Ground Target Detection and Damage Assessment by Patrol Missiles Based on YOLO-VGGNet
Patrol missiles are a common type of unmanned aerial vehicle, which can be efficiently used for reconnaissance and sensing. In this work, target detection and the damage assessment of typical mobile ground targets by patrol missiles are studied, and a new method, combining the YOLO v3 with the VGG n...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/19/9484 |
| _version_ | 1797480860998434816 |
|---|---|
| author | Yibo Xu Qinghua Yu Yanjuan Wang Junhao Xiao Zhiqian Zhou Huimin Lu |
| author_facet | Yibo Xu Qinghua Yu Yanjuan Wang Junhao Xiao Zhiqian Zhou Huimin Lu |
| author_sort | Yibo Xu |
| collection | DOAJ |
| description | Patrol missiles are a common type of unmanned aerial vehicle, which can be efficiently used for reconnaissance and sensing. In this work, target detection and the damage assessment of typical mobile ground targets by patrol missiles are studied, and a new method, combining the YOLO v3 with the VGG networks, is proposed for the problem. Specifically, with YOLO v3 as the precursor, the proposed method can detect, classify, and localize ground targets accurately and quickly. Then, the image blocks of detected targets are fed into the lightweight VGG networks, which can evaluate their damage level coarsely. Meanwhile, based on class activation mapping (CAM) and deconvolution, we further analyse the activation intensity of clustered convolution kernels, which helps determine whether the targets’ key components are destroyed. Unlike traditional image change detection methods, which require images before and after a strike for comparison, the proposed method learns the target model through extensive training and can assess the target’s damage status in a timely and online manner. Compared to previous learning-based methods, our detailed analysis with convolutional feature visualization of the damaged targets and their components gives a more interpretable perspective. Finally, Unity simulation experiments prove the proposed method’s effectiveness, which improves the accuracy of damage level assessment by 16.0% and 8.8% compared with traditional image-change-detection-based methods and the two-CNN learning-based method. The convolutional feature clustering method evaluates the status of the targets’ key components with an accuracy of 72%. |
| first_indexed | 2024-03-09T22:06:16Z |
| format | Article |
| id | doaj.art-237e92e1432f439e8aea1e215c226a0b |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T22:06:16Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-237e92e1432f439e8aea1e215c226a0b2023-11-23T19:40:23ZengMDPI AGApplied Sciences2076-34172022-09-011219948410.3390/app12199484Ground Target Detection and Damage Assessment by Patrol Missiles Based on YOLO-VGGNetYibo Xu0Qinghua Yu1Yanjuan Wang2Junhao Xiao3Zhiqian Zhou4Huimin Lu5College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaBeijing Aerospace Control Center, Beijing 100094, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaPatrol missiles are a common type of unmanned aerial vehicle, which can be efficiently used for reconnaissance and sensing. In this work, target detection and the damage assessment of typical mobile ground targets by patrol missiles are studied, and a new method, combining the YOLO v3 with the VGG networks, is proposed for the problem. Specifically, with YOLO v3 as the precursor, the proposed method can detect, classify, and localize ground targets accurately and quickly. Then, the image blocks of detected targets are fed into the lightweight VGG networks, which can evaluate their damage level coarsely. Meanwhile, based on class activation mapping (CAM) and deconvolution, we further analyse the activation intensity of clustered convolution kernels, which helps determine whether the targets’ key components are destroyed. Unlike traditional image change detection methods, which require images before and after a strike for comparison, the proposed method learns the target model through extensive training and can assess the target’s damage status in a timely and online manner. Compared to previous learning-based methods, our detailed analysis with convolutional feature visualization of the damaged targets and their components gives a more interpretable perspective. Finally, Unity simulation experiments prove the proposed method’s effectiveness, which improves the accuracy of damage level assessment by 16.0% and 8.8% compared with traditional image-change-detection-based methods and the two-CNN learning-based method. The convolutional feature clustering method evaluates the status of the targets’ key components with an accuracy of 72%.https://www.mdpi.com/2076-3417/12/19/9484damage assessmenttarget detectionfeature layer visualizationclass activation mappingdeconvolutionconvolutional feature clustering |
| spellingShingle | Yibo Xu Qinghua Yu Yanjuan Wang Junhao Xiao Zhiqian Zhou Huimin Lu Ground Target Detection and Damage Assessment by Patrol Missiles Based on YOLO-VGGNet Applied Sciences damage assessment target detection feature layer visualization class activation mapping deconvolution convolutional feature clustering |
| title | Ground Target Detection and Damage Assessment by Patrol Missiles Based on YOLO-VGGNet |
| title_full | Ground Target Detection and Damage Assessment by Patrol Missiles Based on YOLO-VGGNet |
| title_fullStr | Ground Target Detection and Damage Assessment by Patrol Missiles Based on YOLO-VGGNet |
| title_full_unstemmed | Ground Target Detection and Damage Assessment by Patrol Missiles Based on YOLO-VGGNet |
| title_short | Ground Target Detection and Damage Assessment by Patrol Missiles Based on YOLO-VGGNet |
| title_sort | ground target detection and damage assessment by patrol missiles based on yolo vggnet |
| topic | damage assessment target detection feature layer visualization class activation mapping deconvolution convolutional feature clustering |
| url | https://www.mdpi.com/2076-3417/12/19/9484 |
| work_keys_str_mv | AT yiboxu groundtargetdetectionanddamageassessmentbypatrolmissilesbasedonyolovggnet AT qinghuayu groundtargetdetectionanddamageassessmentbypatrolmissilesbasedonyolovggnet AT yanjuanwang groundtargetdetectionanddamageassessmentbypatrolmissilesbasedonyolovggnet AT junhaoxiao groundtargetdetectionanddamageassessmentbypatrolmissilesbasedonyolovggnet AT zhiqianzhou groundtargetdetectionanddamageassessmentbypatrolmissilesbasedonyolovggnet AT huiminlu groundtargetdetectionanddamageassessmentbypatrolmissilesbasedonyolovggnet |