Re-Parameterization After Pruning: Lightweight Algorithm Based on UAV Remote Sensing Target Detection
Lightweight object detection algorithms play a paramount role in unmanned aerial vehicles (UAVs) remote sensing. However, UAV remote sensing requires target detection algorithms to have higher inference speeds and greater accuracy in detection. At present, most lightweight object detection algorithm...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/23/7711 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849220356592631808 |
|---|---|
| author | Yang Yang Pinde Song Yongchao Wang Lijia Cao |
| author_facet | Yang Yang Pinde Song Yongchao Wang Lijia Cao |
| author_sort | Yang Yang |
| collection | DOAJ |
| description | Lightweight object detection algorithms play a paramount role in unmanned aerial vehicles (UAVs) remote sensing. However, UAV remote sensing requires target detection algorithms to have higher inference speeds and greater accuracy in detection. At present, most lightweight object detection algorithms have achieved fast inference speed, but their detection precision is not satisfactory. Consequently, this paper presents a refined iteration of the lightweight object detection algorithm to address the above issues. The MobileNetV3 based on the efficient channel attention (ECA) module is used as the backbone network of the model. In addition, the focal and efficient intersection over union (FocalEIoU) is used to improve the regression performance of the algorithm and reduce the false-negative rate. Furthermore, the entire model is pruned using the convolution kernel pruning method. After pruning, model parameters and floating-point operations (FLOPs) on VisDrone and DIOR datasets are reduced to 1.2 M and 1.5 M and 6.2 G and 6.5 G, respectively. The pruned model achieves 49 frames per second (FPS) and 44 FPS inference speeds on Jetson AGX Xavier for VisDrone and DIOR datasets, respectively. To fully exploit the performance of the pruned model, a plug-and-play structural re-parameterization fine-tuning method is proposed. The experimental results show that this fine-tuned method improves mAP@0.5 and mAP@0.5:0.95 by 0.4% on the VisDrone dataset and increases mAP@0.5:0.95 by 0.5% on the DIOR dataset. The proposed algorithm outperforms other mainstream lightweight object detection algorithms (except for FLOPs higher than SSDLite and mAP@0.5 Below YOLOv7 Tiny) in terms of parameters, FLOPs, mAP@0.5, and mAP@0.5:0.95. Furthermore, practical validation tests have also demonstrated that the proposed algorithm significantly reduces instances of missed detection and duplicate detection. |
| format | Article |
| id | doaj-art-0c755c56bddd40ec95ef8584d52bc9a1 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-0c755c56bddd40ec95ef8584d52bc9a12024-12-13T16:32:31ZengMDPI AGSensors1424-82202024-12-012423771110.3390/s24237711Re-Parameterization After Pruning: Lightweight Algorithm Based on UAV Remote Sensing Target DetectionYang Yang0Pinde Song1Yongchao Wang2Lijia Cao3School of Automation & Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, ChinaSchool of Automation & Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, ChinaSchool of Aerospace Science and Technology, Xidian University, Xi’an 710071, ChinaSchool of Automation & Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, ChinaLightweight object detection algorithms play a paramount role in unmanned aerial vehicles (UAVs) remote sensing. However, UAV remote sensing requires target detection algorithms to have higher inference speeds and greater accuracy in detection. At present, most lightweight object detection algorithms have achieved fast inference speed, but their detection precision is not satisfactory. Consequently, this paper presents a refined iteration of the lightweight object detection algorithm to address the above issues. The MobileNetV3 based on the efficient channel attention (ECA) module is used as the backbone network of the model. In addition, the focal and efficient intersection over union (FocalEIoU) is used to improve the regression performance of the algorithm and reduce the false-negative rate. Furthermore, the entire model is pruned using the convolution kernel pruning method. After pruning, model parameters and floating-point operations (FLOPs) on VisDrone and DIOR datasets are reduced to 1.2 M and 1.5 M and 6.2 G and 6.5 G, respectively. The pruned model achieves 49 frames per second (FPS) and 44 FPS inference speeds on Jetson AGX Xavier for VisDrone and DIOR datasets, respectively. To fully exploit the performance of the pruned model, a plug-and-play structural re-parameterization fine-tuning method is proposed. The experimental results show that this fine-tuned method improves mAP@0.5 and mAP@0.5:0.95 by 0.4% on the VisDrone dataset and increases mAP@0.5:0.95 by 0.5% on the DIOR dataset. The proposed algorithm outperforms other mainstream lightweight object detection algorithms (except for FLOPs higher than SSDLite and mAP@0.5 Below YOLOv7 Tiny) in terms of parameters, FLOPs, mAP@0.5, and mAP@0.5:0.95. Furthermore, practical validation tests have also demonstrated that the proposed algorithm significantly reduces instances of missed detection and duplicate detection.https://www.mdpi.com/1424-8220/24/23/7711lightweightobject detectionre-parameterizationpruningUAV remote sensing |
| spellingShingle | Yang Yang Pinde Song Yongchao Wang Lijia Cao Re-Parameterization After Pruning: Lightweight Algorithm Based on UAV Remote Sensing Target Detection Sensors lightweight object detection re-parameterization pruning UAV remote sensing |
| title | Re-Parameterization After Pruning: Lightweight Algorithm Based on UAV Remote Sensing Target Detection |
| title_full | Re-Parameterization After Pruning: Lightweight Algorithm Based on UAV Remote Sensing Target Detection |
| title_fullStr | Re-Parameterization After Pruning: Lightweight Algorithm Based on UAV Remote Sensing Target Detection |
| title_full_unstemmed | Re-Parameterization After Pruning: Lightweight Algorithm Based on UAV Remote Sensing Target Detection |
| title_short | Re-Parameterization After Pruning: Lightweight Algorithm Based on UAV Remote Sensing Target Detection |
| title_sort | re parameterization after pruning lightweight algorithm based on uav remote sensing target detection |
| topic | lightweight object detection re-parameterization pruning UAV remote sensing |
| url | https://www.mdpi.com/1424-8220/24/23/7711 |
| work_keys_str_mv | AT yangyang reparameterizationafterpruninglightweightalgorithmbasedonuavremotesensingtargetdetection AT pindesong reparameterizationafterpruninglightweightalgorithmbasedonuavremotesensingtargetdetection AT yongchaowang reparameterizationafterpruninglightweightalgorithmbasedonuavremotesensingtargetdetection AT lijiacao reparameterizationafterpruninglightweightalgorithmbasedonuavremotesensingtargetdetection |