STIDNet: Spatiotemporally Integrated Detection Network for Infrared Dim and Small Targets
Infrared dim and small target detection (IRDSTD) aims to obtain target position information from the background, clutter, and noise. However, for infrared dim and small targets with low signal-to-clutter ratios (SCRs), the detection difficulty lies in the fact that their poor local spatial saliency...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/2/250 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587544539168768 |
|---|---|
| author | Liuwei Zhang Zhitao Zhou Yuyang Xi Fanjiao Tan Qingyu Hou |
| author_facet | Liuwei Zhang Zhitao Zhou Yuyang Xi Fanjiao Tan Qingyu Hou |
| author_sort | Liuwei Zhang |
| collection | DOAJ |
| description | Infrared dim and small target detection (IRDSTD) aims to obtain target position information from the background, clutter, and noise. However, for infrared dim and small targets with low signal-to-clutter ratios (SCRs), the detection difficulty lies in the fact that their poor local spatial saliency will lead to missed detections and false alarms. In this work, a spatiotemporally integrated detection network (STIDNet) is proposed for IRDSTD. In the network, a spatial saliency feature generation module (SSFGM) employs a U-shaped network to extract deep features from the spatial dimension of the input image in a frame-by-frame manner and splices them based on the temporal dimension to obtain an airtime feature tensor. IRDSTs with direction-of-motion consistency and strong interframe correlation are reinforced, and randomly generated spurious waves, noise, and other false alarms are inhibited via a fixed-weight multiscale motion feature-based 3D convolution kernel (FWMFCK-3D). A mapping from the features to the target probability likelihood map is constructed in a spatiotemporal feature fusion module (STFFM) by performing 3D convolutional fusion on the spatially localized saliency and time-domain motion features. Finally, several ablation and comparison experiments indicate the excellent performance of the proposed network. For infrared dim and small targets with SCRs < 3, the average AUC value still reached 0.99786. |
| format | Article |
| id | doaj-art-06785c11eed744f28e6b67e792d23b37 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-06785c11eed744f28e6b67e792d23b372025-01-24T13:47:52ZengMDPI AGRemote Sensing2072-42922025-01-0117225010.3390/rs17020250STIDNet: Spatiotemporally Integrated Detection Network for Infrared Dim and Small TargetsLiuwei Zhang0Zhitao Zhou1Yuyang Xi2Fanjiao Tan3Qingyu Hou4Research Center for Space Optical Engineering, Harbin Institute of Technology, Harbin 150001, ChinaShanghai Institute of Satellite Engineering, Shanghai 201109, ChinaResearch Center for Space Optical Engineering, Harbin Institute of Technology, Harbin 150001, ChinaResearch Center for Space Optical Engineering, Harbin Institute of Technology, Harbin 150001, ChinaResearch Center for Space Optical Engineering, Harbin Institute of Technology, Harbin 150001, ChinaInfrared dim and small target detection (IRDSTD) aims to obtain target position information from the background, clutter, and noise. However, for infrared dim and small targets with low signal-to-clutter ratios (SCRs), the detection difficulty lies in the fact that their poor local spatial saliency will lead to missed detections and false alarms. In this work, a spatiotemporally integrated detection network (STIDNet) is proposed for IRDSTD. In the network, a spatial saliency feature generation module (SSFGM) employs a U-shaped network to extract deep features from the spatial dimension of the input image in a frame-by-frame manner and splices them based on the temporal dimension to obtain an airtime feature tensor. IRDSTs with direction-of-motion consistency and strong interframe correlation are reinforced, and randomly generated spurious waves, noise, and other false alarms are inhibited via a fixed-weight multiscale motion feature-based 3D convolution kernel (FWMFCK-3D). A mapping from the features to the target probability likelihood map is constructed in a spatiotemporal feature fusion module (STFFM) by performing 3D convolutional fusion on the spatially localized saliency and time-domain motion features. Finally, several ablation and comparison experiments indicate the excellent performance of the proposed network. For infrared dim and small targets with SCRs < 3, the average AUC value still reached 0.99786.https://www.mdpi.com/2072-4292/17/2/250infrared dim and small target detection (IRDSTD)spatiotemporal networkmultiframe imagespatiotemporally integrated |
| spellingShingle | Liuwei Zhang Zhitao Zhou Yuyang Xi Fanjiao Tan Qingyu Hou STIDNet: Spatiotemporally Integrated Detection Network for Infrared Dim and Small Targets Remote Sensing infrared dim and small target detection (IRDSTD) spatiotemporal network multiframe image spatiotemporally integrated |
| title | STIDNet: Spatiotemporally Integrated Detection Network for Infrared Dim and Small Targets |
| title_full | STIDNet: Spatiotemporally Integrated Detection Network for Infrared Dim and Small Targets |
| title_fullStr | STIDNet: Spatiotemporally Integrated Detection Network for Infrared Dim and Small Targets |
| title_full_unstemmed | STIDNet: Spatiotemporally Integrated Detection Network for Infrared Dim and Small Targets |
| title_short | STIDNet: Spatiotemporally Integrated Detection Network for Infrared Dim and Small Targets |
| title_sort | stidnet spatiotemporally integrated detection network for infrared dim and small targets |
| topic | infrared dim and small target detection (IRDSTD) spatiotemporal network multiframe image spatiotemporally integrated |
| url | https://www.mdpi.com/2072-4292/17/2/250 |
| work_keys_str_mv | AT liuweizhang stidnetspatiotemporallyintegrateddetectionnetworkforinfrareddimandsmalltargets AT zhitaozhou stidnetspatiotemporallyintegrateddetectionnetworkforinfrareddimandsmalltargets AT yuyangxi stidnetspatiotemporallyintegrateddetectionnetworkforinfrareddimandsmalltargets AT fanjiaotan stidnetspatiotemporallyintegrateddetectionnetworkforinfrareddimandsmalltargets AT qingyuhou stidnetspatiotemporallyintegrateddetectionnetworkforinfrareddimandsmalltargets |