FFESSD: An Accurate and Efficient Single-Shot Detector for Target Detection
The Single Shot MultiBox Detector (SSD) is one of the fastest algorithms in the current target detection field. It has achieved good results in target detection but there are problems such as poor extraction of features in shallow layers and loss of features in deep layers. In this paper, we propose...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/20/4276 |
| _version_ | 1811204185760202752 |
|---|---|
| author | Wenxu Shi Shengli Bao Dailun Tan |
| author_facet | Wenxu Shi Shengli Bao Dailun Tan |
| author_sort | Wenxu Shi |
| collection | DOAJ |
| description | The Single Shot MultiBox Detector (SSD) is one of the fastest algorithms in the current target detection field. It has achieved good results in target detection but there are problems such as poor extraction of features in shallow layers and loss of features in deep layers. In this paper, we propose an accurate and efficient target detection method, named Single Shot Object Detection with Feature Enhancement and Fusion (FFESSD), which is to enhance and exploit the shallow and deep features in the feature pyramid structure of the SSD algorithm. To achieve it we introduced the Feature Fusion Module and two Feature Enhancement Modules, and integrated them into the conventional structure of the SSD. Experimental results on the PASCAL VOC 2007 dataset demonstrated that FFESSD achieved 79.1% mean average precision (mAP) at the speed of 54.3 frame per second (FPS) with the input size 300 × 300, while FFESSD with a 512 × 512 sized input achieved 81.8% mAP at 30.2 FPS. The proposed network shows state-of-the-art mAP, which is better than the conventional SSD, Deconvolutional Single Shot Detector (DSSD), Feature-Fusion SSD (FSSD), and other advanced detectors. On extended experiment, the performance of FFESSD in fuzzy target detection was better than the conventional SSD. |
| first_indexed | 2024-04-12T03:08:09Z |
| format | Article |
| id | doaj.art-37a3166659c74710b5d762caadf4e2e1 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-12T03:08:09Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-37a3166659c74710b5d762caadf4e2e12022-12-22T03:50:27ZengMDPI AGApplied Sciences2076-34172019-10-01920427610.3390/app9204276app9204276FFESSD: An Accurate and Efficient Single-Shot Detector for Target DetectionWenxu Shi0Shengli Bao1Dailun Tan2Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu 610081, ChinaChengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu 610081, ChinaSchool of Mathematics and Information, China West Normal University, Nanchong 637009, ChinaThe Single Shot MultiBox Detector (SSD) is one of the fastest algorithms in the current target detection field. It has achieved good results in target detection but there are problems such as poor extraction of features in shallow layers and loss of features in deep layers. In this paper, we propose an accurate and efficient target detection method, named Single Shot Object Detection with Feature Enhancement and Fusion (FFESSD), which is to enhance and exploit the shallow and deep features in the feature pyramid structure of the SSD algorithm. To achieve it we introduced the Feature Fusion Module and two Feature Enhancement Modules, and integrated them into the conventional structure of the SSD. Experimental results on the PASCAL VOC 2007 dataset demonstrated that FFESSD achieved 79.1% mean average precision (mAP) at the speed of 54.3 frame per second (FPS) with the input size 300 × 300, while FFESSD with a 512 × 512 sized input achieved 81.8% mAP at 30.2 FPS. The proposed network shows state-of-the-art mAP, which is better than the conventional SSD, Deconvolutional Single Shot Detector (DSSD), Feature-Fusion SSD (FSSD), and other advanced detectors. On extended experiment, the performance of FFESSD in fuzzy target detection was better than the conventional SSD.https://www.mdpi.com/2076-3417/9/20/4276target detectionfeature enhancementfeature fusionreal-time object detectiondeep convolutional neural network |
| spellingShingle | Wenxu Shi Shengli Bao Dailun Tan FFESSD: An Accurate and Efficient Single-Shot Detector for Target Detection Applied Sciences target detection feature enhancement feature fusion real-time object detection deep convolutional neural network |
| title | FFESSD: An Accurate and Efficient Single-Shot Detector for Target Detection |
| title_full | FFESSD: An Accurate and Efficient Single-Shot Detector for Target Detection |
| title_fullStr | FFESSD: An Accurate and Efficient Single-Shot Detector for Target Detection |
| title_full_unstemmed | FFESSD: An Accurate and Efficient Single-Shot Detector for Target Detection |
| title_short | FFESSD: An Accurate and Efficient Single-Shot Detector for Target Detection |
| title_sort | ffessd an accurate and efficient single shot detector for target detection |
| topic | target detection feature enhancement feature fusion real-time object detection deep convolutional neural network |
| url | https://www.mdpi.com/2076-3417/9/20/4276 |
| work_keys_str_mv | AT wenxushi ffessdanaccurateandefficientsingleshotdetectorfortargetdetection AT shenglibao ffessdanaccurateandefficientsingleshotdetectorfortargetdetection AT dailuntan ffessdanaccurateandefficientsingleshotdetectorfortargetdetection |