赞
踩
目录
单帧红外小目标数据集 | Single-frame InfraRed Small Target (SIRST) Benchmark
南航戴一冕的文章中提出了一个用于红外小目标检测的单帧数据集 "Asymmetric Contextual Modulation for Infrared Small Target Detection" https://arxiv.org/abs/2009.14530
“Asymmetric Contextual Modulation for Infrared Small Target Detection”文中首先提供了一个具有高质量标注的开放数据集来推进红外小目标领域的研究。
IRST是专门为单帧红外小目标检测而构建的数据集,其中的图像是从数百个不同场景的红外序列中选取的。https://github.com/YimianDai/sirst/blob/master/gallery.png
The bounding box and semantic segmentation annotations are available now. The rest annotation forms will come soon.
手动标记为五种标注形式。边界框和语义分割标注现在可用。其余的标注表格将很快发布。(还有其他同类型数据集[31],但SIRST是数据量最多的)
(a) 类别标签 (b)实例分割 (c)边界框 (d)语义分割 (e)实例发现
为了更好地平衡数据驱动方法和传统模型驱动方法,提出了一种新的评价指标。
我们提出了在并集上的归一化交点(nIoU)作为IoU的替代,它定义为:
N是样本总数,IoU和nIoU都不能代替receiver operating characteristic (ROC)曲线,因为它们反映的是固定阈值下的分割效果,而ROC反映的是滑动阈值下的整体效果。
通常,大多数研究人员将单帧检测问题建模为不同假设下的目标点检测,如显著目标点[3,8]、低秩背景下稀疏的点[5,40],匀质(均匀)背景上的pop-out的点[33,7]。然后离群值映射(红外小目标检测结果)可以通过显著性检测、稀疏低秩矩阵/张量分解或局部对比度测量得到。最后,在给定阈值的条件下对红外小目标进行分割。尽管这些方法具有计算友好和无需学习的特点,但对场景变化的辨识能力不足,且具有超参数敏感性。
信号处理界普遍的想法是直接建立模型来测量红外小目标与其邻域环境的对比度[2,10]。尽管这些模型驱动的方法无需学习,也易于计算,但它们存在以下缺点:
红外小目标检测领域的基于深度学习研究很少,原因大致有:
针对红外小目标的深度网络需要定制:
我们提出了一个非对称上下文调制(ACM)机制,一个插件模块,可以集成到多个主网络。
[2] C. L. Philip Chen, Hong Li, Yantao Wei, Tian Xia, and Yuan Yan Tang. A local contrast method for small infrared target detection. IEEE Transactions on Geoscience and Remote Sensing, 52(1):574–581, 2014.
[4] Yimian Dai and Yiquan Wu. Reweighted infrared patch-tensor model with both nonlocal and local priors for single-frame small target detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(8):3752– 3767, 2017.
[9] Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang, and Hanqing Lu. Dual attention network for scene segmentation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 3146–3154, 2019.
[10] Chenqiang Gao, Deyu Meng, Yi Yang, Yongtao Wang, Xiaofang Zhou, and Alexander G. Hauptmann. Infrared patch image model for small target detection in a single image. IEEE Transactions on Image Processing, 22(12):4996–5009, 2013.
[14] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770–778, 2016.
[15] Jie Hu, Li Shen, and Gang Sun. Squeeze-and-excitation networks. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 7132–7141, 2018.
[20] Yanghao Li, Yuntao Chen, Naiyan Wang, and Zhao-Xiang Zhang. Scale-aware trident networks for object detection. In IEEE International Conference on Computer Vision (ICCV), pages 6053–6062, 2019.
[29] Bharat Singh and Larry S. Davis. An analysis of scale invariance in object detection - SNIP. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 3578–3587, June 2018.
[31] Huan Wang, Luping Zhou, and Lei Wang. Miss detection vs. false alarm: Adversarial learning for small object segmentation in infrared images. In IEEE International Conference on Computer Vision (ICCV), pages 8508–8517, 2019.
[34] Wei Zhang, Mingyu Cong, and Liping Wang. Algorithms for optical weak small targets detection and tracking: review. In International Conference on Neural Networks and Signal Processing, volume 1, pages 643–647, 2003.
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。