Human Activity Classification Based on Dual Micro-Motion Signatures Using Interferometric Radar
Micro-Doppler signatures obtained from the Doppler radar are generally used for human activity classification. However, if the angle between the direction of motion and radar antenna broadside is greater than 60°, the micro-Doppler signatures generated by the radial motion of human body reduce signi...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/7/1752 |
| _version_ | 1827746552929583104 |
|---|---|
| author | Shahid Hassan Xiangrong Wang Saima Ishtiaq Nasim Ullah Alsharef Mohammad Abdulfattah Noorwali |
| author_facet | Shahid Hassan Xiangrong Wang Saima Ishtiaq Nasim Ullah Alsharef Mohammad Abdulfattah Noorwali |
| author_sort | Shahid Hassan |
| collection | DOAJ |
| description | Micro-Doppler signatures obtained from the Doppler radar are generally used for human activity classification. However, if the angle between the direction of motion and radar antenna broadside is greater than 60°, the micro-Doppler signatures generated by the radial motion of human body reduce significantly, thereby degrading the performance of the classification algorithm. For the accurate classification of different human activities irrespective of trajectory, we propose a new algorithm based on dual micro-motion signatures, namely, the micro-Doppler and interferometric micro-motion signatures, using an interferometric radar. First, the motion of different parts of the human body is simulated using motion capture (MOCAP) data, which is further utilized for radar echo signal generation. Second, time-varying Doppler and interferometric spectrograms obtained from time-frequency analysis of a single Doppler receiver and interferometric output data, respectively, are fed as input to the deep convolutional neural network (DCNN) for feature extraction and the training/testing process. The performance of the proposed algorithm is analyzed and compared with a micro-Doppler signatures-based classifier. Results show that a dual micro-motion-based DCNN classifier using an interferometric radar is capable of classifying different human activities with an accuracy level of 98%, where Doppler signatures diminish considerably, providing insufficient information for classification. Verification of the proposed classification algorithm based on dual micro-motion signatures is also performed using a real radar test dataset of different human walking patterns, and a classification accuracy level of approximately 90% is achieved. |
| first_indexed | 2024-03-11T05:26:54Z |
| format | Article |
| id | doaj.art-8b6719cf3775461da42a640137c698d0 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T05:26:54Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8b6719cf3775461da42a640137c698d02023-11-17T17:28:24ZengMDPI AGRemote Sensing2072-42922023-03-01157175210.3390/rs15071752Human Activity Classification Based on Dual Micro-Motion Signatures Using Interferometric RadarShahid Hassan0Xiangrong Wang1Saima Ishtiaq2Nasim Ullah3Alsharef Mohammad4Abdulfattah Noorwali5School of Electronic and Information Engineering, Beihang University, Beijing 100191, ChinaSchool of Electronic and Information Engineering, Beihang University, Beijing 100191, ChinaSchool of Electronic and Information Engineering, Beihang University, Beijing 100191, ChinaDepartment of Electrical Engineering, College of Engineering, Taif University, Al-Hawiyah, Taif 21974, Saudi ArabiaDepartment of Electrical Engineering, College of Engineering, Taif University, Al-Hawiyah, Taif 21974, Saudi ArabiaDepartment of Electrical Engineering, Umm Al-Qura University, Makkah 21955, Saudi ArabiaMicro-Doppler signatures obtained from the Doppler radar are generally used for human activity classification. However, if the angle between the direction of motion and radar antenna broadside is greater than 60°, the micro-Doppler signatures generated by the radial motion of human body reduce significantly, thereby degrading the performance of the classification algorithm. For the accurate classification of different human activities irrespective of trajectory, we propose a new algorithm based on dual micro-motion signatures, namely, the micro-Doppler and interferometric micro-motion signatures, using an interferometric radar. First, the motion of different parts of the human body is simulated using motion capture (MOCAP) data, which is further utilized for radar echo signal generation. Second, time-varying Doppler and interferometric spectrograms obtained from time-frequency analysis of a single Doppler receiver and interferometric output data, respectively, are fed as input to the deep convolutional neural network (DCNN) for feature extraction and the training/testing process. The performance of the proposed algorithm is analyzed and compared with a micro-Doppler signatures-based classifier. Results show that a dual micro-motion-based DCNN classifier using an interferometric radar is capable of classifying different human activities with an accuracy level of 98%, where Doppler signatures diminish considerably, providing insufficient information for classification. Verification of the proposed classification algorithm based on dual micro-motion signatures is also performed using a real radar test dataset of different human walking patterns, and a classification accuracy level of approximately 90% is achieved.https://www.mdpi.com/2072-4292/15/7/1752human activity classificationdual micro-motion signaturesmotion capture (MOCAP) datatime-frequency analysisinterferometric radardeep convolutional neural network (DCNN) |
| spellingShingle | Shahid Hassan Xiangrong Wang Saima Ishtiaq Nasim Ullah Alsharef Mohammad Abdulfattah Noorwali Human Activity Classification Based on Dual Micro-Motion Signatures Using Interferometric Radar Remote Sensing human activity classification dual micro-motion signatures motion capture (MOCAP) data time-frequency analysis interferometric radar deep convolutional neural network (DCNN) |
| title | Human Activity Classification Based on Dual Micro-Motion Signatures Using Interferometric Radar |
| title_full | Human Activity Classification Based on Dual Micro-Motion Signatures Using Interferometric Radar |
| title_fullStr | Human Activity Classification Based on Dual Micro-Motion Signatures Using Interferometric Radar |
| title_full_unstemmed | Human Activity Classification Based on Dual Micro-Motion Signatures Using Interferometric Radar |
| title_short | Human Activity Classification Based on Dual Micro-Motion Signatures Using Interferometric Radar |
| title_sort | human activity classification based on dual micro motion signatures using interferometric radar |
| topic | human activity classification dual micro-motion signatures motion capture (MOCAP) data time-frequency analysis interferometric radar deep convolutional neural network (DCNN) |
| url | https://www.mdpi.com/2072-4292/15/7/1752 |
| work_keys_str_mv | AT shahidhassan humanactivityclassificationbasedondualmicromotionsignaturesusinginterferometricradar AT xiangrongwang humanactivityclassificationbasedondualmicromotionsignaturesusinginterferometricradar AT saimaishtiaq humanactivityclassificationbasedondualmicromotionsignaturesusinginterferometricradar AT nasimullah humanactivityclassificationbasedondualmicromotionsignaturesusinginterferometricradar AT alsharefmohammad humanactivityclassificationbasedondualmicromotionsignaturesusinginterferometricradar AT abdulfattahnoorwali humanactivityclassificationbasedondualmicromotionsignaturesusinginterferometricradar |