong, Gao (bib0038) 2023; 35 arXiv. Xie, S., Girshick, R., Dollár, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks (arXiv:1611.05431). arXiv. Isaac-Medina, B.K.S., Poyser, M., Organisciak, D., Willcocks, C.G., Breckon, T.P., & Shum, H.P.H. (2021). Unmanned aerial vehicle visual detection and tracking using deep neural networks: A performance benchmark. ArXiv:2103.13933 [Cs]. Caltech-UCSD Birds-200-2011. (2022). Retrieved March 7, 2022, from Samadzadegan, Dadrass Javan, Ashtari Mahini, Gholamshahi (bib0028) 2022; 9 Singha, Aydin (bib0031) 2021; 5 Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y.M. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors (arXiv:2207.02696). arXiv. Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y.M. (2020). YOLOv4: Optimal speed and accuracy of object detection (arXiv:2004.10934). arXiv. Rao, Y., Zhao, W., Tang, Y., Zhou, J., Lim, S.-N., & Lu, J. (2022). HorNet: Efficient high-order spatial interactions with recursive gated convolutions (arXiv:2207.14284). arXiv. Tan, Lee, Lim, Anbananthen (bib0033) 2022; 10 Garcia, Min Lee, Kim (bib0013) 2020 Kim, J., Lee, D., Kim, Y., Shin, H., Heo, Y., Wang, Y., & Matson, E. T. (2022). Deep learning based malicious drone detection using acoustic and image data. 7. Woo, Debnath, Hu, Chen, Liu, Kweon, Xie (bib0041) 2023 . Zhang, H., Cisse, M., Dauphin, Y.N., & Lopez-Paz, D. (2018). mixup: Beyond empirical risk minimization (arXiv:1710.09412). arXiv. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16×16 words: Transformers for image recognition at scale Ultralytics/yolov5. (2022). [Python]. Ultralytics. Al-Qubaydhi, Alenezi, Alanazi, Senyor, Alanezi, Alotaibi, Alotaibi, Abdelhamid, Razaque, Alotaibi (bib0004) 2022 Wang, Li, Guo, Cao (bib0039) 2021 Chujai, Chomboon, Teerarassamee, Kerdprasop, Kerdprasop (bib0008) 2015 Wang, Mark Liao, Wu, Chen, Hsieh, Yeh (bib0037) 2020 Dong, Yu, Cao, Shi, Ma (bib0009) 2020; 14 Wu, B., Xu, C., Dai, X., Wan, A., Zhang, P., Yan, Z., Tomizuka, M., Gonzalez, J., Keutzer, K., & Vajda, P. (2020). Visual transformers: Token-based image representation and processing for computer vision (arXiv:2006.03677). arXiv. Ge, Z., Liu, S., Wang, F., Li, Z., & Sun, J. (2021). YOLOX: Exceeding YOLO Series in 2021 Redmon, Divvala, Girshick, Farhadi (bib0026) 2016 Zhu, X., Lyu, S., Wang, X., & Zhao, Q. (2021). TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. Fujii, Akita, Ukita (bib0012) 2021 Wisniewski, Rana, Petrunin (bib0040) 2022; 8 Ajakwe, S.O., Ihekoronye, V.U., Kim, D.-S., & Lee, J.M. (2022). Scenario-based drone detection and identification system for real-time industrial facility aerial surveillance and safety. 4. Lykou, Moustakas, Gritzalis (bib0021) 2020; 20 Yasmine, G., Maha, G., & Hicham, M. (2023). Overview of single-stage object detection models: From Yolov1 to Yolov7. 2023 International wireless communications and mobile computing (IWCMC), 1579–1584. Schindler, Lidy, Rauber (bib0029) 2016; 5 Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., & Yoo, Y. (2019). CutMix: Regularization strategy to train strong classifiers with localizable features (arXiv:1905.04899). arXiv. MacKay (bib0022) 1995 Pawełczyk, Wojtyra (bib0024) 2020; 8 Roboflow Universe: Open source computer vision community. (2022). Roboflow. Retrieved November 1, 2022, from Akyon, Eryuksel, Ozfuttu, Altinuc (bib0003) 2021 Ajakwe, Ihekoronye, Kim, Lee (bib0002) 2022; 6 Behera, Bazil Raj (bib0005) 2020 Hu, J., Shen, L., Albanie, S., Sun, G., & Wu, E. (2019). Squeeze-and-excitation networks Sagi, Rokach (bib0011) 2018; 8 Liu, L., Liu, J., & Han, J. (2021). Multi-head or single-head? An empirical comparison for transformer training (arXiv:2106.09650). arXiv. Liu, Luo (bib0019) 2022; 11 (Original work published 2020). He, Zhang, Ren, Sun (bib0015) 2015; 37 Yasmine, Maha, Hicham (bib0045) 2022; 12 Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is All you Need. Woo, S., Park, J., Lee, J.-Y., & Kweon, I.S. (2018). CBAM: Convolutional block attention module. 3–19. Soviany, P., & Ionescu, R.T. (2018). Optimizing the trade-off between single-stage and two-stage object detectors using image difficulty prediction. ArXiv:1803.08707 [Cs]. Shi, Yang, Xie, Liang, Shi, Chen (bib0030) 2018; 56 Zhuang, Xing, Fan, Gao, Zhang (bib0051) 2022; 2022 Zhong, Ling, Wang (bib0049) 2019; 9 Park, Kim, Lee, Joo, Kim (bib0023) 2021; 9 Singha (10.1016/j.iswa.2023.200296_bib0031) 2021; 5 Woo (10.1016/j.iswa.2023.200296_bib0041) 2023 Tan (10.1016/j.iswa.2023.200296_bib0033) 2022; 10 Lykou (10.1016/j.iswa.2023.200296_bib0021) 2020; 20 10.1016/j.iswa.2023.200296_bib0036 10.1016/j.iswa.2023.200296_bib0035 Park (10.1016/j.iswa.2023.200296_bib0023) 2021; 9 Wang (10.1016/j.iswa.2023.200296_bib0038) 2023; 35 10.1016/j.iswa.2023.200296_bib0034 10.1016/j.iswa.2023.200296_bib0032 Dong (10.1016/j.iswa.2023.200296_bib0009) 2020; 14 Wang (10.1016/j.iswa.2023.200296_bib0039) 2021 Zhong (10.1016/j.iswa.2023.200296_bib0049) 2019; 9 Al-Qubaydhi (10.1016/j.iswa.2023.200296_bib0004) 2022 Chujai (10.1016/j.iswa.2023.200296_bib0008) 2015 10.1016/j.iswa.2023.200296_bib0027 10.1016/j.iswa.2023.200296_bib0025 Redmon (10.1016/j.iswa.2023.200296_bib0026) 2016 10.1016/j.iswa.2023.200296_bib0020 Samadzadegan (10.1016/j.iswa.2023.200296_bib0028) 2022; 9 MacKay (10.1016/j.iswa.2023.200296_bib0022) 1995 Liu (10.1016/j.iswa.2023.200296_bib0019) 2022; 11 Zhuang (10.1016/j.iswa.2023.200296_bib0051) 2022; 2022 Fujii (10.1016/j.iswa.2023.200296_bib0012) 2021 10.1016/j.iswa.2023.200296_bib0016 10.1016/j.iswa.2023.200296_bib0014 Behera (10.1016/j.iswa.2023.200296_bib0005) 2020 10.1016/j.iswa.2023.200296_bib0018 Sagi (10.1016/j.iswa.2023.200296_bib0011) 2018; 8 10.1016/j.iswa.2023.200296_bib0017 10.1016/j.iswa.2023.200296_bib0050 10.1016/j.iswa.2023.200296_bib0010 Yasmine (10.1016/j.iswa.2023.200296_bib0045) 2022; 12 Pawełczyk (10.1016/j.iswa.2023.200296_bib0024) 2020; 8 Wisniewski (10.1016/j.iswa.2023.200296_bib0040) 2022; 8 10.1016/j.iswa.2023.200296_bib0048 10.1016/j.iswa.2023.200296_bib0047 Wang (10.1016/j.iswa.2023.200296_bib0037) 2020 10.1016/j.iswa.2023.200296_bib0046 10.1016/j.iswa.2023.200296_bib0007 He (10.1016/j.iswa.2023.200296_bib0015) 2015; 37 Shi (10.1016/j.iswa.2023.200296_bib0030) 2018; 56 10.1016/j.iswa.2023.200296_bib0006 Schindler (10.1016/j.iswa.2023.200296_bib0029) 2016; 5 10.1016/j.iswa.2023.200296_bib0001 10.1016/j.iswa.2023.200296_bib0044 Ajakwe (10.1016/j.iswa.2023.200296_bib0002) 2022; 6 10.1016/j.iswa.2023.200296_bib0043 10.1016/j.iswa.2023.200296_bib0042 Akyon (10.1016/j.iswa.2023.200296_bib0003) 2021 Garcia (10.1016/j.iswa.2023.200296_bib0013) 2020 |
References_xml | – volume: 14 start-page: 241 year: 2020 end-page: 258 ident: bib0009 article-title: A survey on ensemble learning publication-title: Frontiers of Computer Science contributor: fullname: Ma – volume: 2022 start-page: 1 year: 2022 end-page: 13 ident: bib0051 article-title: An integrated model for on-site teaching quality evaluation based on deep learning publication-title: Wireless Communications and Mobile Computing contributor: fullname: Zhang – start-page: 559 year: 2020 end-page: 561 ident: bib0013 article-title: Anti-drone system: A visual-based drone detection using neural networks publication-title: 2020 International Conference on Information and Communication Technology Convergence (ICTC) contributor: fullname: Kim – year: 1995 ident: bib0022 publication-title: Ensemble learning and evidence maximization contributor: fullname: MacKay – volume: 6 start-page: 46 year: 2022 ident: bib0002 article-title: DRONET: Multi-tasking framework for real-time industrial facility aerial surveillance and safety publication-title: Drones contributor: fullname: Lee – volume: 8 year: 2018 ident: bib0011 article-title: Ensemble learning: A survey. publication-title: Discovery contributor: fullname: Rokach – volume: 8 start-page: 218 year: 2022 ident: bib0040 article-title: Drone model classification using convolutional neural network trained on synthetic data publication-title: Journal of Imaging contributor: fullname: Petrunin – volume: 5 start-page: 95 year: 2021 ident: bib0031 article-title: Automated drone detection using YOLOv4 publication-title: Drones contributor: fullname: Aydin – volume: 10 start-page: 103694 year: 2022 end-page: 103704 ident: bib0033 article-title: Sentiment analysis with ensemble hybrid deep learning model publication-title: IEEE access : practical innovations, open solutions contributor: fullname: Anbananthen – volume: 5 year: 2016 ident: bib0029 publication-title: Comparing shallow versus deep neural network architectures for automatic music genre classification contributor: fullname: Rauber – start-page: 16133 year: 2023 end-page: 16142 ident: bib0041 publication-title: ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders contributor: fullname: Xie – volume: 12 start-page: 235 year: 2022 end-page: 270 ident: bib0045 article-title: Survey on current anti-drone systems: Process, technologies, and algorithms publication-title: International Journal of System of Systems Engineering contributor: fullname: Hicham – start-page: 779 year: 2016 end-page: 788 ident: bib0026 article-title: You only look once: Unified, real-time object detection publication-title: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) contributor: fullname: Farhadi – year: 2022 ident: bib0004 article-title: Unauthorized unmanned aerial vehicle detection using YOLOv5 and transfer learning [Preprint] publication-title: ENGINEERING contributor: fullname: Alotaibi – volume: 9 year: 2019 ident: bib0049 article-title: From shallow feature learning to deep learning: Benefits from the width and depth of deep architectures publication-title: WIREs Data Mining and Knowledge Discovery contributor: fullname: Wang – start-page: 1 year: 2021 end-page: 5 ident: bib0012 article-title: Distant bird detection for safe drone flight and its dataset publication-title: 17th International Conference on Machine Vision and Applications (MVA) contributor: fullname: Ukita – volume: 11 start-page: 2330 year: 2022 ident: bib0019 article-title: An improved Yolov5 for multi-rotor UAV detection publication-title: Electronics contributor: fullname: Luo – start-page: 1571 year: 2020 end-page: 1580 ident: bib0037 article-title: CSPNet: A new backbone that can enhance learning capability of CNN publication-title: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) contributor: fullname: Yeh – volume: 35 start-page: 7853 year: 2023 end-page: 7865 ident: bib0038 article-title: Improved YOLOv5 network for real-time multi-scale traffic sign detection publication-title: Neural Computing and Applications contributor: fullname: Gao – volume: 9 start-page: 42635 year: 2021 end-page: 42659 ident: bib0023 article-title: Survey on anti-drone systems: Components, designs, and challenges publication-title: IEEE Access contributor: fullname: Kim – volume: 9 start-page: 31 year: 2022 ident: bib0028 article-title: Detection and Recognition of Drones Based on a Deep Convolutional Neural Network Using Visible Imagery publication-title: Aerospace contributor: fullname: Gholamshahi – start-page: 1 year: 2021 end-page: 5 ident: bib0003 article-title: Track boosting and synthetic data aided drone detection publication-title: 2021 17th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) contributor: fullname: Altinuc – volume: 8 start-page: 174394 year: 2020 end-page: 174409 ident: bib0024 article-title: Real world object detection dataset for quadcopter unmanned aerial vehicle detection publication-title: IEEE access : practical innovations, open solutions contributor: fullname: Wojtyra – start-page: 1012 year: 2020 end-page: 1016 ident: bib0005 article-title: Drone detection and classification using deep learning publication-title: 2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS) contributor: fullname: Bazil Raj – volume: 20 start-page: 3537 year: 2020 ident: bib0021 article-title: Defending airports from UAS: A survey on cyber-attacks and counter-drone sensing technologies publication-title: Sensors contributor: fullname: Gritzalis – volume: 56 start-page: 68 year: 2018 end-page: 74 ident: bib0030 article-title: Anti-drone system with multiple surveillance technologies: Architecture, implementation, and challenges publication-title: IEEE Communications Magazine contributor: fullname: Chen – start-page: 449 year: 2015 end-page: 456 ident: bib0008 article-title: Ensemble learning for imbalanced data classification problem publication-title: The Proceedings of the 2nd International Conference on Industrial Application Engineering contributor: fullname: Kerdprasop – start-page: 099 year: 2021 end-page: 104 ident: bib0039 article-title: SPB-YOLO: An efficient real-time detector for unmanned aerial vehicle images publication-title: 2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) contributor: fullname: Cao – volume: 37 start-page: 1904 year: 2015 end-page: 1916 ident: bib0015 article-title: Spatial pyramid pooling in deep convolutional networks for visual recognition publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence contributor: fullname: Sun – volume: 8 issue: 4 year: 2018 ident: 10.1016/j.iswa.2023.200296_bib0011 article-title: Ensemble learning: A survey. WIREs Data Mining and Knowledge publication-title: Discovery contributor: fullname: Sagi – volume: 10 start-page: 103694 year: 2022 ident: 10.1016/j.iswa.2023.200296_bib0033 article-title: Sentiment analysis with ensemble hybrid deep learning model publication-title: IEEE access : practical innovations, open solutions doi: 10.1109/ACCESS.2022.3210182 contributor: fullname: Tan – start-page: 449 year: 2015 ident: 10.1016/j.iswa.2023.200296_bib0008 article-title: Ensemble learning for imbalanced data classification problem contributor: fullname: Chujai – volume: 56 start-page: 68 issue: 4 year: 2018 ident: 10.1016/j.iswa.2023.200296_bib0030 article-title: Anti-drone system with multiple surveillance technologies: Architecture, implementation, and challenges publication-title: IEEE Communications Magazine doi: 10.1109/MCOM.2018.1700430 contributor: fullname: Shi – volume: 9 start-page: 31 issue: 1 year: 2022 ident: 10.1016/j.iswa.2023.200296_bib0028 article-title: Detection and Recognition of Drones Based on a Deep Convolutional Neural Network Using Visible Imagery publication-title: Aerospace doi: 10.3390/aerospace9010031 contributor: fullname: Samadzadegan – volume: 35 start-page: 7853 issue: 10 year: 2023 ident: 10.1016/j.iswa.2023.200296_bib0038 article-title: Improved YOLOv5 network for real-time multi-scale traffic sign detection publication-title: Neural Computing and Applications doi: 10.1007/s00521-022-08077-5 contributor: fullname: Wang – ident: 10.1016/j.iswa.2023.200296_bib0016 – start-page: 1 year: 2021 ident: 10.1016/j.iswa.2023.200296_bib0003 article-title: Track boosting and synthetic data aided drone detection contributor: fullname: Akyon – ident: 10.1016/j.iswa.2023.200296_bib0035 – ident: 10.1016/j.iswa.2023.200296_bib0006 – volume: 37 start-page: 1904 issue: 9 year: 2015 ident: 10.1016/j.iswa.2023.200296_bib0015 article-title: Spatial pyramid pooling in deep convolutional networks for visual recognition publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2015.2389824 contributor: fullname: He – ident: 10.1016/j.iswa.2023.200296_bib0018 doi: 10.1109/IRC55401.2022.00024 – year: 1995 ident: 10.1016/j.iswa.2023.200296_bib0022 contributor: fullname: MacKay – ident: 10.1016/j.iswa.2023.200296_bib0048 – ident: 10.1016/j.iswa.2023.200296_bib0017 doi: 10.1109/ICCVW54120.2021.00142 – ident: 10.1016/j.iswa.2023.200296_bib0025 – start-page: 16133 year: 2023 ident: 10.1016/j.iswa.2023.200296_bib0041 publication-title: ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders contributor: fullname: Woo – ident: 10.1016/j.iswa.2023.200296_bib0036 doi: 10.1109/CVPR52729.2023.00721 – volume: 9 start-page: 42635 year: 2021 ident: 10.1016/j.iswa.2023.200296_bib0023 article-title: Survey on anti-drone systems: Components, designs, and challenges publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3065926 contributor: fullname: Park – volume: 12 start-page: 235 issue: 3 year: 2022 ident: 10.1016/j.iswa.2023.200296_bib0045 article-title: Survey on current anti-drone systems: Process, technologies, and algorithms publication-title: International Journal of System of Systems Engineering doi: 10.1504/IJSSE.2022.125947 contributor: fullname: Yasmine – start-page: 1 year: 2021 ident: 10.1016/j.iswa.2023.200296_bib0012 article-title: Distant bird detection for safe drone flight and its dataset contributor: fullname: Fujii – ident: 10.1016/j.iswa.2023.200296_bib0032 doi: 10.1109/SYNASC.2018.00041 – volume: 8 start-page: 218 issue: 8 year: 2022 ident: 10.1016/j.iswa.2023.200296_bib0040 article-title: Drone model classification using convolutional neural network trained on synthetic data publication-title: Journal of Imaging doi: 10.3390/jimaging8080218 contributor: fullname: Wisniewski – ident: 10.1016/j.iswa.2023.200296_bib0043 – ident: 10.1016/j.iswa.2023.200296_bib0020 – volume: 11 start-page: 2330 issue: 15 year: 2022 ident: 10.1016/j.iswa.2023.200296_bib0019 article-title: An improved Yolov5 for multi-rotor UAV detection publication-title: Electronics doi: 10.3390/electronics11152330 contributor: fullname: Liu – ident: 10.1016/j.iswa.2023.200296_bib0044 doi: 10.1109/CVPR.2017.634 – ident: 10.1016/j.iswa.2023.200296_bib0047 doi: 10.1109/ICCV.2019.00612 – volume: 9 issue: 1 year: 2019 ident: 10.1016/j.iswa.2023.200296_bib0049 article-title: From shallow feature learning to deep learning: Benefits from the width and depth of deep architectures publication-title: WIREs Data Mining and Knowledge Discovery doi: 10.1002/widm.1255 contributor: fullname: Zhong – volume: 5 year: 2016 ident: 10.1016/j.iswa.2023.200296_bib0029 publication-title: Comparing shallow versus deep neural network architectures for automatic music genre classification contributor: fullname: Schindler – volume: 6 start-page: 46 issue: 2 year: 2022 ident: 10.1016/j.iswa.2023.200296_bib0002 article-title: DRONET: Multi-tasking framework for real-time industrial facility aerial surveillance and safety publication-title: Drones doi: 10.3390/drones6020046 contributor: fullname: Ajakwe – ident: 10.1016/j.iswa.2023.200296_bib0014 – ident: 10.1016/j.iswa.2023.200296_bib0050 doi: 10.1109/ICCVW54120.2021.00312 – volume: 5 start-page: 95 issue: 3 year: 2021 ident: 10.1016/j.iswa.2023.200296_bib0031 article-title: Automated drone detection using YOLOv4 publication-title: Drones doi: 10.3390/drones5030095 contributor: fullname: Singha – start-page: 1571 year: 2020 ident: 10.1016/j.iswa.2023.200296_bib0037 article-title: CSPNet: A new backbone that can enhance learning capability of CNN contributor: fullname: Wang – volume: 20 start-page: 3537 issue: 12 year: 2020 ident: 10.1016/j.iswa.2023.200296_bib0021 article-title: Defending airports from UAS: A survey on cyber-attacks and counter-drone sensing technologies publication-title: Sensors doi: 10.3390/s20123537 contributor: fullname: Lykou – volume: 8 start-page: 174394 year: 2020 ident: 10.1016/j.iswa.2023.200296_bib0024 article-title: Real world object detection dataset for quadcopter unmanned aerial vehicle detection publication-title: IEEE access : practical innovations, open solutions doi: 10.1109/ACCESS.2020.3026192 contributor: fullname: Pawełczyk – volume: 2022 start-page: 1 year: 2022 ident: 10.1016/j.iswa.2023.200296_bib0051 article-title: An integrated model for on-site teaching quality evaluation based on deep learning publication-title: Wireless Communications and Mobile Computing doi: 10.1155/2022/8929437 contributor: fullname: Zhuang – ident: 10.1016/j.iswa.2023.200296_bib0042 doi: 10.1007/978-3-030-01234-2_1 – ident: 10.1016/j.iswa.2023.200296_bib0027 – ident: 10.1016/j.iswa.2023.200296_bib0046 doi: 10.1109/IWCMC58020.2023.10182423 – volume: 14 start-page: 241 issue: 2 year: 2020 ident: 10.1016/j.iswa.2023.200296_bib0009 article-title: A survey on ensemble learning publication-title: Frontiers of Computer Science doi: 10.1007/s11704-019-8208-z contributor: fullname: Dong – start-page: 099 year: 2021 ident: 10.1016/j.iswa.2023.200296_bib0039 article-title: SPB-YOLO: An efficient real-time detector for unmanned aerial vehicle images contributor: fullname: Wang – start-page: 559 year: 2020 ident: 10.1016/j.iswa.2023.200296_bib0013 article-title: Anti-drone system: A visual-based drone detection using neural networks contributor: fullname: Garcia – start-page: 779 year: 2016 ident: 10.1016/j.iswa.2023.200296_bib0026 article-title: You only look once: Unified, real-time object detection contributor: fullname: Redmon – ident: 10.1016/j.iswa.2023.200296_bib0034 – ident: 10.1016/j.iswa.2023.200296_bib0007 – year: 2022 ident: 10.1016/j.iswa.2023.200296_bib0004 article-title: Unauthorized unmanned aerial vehicle detection using YOLOv5 and transfer learning [Preprint] publication-title: ENGINEERING contributor: fullname: Al-Qubaydhi – ident: 10.1016/j.iswa.2023.200296_bib0010 – ident: 10.1016/j.iswa.2023.200296_bib0001 doi: 10.3390/drones6020046 – start-page: 1012 year: 2020 ident: 10.1016/j.iswa.2023.200296_bib0005 article-title: Drone detection and classification using deep learning contributor: fullname: Behera |
SSID | ssj0002811344 |
Score | 2.2957702 |
Snippet | •The paper has been revised according the reviewers ‘comments. Yellow and blue highlights indications show the new edited corrections.•For security issues, it... Recently, with the significant rise of drones, reinforcing and securing aerial security and privacy has become an urgent task. Their malicious use takes... |
SourceID | doaj crossref elsevier |
SourceType | Open Website Aggregation Database Publisher |
StartPage | 200296 |
SubjectTerms | Airspace safety Deep learning Drone identification Real-time detection |
Title | Anti-drone systems: An attention based improved YOLOv7 model for a real-time detection and identification of multi-airborne target |
URI | https://dx.doi.org/10.1016/j.iswa.2023.200296 https://doaj.org/article/be34510b9cd04d4ab74a5d037b75f538 |
Volume | 20 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELZQJxbeiPKSBzZk4cR2nLIV1KpCQJcilSmKH5FSoRS1ATYGfjlnO0GZYGGJoiiOE9859531-TuELpRkTAwiRQBrWwL5hiFpIS0pdJFIqVmkrWf5PiaTJ343F_NOqS_HCQvywGHgrpRlHPxGDbSh3PBcSZ4LQ5lUUhQwW_3fNxKdZGrhl4yiiHHe7JIJhK5y_eGEhmLmiQlOpb8TibxgfycgdYLMeAdtNegQD8Nb7aINW-2h7bbyAm4m4j76GlZ1ScxqWVkctJjX13hYYSeW6emL2EUng0u_ZAAnz9P76bvEvu4NBpyKcwxo8YW40vLY2NoTsqB9BW1MQyDyNsPLAnvSIcnLFfgLdBjI4wdoNh7NbiekqaZANANcQ1SeDDi1NjVGMapSRSG1sIlWDEBDVFALiYdUPEpzK2yseQyWcmKCjPFcc8kOUa-CrzpCOI21ihKhtRCGJ4pDSiIY5RYmc15wQfvosh3Y7DVoZmQtmWyROTNkzgxZMEMf3bix_7nT6V37C-AFWeMF2V9e0EeitVzWQIcACeBR5S-dH_9H5ydo0z0y7FA8Rb169WbPAKrU6tx7JRwfPkff437oJw |
link.rule.ids | 315,786,790,870,2115,27957,27958 |
linkProvider | Directory of Open Access Journals |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Anti-drone+systems%3A+An+attention+based+improved+YOLOv7+model+for+a+real-time+detection+and+identification+of+multi-airborne+target&rft.jtitle=Intelligent+systems+with+applications&rft.au=Yasmine%2C+Ghazlane&rft.au=Maha%2C+Gmira&rft.au=Hicham%2C+Medromi&rft.date=2023-11-01&rft.pub=Elsevier+Ltd&rft.issn=2667-3053&rft.eissn=2667-3053&rft.volume=20&rft_id=info:doi/10.1016%2Fj.iswa.2023.200296&rft.externalDocID=S2667305323001217 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2667-3053&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2667-3053&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2667-3053&client=summon |