Multi-scale attention feature-enhanced fusion of a new network for infrared small object detection

doi:10.16265/j.cnki.issn1003-3033.2024.06.1565

Abstract

Abstract:

In order to improve the performance of small target detection in infrared imaging and the ability of low altitude airspace supervision, an infrared small target detection network based on multi-scale attention feature enhancement fusion was proposed. Firstly, Resnet34 was used to extract the multi-scale features of infrared images. Secondly, the multi-scale spatial attention feature enhancement module(MFEM) was used to improve the ability of feature extraction. Then, in the step-by-step up sampling process, the dual channel attention feature fusion module(DFFM) was used to fuse the semantic information and detail information to better protect the characteristics of infrared small targets. Finally, taking the video sequence detection of ground/air infrared dim small aircraft target as an example, the real scene test was carried out by comparing with other methods. The results show that compared with existing methods, the proposed method improves the scores of intersection over union(IoU), F-measure and false negative rate(FNR), and can accurately locate the target and generate good segmentation results. The DFFM can simultaneously use multi-scale context information and spatial attention mechanism to highlight infiared small targets. The DFFM assigns weights to sets of different channel features, thereby obtaining the most appropriate feature map for feature fusion and improving the detection performance.

Key words: infrared image, small target detection, feature enhancement, feature fusion, attention mechanism

CLC Number:

X949

JIA Guimin, CHENG Yu, QI Mengfei. Multi-scale attention feature-enhanced fusion of a new network for infrared small object detection[J]. China Safety Science Journal, 2024, 34(6): 90-98.

Figures/Tables 13

Fig.1

Fig.2

Fig.3

Table 1

Table 2

Table 3

Table 4

Table 5

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

References 19

[1]	张磊, 李熙蔚, 燕倩如, 等. 基于改进YOLOv5s的综采工作面人员检测算法[J]. 中国安全科学学报, 2023, 33(7):82-89. doi: 10.16265/j.cnki.issn1003-3033.2023.07.2226
	ZHANG Lei, LI Xiwei, YAN Qianru, et al. Personnel detection algorithm in fully mechanized coal face based on improved YOLOv5s[J]. China Safety Science Journal, 2023, 33(7):82-89. doi: 10.16265/j.cnki.issn1003-3033.2023.07.2226
[2]	张萌, 韩豫, 刘泽峰. 深度学习下建筑工人高空安全防护装备检测方法[J]. 中国安全科学学报, 2023, 32(5):140-146.
	ZHANG Meng, HAN Yu, LIU Zefeng. Detection method of high-altitude safety protective equipment for construction workers based on deep learning[J]. China Safety Science Journal, 2023, 32(5):140-146.
[3]	BAI Xiangzhi, ZHOU Fugen. Analysis of new top-hat transformation and the application for infrared dim small target detection[J]. Pattern Recognition, 2010, 43(6):2145-2156.
[4]	CHEN C L P, LI Hong, WEI Yantao, et al. A local contrast method for small infrared target detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(1):574-581.
[5]	DU Peng, HAMDULLA A. Infrared small target detection using homogeneity-weighted local contrast measure[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(3):514-518.
[6]	WEI Yantao, YOU Xinge, LI Hong. Multiscale patch-based contrast measure for small infrared target detection[J]. Pattern Recognition, 2016, 58:216-226.
[7]	HAN Jinhui, MORADI S, FARAMARZI I, et al. Infrared small target detection based on the weighted strengthened local contrast measure[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 18(9):1670-1674.
[8]	GAO Chenqiang, MENG Deyu, YANG Yi, et al. Infrared patch-image model for small target detection in a single image[J]. IEEE Transactions on Image Processing, 2013, 22(12):4996-5009. pmid: 24043387
[9]	ZHANG Landan, PENG Zhenming. Infrared small target detection based on partial sum of the tensor nuclear norm[J]. Remote Sensing, 2019, 11(4): DOI: 10.3390/rs11040382.
[10]	HOU Qingyu, ZHANG Liuwei, TAN Fanjiao, et al. ISTDU-Net: infrared small-target detection U-Net[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19:1-5.
[11]	MA Tianlei, YANG Zhen, WANG Jiaqi, et al. Infrared small target detection network with generate label and feature mapping[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19:1-5.
[12]	ZHAO Bin, WANG Chunping, FU Qiang, et al. A novel pattern for infrared small target detection with generative adversarial network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(5):4481-4492.
[13]	DAI Yimian, WU Yiquan, ZHOU Fei, et al. Asymmetric contextual modulation for infrared small target detection[C]. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021:950-959.
[14]	ZHANG Tianfang, LEI Li, CAO Siying, et al. Attention-guided pyramid context networks for detecting infrared small target under complex background[J]. IEEE Transactions on Aerospace and Electronic Systems, 2023, 59(4):4250-4261.
[15]	HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016:770-778.
[16]	DAI Yimian, WU Yiquan, ZHOU Fei, et al. Attentional local contrast networks for infrared small target detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(11):9813-9824.
[17]	回丙伟, 宋志勇, 范红旗, 等. 地/空背景下红外图像弱小飞机目标检测跟踪数据集[J]. 中国科学数据, 2020, 5(3):291-302.
	HUI Bingwei, SONG Zhiyong, FAN Hongqi, et al. A dataset for infrared image dim-small aircraft target detection and tracking under ground/air background[J]. Science Data Bank, 2020, 5(3):291-302.
[18]	RAHMAN M A, WANG Yang. Optimizing intersection-over-union in deep neural networks for image segmentation[C]. Proceedings of 12^th International Symposium of Advances in Visual Computing (ISVC), 2016:234-244.
[19]	CHEN L C, ZHU Yukun, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]. Proceedings of the European Conference on Computer Vision (ECCV), 2018:833-851.

不同方法	IoU	F值	FPR/10^-2	FNR
Baseline	0.746 6	0.854 8	0.012 4	0.151 3
Baseline+MFEM	0.748 9	0.857 6	0.010 8	0.148 7
Baseline+DFFM	0.757 4	0.860 2	0.009 5	0.136 6
Baseline+MFEM+DFFM	0.762 0	0.864 9	0.008 6	0.128 5

不同方法	IoU	F值	FPR/10^-2	FNR
Baseline	0.753 8	0.859 6	0.013 6	0.147 7
Baseline+MFEM	0.756 2	0.861 1	0.012 8	0.142 3
Baseline+DFFM	0.766 6	0.867 9	0.011 3	0.135 8
Baseline+MFEM+DFFM	0.771 2	0.870 8	0.010 2	0.129 1

不同方法	IoU	F值	FPR/10^-2	FNR
WSLCM	0.049 8	0.094 8	0.798 4	0.406 1
PSTNN	0.515 3	0.680 2	0.003 9	0.390 5
ACM	0.743	0.831 2	0.011 7	0.266 6
DeepLabv3+	0.684 7	0.812 8	0.032 6	0.191 7
AGPCNet	0.736 1	0.848 0	0.008 9	0.153 9
文中方法	0.762 0	0.864 9	0.008 6	0.128 5

不同方法	IoU	F值	FPR/10^-2	FNR
WSLCM	0.063 8	0.119 7	0.382 1	0.701 1
PSTNN	0.136 1	0.239 5	0.018 2	0.858 5
ACM	0.677 1	0.807 4	0.017 4	0.181 1
DeepLabv3+	0.685 6	0.813 5	0.035 4	0.171 1
AGPCNet	0.768 0	0.868 7	0.010 0	0.139 0
文中方法	0.771 2	0.870 8	0.010 2	0.129 1