基于轻量型卷积神经网络的海面红外显著性目标检测方法

doi:10.6040/j.issn.1672-3961.0.2021.352

摘要/Abstract

摘要： 为提高红外舰船图像显著性检测精度,同时降低参数量,提出一种轻量型红外舰船显著性检测模型。该模型针对红外图像缺乏颜色、纹理等细节特征的特点,从以下三个方面进行轻量化设计:在骨干网络设计方面,将视觉几何组网络(visual geometry group, VGG)各层的通道数减少一半作为骨干网络,以减少冗余的特征;为了进一步减少模型参数量,在前两个低层卷积模块中引入一种轻量型的线性瓶颈模块(linear bottleneck, LB)替换传统卷积模块;提出一种新的提取全局特征能力更强的轻量型的高层线性瓶颈模块(high-level linear bottleneck, HLLB)替换后3个高层传统卷积模块,并且使用自适应平均池化提取高层特征作为全局特征以得到更丰富的上下文信息。针对红外数据集缺少的问题,构建一个红外舰船数据集IRShip,包括1002幅图像。试验结果表明:该算法能够有效实现红外舰船目标的显著性检测,并且通过与其他7种常用的显著性检测模型对比,本研究提出的模型可以在大幅减少参数量的情况下有效提升红外舰船显著性目标检测的性能。

关键词: 卷积神经网络, 红外舰船, 显著性检测, 轻量化模块, 全局特征提取

中图分类号:

TP18

张学思,张婷,刘兆英,江天鹏. 基于轻量型卷积神经网络的海面红外显著性目标检测方法[J]. 山东大学学报 (工学版), 2022, 52(2): 41-49.

ZHANG Xuesi, ZHANG Ting, LIU Zhaoying, JIANG Tianpeng. Infrared salient object detection of sea background based on lightweight CNN[J]. Journal of Shandong University(Engineering Science), 2022, 52(2): 41-49.

参考文献

[1] ZHANG Baohua, JIAO Doudou, PEI Huiquan, et al. Infrared moving object detection based on local saliency and sparse representation[J]. Infrared Physics & Technology, 2017, 86:187-193.
[2] YI Xiang, WANG Bingjian, ZHOU Huixin, et al. Dim and small infrared target fast detection guided by visual saliency[J]. Infrared Physics & Technology, 2019, 97:6-14.
[3] DONOSER M, URSCHLER M, HIRZER M, et al. Saliency driven total variation segmentation[C] //2009 IEEE 12th International Conference on Computer Vision. Kyoto, Japan: IEEE, 2009.
[4] KHAN F S, WEIJER J V, VANRELL M. Modulating shape features by color attention for object recognition[J]. International Journal of Computer Vision, 2012, 98(1):49-64.
[5] WANG Qing, ZHANG Lu, LI Yan, et al. Overview of deep-learning based methods for salient object detection in videos[J]. Pattern Recognit, 2020, 104(107347):1-16.
[6] ZHANG Lihe, WU Jie, WANG Tiantian, et al. A multistage refinement network for salient object detection[J]. IEEE Transactions on Image Processing, 2020, 29: 3534-3545.
[7] LIU Zhaoying, BAI Xiangzhi, SUN Changming, et al. Infrared ship target segmentation through integration of multiple feature maps[J]. Image and Vision Computing, 2016(48/49): 48-49.
[8] YU Jingang, XIA Guisong, DENG Jianjin, et al. Small object detection in forward-looking infrared images with sea clutter using context-driven Bayesian saliency model[J]. Infrared Physics and Technology, 2015, 73: 175-183.
[9] QI Baojun, WU Tao, HE Hangen. Robust detection of small infrared objects in maritime scenarios using local minimum patterns and spatio-temporal context[J]. Optical Engineering, 2012, 51(2): 027205.
[10] HAN Jinhui, MA Yong, ZHOU Bo, et al. A robust infrared small target detection algorithm based on human visual system[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(12): 2168-2172.
[11] ZHAO Ting, WU Xiangqian. Pyramid feature attention network for saliency detection[C] //IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). California, USA: IEEE, 2019.
[12] LUO Zhiming, MISHRA A, ACHKAR A, et al. Non-local deep features for salient object detection [C] //IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu, USA: IEEE, 2017.
[13] LIU Jiangjiang, HOU Qinbing, CHENG Mingming, et al. A Simple pooling-Based design for real-time salient object detection[C] //IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). California, USA: IEEE, 2019.
[14] ZHAO Jiaxing, LIU Jiangjiang, FAN Dengping, et al. EGNet:edge guidance network for salient object detection[C] //Proceedings of the IEEE/CVF International Conference on Computer Vision. California, USA: IEEE, 2019.
[15] CHEN Zuyao, XU Qianqian, CONG Runming, et al. global context-aware progressive aggregation network for salient object Detection[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7):10599-10606.
[16] ZHOU Huajun, XIE Xiaohua, LAI Jianhua, et al. Interactive two-stream decoder for accurate and fast saliency detection[C] //2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Washington, USA: IEEE, 2020.
[17] SANDLER M, HOWARD A, ZHU M, et al. MobileNetV2: inverted residuals and linear bottlenecks[C] //IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018.
[18] ZHANG Xiangyu, ZHOU Xinyu, LIN Mengxiao, et al. ShuffleNet: an extremely efficient convolutional neural network for mobile devices[C] //IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018.
[19] CHOLLET F. Xception: deep learning with depthwise separable convolutions[C] //IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu, USA: IEEE, 2017.
[20] HUANG Gao, LIU Shichen, KILIAN Q, et al. CondenseNet: an efficient densenet using learned group convolutions[C] //IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018.
[21] LIN Tsungyi, DOLLR Piotr, GIRSHICK Ross B, HE Kaiming, et al. Feature pyramid networks for object detection[C] //2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu, USA: IEEE, 2017.
[22] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C] //IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas, USA: IEEE, 2016.
[23] JIANG Tinpeng, LIU Zhaoying, LI Yujian, et al. Multi-level up-sampling network for infrared ship saliency object detection[C] //in Proceedings of the 2019 3rd International Conference on Video and Image Process. Wuhan, China: ACM, 2019.
[24] LIU Zhangying, ZHANG Xuesi, JIANG Tianpeng, et al. Infrared salient object detection based on global guided lightweight non-local deep features[J]. Infrared Physics & Technology, 2021, 115: 103672.
[25] HOU Qibin, CHENG Mingming, HU Xiaowei, et al. Deeply supervised salient object detection with short connections[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41(4):815-828.

相关文章 15

[1]	梁晔,马楠,刘宏哲. 图像依赖的显著图融合方法[J]. 山东大学学报 (工学版), 2021, 51(4): 1-7.
[2]	陶亮,刘宝宁,梁玮. 基于CNN-LSTM 混合模型的心律失常自动检测[J]. 山东大学学报 (工学版), 2021, 51(3): 30-36.
[3]	廖锦萍,莫毓昌,YAN Ke. 基于C-LSTM的短期用电预测模型和应用[J]. 山东大学学报 (工学版), 2021, 51(2): 90-97.
[4]	廖南星,周世斌,张国鹏,程德强. 基于类激活映射-注意力机制的图像描述方法[J]. 山东大学学报 (工学版), 2020, 50(4): 28-34.
[5]	李春阳,李楠,冯涛,王朱贺,马靖凯. 基于深度学习的洗衣机异常音检测[J]. 山东大学学报 (工学版), 2020, 50(2): 108-117.
[6]	宋士奇,朴燕,蒋泽新. 基于改进YOLOv3的复杂场景车辆分类与跟踪[J]. 山东大学学报 (工学版), 2020, 50(2): 27-33.
[7]	蔡国永,林强,任凯琪. 基于域对抗网络和BERT的跨领域文本情感分析[J]. 山东大学学报 (工学版), 2020, 50(1): 1-7,20.
[8]	侯霄雄,许新征,朱炯,郭燕燕. 基于AlexNet和集成分类器的乳腺癌计算机辅助诊断方法[J]. 山东大学学报 (工学版), 2019, 49(2): 74-79.
[9]	权稳稳,林明星. CNN特征与BOF相融合的水下目标识别算法[J]. 山东大学学报 (工学版), 2019, 49(1): 107-113.
[10]	梁蒙蒙,周涛,夏勇,张飞飞,杨健. 基于PSO-ConvK卷积神经网络的肺部肿瘤图像识别[J]. 山东大学学报 (工学版), 2018, 48(5): 77-84.
[11]	张璞,刘畅,王永. 基于特征融合和集成学习的建议语句分类模型[J]. 山东大学学报 (工学版), 2018, 48(5): 47-54.
[12]	谢志峰,吴佳萍,马利庄. 基于卷积神经网络的中文财经新闻分类方法[J]. 山东大学学报(工学版), 2018, 48(3): 34-39.
[13]	赵彦霞, 王熙照. 基于SVD和DCNN的彩色图像多功能零水印算法[J]. 山东大学学报(工学版), 2018, 48(3): 25-33.
[14]	何正义,曾宪华,郭姜. 一种集成卷积神经网络和深信网的步态识别与模拟方法[J]. 山东大学学报(工学版), 2018, 48(3): 88-95.
[15]	任永峰,董学育. 基于自适应流形相似性的图像显著性区域提取算法[J]. 山东大学学报(工学版), 2017, 47(3): 56-62.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed