Lightweight resilience: Advancing visual-inertial odometry with deep convolutional networks and an intelligent learnable Kalman filter for defense against laser remote attacks
A combination of multiple positioning sources is often employed to achieve precise and high-rate localization, especially in indoor applications where satellite-based navigation systems are not feasible. This paper presents a super-robust Visual-Inertial Odometry (VIO) system designed to counter las...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Ain Shams Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2090447924005562 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526304170573824 |
|---|---|
| author | A. Ebrahimi M.R. Mosavi A. Ayatollahi |
| author_facet | A. Ebrahimi M.R. Mosavi A. Ayatollahi |
| author_sort | A. Ebrahimi |
| collection | DOAJ |
| description | A combination of multiple positioning sources is often employed to achieve precise and high-rate localization, especially in indoor applications where satellite-based navigation systems are not feasible. This paper presents a super-robust Visual-Inertial Odometry (VIO) system designed to counter laser-induced attacks on camera lenses, a critical vulnerability in visual localization systems. The proposed system integrates lightweight Convolutional Neural Networks (CNNs) to enhance robustness against such attacks. To address power constraints in applications such as battery-powered systems, the solution employs an Intelligent Learnable Kalman Filter (ILKF) for fusing multiple positioning sources, offering a more efficient alternative to Recurrent Neural Networks (RNNs). Simulation results show that the proposed system achieves a 23.09 % improvement in localization accuracy compared to pure INS and a 4.01 % improvement compared to existing robust VIO systems under attack conditions. Additionally, the system reduces the negative impact of laser attacks by 96 %, making it highly suitable for precise indoor navigation in environments where satellite-based systems are unavailable. |
| format | Article |
| id | doaj-art-d3131854b20b48e3bd942aab0a4fd5d9 |
| institution | Kabale University |
| issn | 2090-4479 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ain Shams Engineering Journal |
| spelling | doaj-art-d3131854b20b48e3bd942aab0a4fd5d92025-01-17T04:49:18ZengElsevierAin Shams Engineering Journal2090-44792025-01-01161103175Lightweight resilience: Advancing visual-inertial odometry with deep convolutional networks and an intelligent learnable Kalman filter for defense against laser remote attacksA. Ebrahimi0M.R. Mosavi1A. Ayatollahi2Department of Electrical Engineering, Iran University of Science and Technology, Tehran 16846-13114, IranCorresponding author.; Department of Electrical Engineering, Iran University of Science and Technology, Tehran 16846-13114, IranDepartment of Electrical Engineering, Iran University of Science and Technology, Tehran 16846-13114, IranA combination of multiple positioning sources is often employed to achieve precise and high-rate localization, especially in indoor applications where satellite-based navigation systems are not feasible. This paper presents a super-robust Visual-Inertial Odometry (VIO) system designed to counter laser-induced attacks on camera lenses, a critical vulnerability in visual localization systems. The proposed system integrates lightweight Convolutional Neural Networks (CNNs) to enhance robustness against such attacks. To address power constraints in applications such as battery-powered systems, the solution employs an Intelligent Learnable Kalman Filter (ILKF) for fusing multiple positioning sources, offering a more efficient alternative to Recurrent Neural Networks (RNNs). Simulation results show that the proposed system achieves a 23.09 % improvement in localization accuracy compared to pure INS and a 4.01 % improvement compared to existing robust VIO systems under attack conditions. Additionally, the system reduces the negative impact of laser attacks by 96 %, making it highly suitable for precise indoor navigation in environments where satellite-based systems are unavailable.http://www.sciencedirect.com/science/article/pii/S2090447924005562Visual-Inertial Odometry (VIO)Inertial Measurement Unit (IMU)Inertial Navigation System (INS)Laser AttackIntegrationArtificial Intelligent (AI) |
| spellingShingle | A. Ebrahimi M.R. Mosavi A. Ayatollahi Lightweight resilience: Advancing visual-inertial odometry with deep convolutional networks and an intelligent learnable Kalman filter for defense against laser remote attacks Ain Shams Engineering Journal Visual-Inertial Odometry (VIO) Inertial Measurement Unit (IMU) Inertial Navigation System (INS) Laser Attack Integration Artificial Intelligent (AI) |
| title | Lightweight resilience: Advancing visual-inertial odometry with deep convolutional networks and an intelligent learnable Kalman filter for defense against laser remote attacks |
| title_full | Lightweight resilience: Advancing visual-inertial odometry with deep convolutional networks and an intelligent learnable Kalman filter for defense against laser remote attacks |
| title_fullStr | Lightweight resilience: Advancing visual-inertial odometry with deep convolutional networks and an intelligent learnable Kalman filter for defense against laser remote attacks |
| title_full_unstemmed | Lightweight resilience: Advancing visual-inertial odometry with deep convolutional networks and an intelligent learnable Kalman filter for defense against laser remote attacks |
| title_short | Lightweight resilience: Advancing visual-inertial odometry with deep convolutional networks and an intelligent learnable Kalman filter for defense against laser remote attacks |
| title_sort | lightweight resilience advancing visual inertial odometry with deep convolutional networks and an intelligent learnable kalman filter for defense against laser remote attacks |
| topic | Visual-Inertial Odometry (VIO) Inertial Measurement Unit (IMU) Inertial Navigation System (INS) Laser Attack Integration Artificial Intelligent (AI) |
| url | http://www.sciencedirect.com/science/article/pii/S2090447924005562 |
| work_keys_str_mv | AT aebrahimi lightweightresilienceadvancingvisualinertialodometrywithdeepconvolutionalnetworksandanintelligentlearnablekalmanfilterfordefenseagainstlaserremoteattacks AT mrmosavi lightweightresilienceadvancingvisualinertialodometrywithdeepconvolutionalnetworksandanintelligentlearnablekalmanfilterfordefenseagainstlaserremoteattacks AT aayatollahi lightweightresilienceadvancingvisualinertialodometrywithdeepconvolutionalnetworksandanintelligentlearnablekalmanfilterfordefenseagainstlaserremoteattacks |