Retracted: KSSD: single‐stage multi‐object detection algorithm with higher accuracy
Considering that the single shot multibox detector (SSD) algorithm will be missed or even false when is used to detect the small‐ and medium‐sized objects, in this study, Kullback–Leibler single shot multibox detection (KSSD) object detection algorithm is proposed to improve the accuracy of small‐ a...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-12-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-ipr.2020.0077 |
| _version_ | 1828356631186898944 |
|---|---|
| author | Qingshan Hou Jinsheng Xing |
| author_facet | Qingshan Hou Jinsheng Xing |
| author_sort | Qingshan Hou |
| collection | DOAJ |
| description | Considering that the single shot multibox detector (SSD) algorithm will be missed or even false when is used to detect the small‐ and medium‐sized objects, in this study, Kullback–Leibler single shot multibox detection (KSSD) object detection algorithm is proposed to improve the accuracy of small‐ and medium‐sized objects detection. Firstly, the details in the detection process are visualised with gradient‐weighted class activation mapping technology, and the details of each detection layer are shown in the form of class activation maps. Then it is noted that the phenomenon of the false or missed detection of the objects to be detected on small‐ and medium‐sized objects in the SSD algorithm is related to the regression loss function. Accordingly, Kullback–Leibler border regression loss strategy is adopted and non‐maximum suppression algorithm is used to output the final prediction boxes. Experimental results show that compared with the existed detection algorithms, the improved algorithm in this study has higher accuracy and stability, and can significantly improve the detection effect on small‐ and medium‐sized objects. |
| first_indexed | 2024-04-14T03:03:00Z |
| format | Article |
| id | doaj.art-aaa4761ae89d4c90912e1c4e6b9c54c2 |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-14T03:03:00Z |
| publishDate | 2020-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-aaa4761ae89d4c90912e1c4e6b9c54c22022-12-22T02:15:52ZengWileyIET Image Processing1751-96591751-96672020-12-0114153651366110.1049/iet-ipr.2020.0077Retracted: KSSD: single‐stage multi‐object detection algorithm with higher accuracyQingshan Hou0Jinsheng Xing1School of Mathematics and Computer ScienceShanxi Normal UniversityLinfenShanxiPeople's Republic of ChinaSchool of Mathematics and Computer ScienceShanxi Normal UniversityLinfenShanxiPeople's Republic of ChinaConsidering that the single shot multibox detector (SSD) algorithm will be missed or even false when is used to detect the small‐ and medium‐sized objects, in this study, Kullback–Leibler single shot multibox detection (KSSD) object detection algorithm is proposed to improve the accuracy of small‐ and medium‐sized objects detection. Firstly, the details in the detection process are visualised with gradient‐weighted class activation mapping technology, and the details of each detection layer are shown in the form of class activation maps. Then it is noted that the phenomenon of the false or missed detection of the objects to be detected on small‐ and medium‐sized objects in the SSD algorithm is related to the regression loss function. Accordingly, Kullback–Leibler border regression loss strategy is adopted and non‐maximum suppression algorithm is used to output the final prediction boxes. Experimental results show that compared with the existed detection algorithms, the improved algorithm in this study has higher accuracy and stability, and can significantly improve the detection effect on small‐ and medium‐sized objects.https://doi.org/10.1049/iet-ipr.2020.0077KSSDmultiobject detection algorithmsingle shot multibox detector algorithmKullback–Leibler single shot multibox detectionmedium‐sized objects detectiondetection process |
| spellingShingle | Qingshan Hou Jinsheng Xing Retracted: KSSD: single‐stage multi‐object detection algorithm with higher accuracy IET Image Processing KSSD multiobject detection algorithm single shot multibox detector algorithm Kullback–Leibler single shot multibox detection medium‐sized objects detection detection process |
| title | Retracted: KSSD: single‐stage multi‐object detection algorithm with higher accuracy |
| title_full | Retracted: KSSD: single‐stage multi‐object detection algorithm with higher accuracy |
| title_fullStr | Retracted: KSSD: single‐stage multi‐object detection algorithm with higher accuracy |
| title_full_unstemmed | Retracted: KSSD: single‐stage multi‐object detection algorithm with higher accuracy |
| title_short | Retracted: KSSD: single‐stage multi‐object detection algorithm with higher accuracy |
| title_sort | retracted kssd single stage multi object detection algorithm with higher accuracy |
| topic | KSSD multiobject detection algorithm single shot multibox detector algorithm Kullback–Leibler single shot multibox detection medium‐sized objects detection detection process |
| url | https://doi.org/10.1049/iet-ipr.2020.0077 |
| work_keys_str_mv | AT qingshanhou retractedkssdsinglestagemultiobjectdetectionalgorithmwithhigheraccuracy AT jinshengxing retractedkssdsinglestagemultiobjectdetectionalgorithmwithhigheraccuracy |