Affiliation(s):
Qingdao Innovation and Development Center of Harbin Engineering University, Qingdao 266000, china;
moreAffiliation(s): Qingdao Innovation and Development Center of Harbin Engineering University, Qingdao 266000, china; College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, china; Naval Aeronautical University, Yantai 264001, China;
less
Ruihui PENG, Jie LAI, Xueting YANG, Dianxing SUN,Shuncheng TAN, Yingjuan SONG, Wei GUO. Camouflaged target detection based on multimodal image input pixel-level fusion[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.2300503
@article{title="Camouflaged target detection based on multimodal image input pixel-level fusion", author="Ruihui PENG, Jie LAI, Xueting YANG, Dianxing SUN,Shuncheng TAN, Yingjuan SONG, Wei GUO", journal="Frontiers of Information Technology & Electronic Engineering", year="in press", publisher="Zhejiang University Press & Springer", doi="https://doi.org/10.1631/FITEE.2300503" }
%0 Journal Article %T Camouflaged target detection based on multimodal image input pixel-level fusion %A Ruihui PENG %A Jie LAI %A Xueting YANG %A Dianxing SUN %A Shuncheng TAN %A Yingjuan SONG %A Wei GUO %J Frontiers of Information Technology & Electronic Engineering %P %@ 2095-9184 %D in press %I Zhejiang University Press & Springer doi="https://doi.org/10.1631/FITEE.2300503"
TY - JOUR T1 - Camouflaged target detection based on multimodal image input pixel-level fusion A1 - Ruihui PENG A1 - Jie LAI A1 - Xueting YANG A1 - Dianxing SUN A1 - Shuncheng TAN A1 - Yingjuan SONG A1 - Wei GUO J0 - Frontiers of Information Technology & Electronic Engineering SP - EP - %@ 2095-9184 Y1 - in press PB - Zhejiang University Press & Springer ER - doi="https://doi.org/10.1631/FITEE.2300503"
Abstract: Camouflaged targets are a type of nonsalient target with high foreground and background fusion and minimal target feature information, making target recognition extremely difficult. Most detection algorithms for camouflaged targets only use the target's single-band information, resulting in low detection accuracy and a high missed detection rate. We present a multimodal image fusion camouflaged target detection technique (MIF-YOLOv5) in this paper. First, we provide a multimodal image input to achieve pixel-level fusion of the camouflaged target's optical and infrared images to improve the effective feature information of the camouflaged target. Second, a loss function is created, and the K-Means + + clustering technique is utilized to optimize the target anchor frame in the dataset to increase camouflage personnel detection accuracy and robustness. Finally, a comprehensive detection index of camouflaged targets is proposed to compare the overall effectiveness of various approaches. More crucially, we create a multispectral camouflage target dataset to test the suggested technique. The experimental results show that the proposed method has a detection accuracy of 96.5%, a recognition probability of 92.5%, a parameter quantity of the model of 0.01 M, a theoretical calculation amount of 0.03GFLOPs, and a comprehensive detection index of the camouflage target of 0.85, which has the best comprehensive detection performance. The absolute advantage of this method in detecting accuracy is also apparent in performance comparisons with other target algorithms.
Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article
Reference
Open peer comments: Debate/Discuss/Question/Opinion
Open peer comments: Debate/Discuss/Question/Opinion
<1>