浏览全部资源
扫码关注微信
纸质出版日期： 2023-07-16 ，
移动端阅览
王蓉芳， 王良， 李畅， 霍春雷， 陈佳伟. 2023. 整型推理量化CNN的SAR图像跨域变化检测. 中国图象图形学报， 28(07):2208-2220
Wang Rongfang， Wang Liang， Li Chang， Huo Chunlei， Chen Jiawei. 2023. IIQ-CNN-based cross-domain change detection of SAR images. Journal of Image and Graphics， 28(07):2208-2220
目的
2
合成孔径雷达（synthetic aperture radar，SAR）特有的成像优势使得SAR图像变化检测在民用和军事领域有着广泛的应用场景，但实际应用中对SAR图像的变化区域进行标注既耗时又昂贵，而且现有的变化检测方法复杂度较高，无法满足实时、快速检测的需求。对此，提出了一种基于整型推理量化卷积神经网络的SAR图像跨域变化检测方法（integer inference-based quantization convolutional neural network，IIQ-CNN）。
方法
2
该方法研究了不同场景之间的跨域变化检测问题，即利用已有标记的源域数据对未知的目标域数据进行检测；设计了同时使用时相图和差异图的样本构建方法，既避免了检测结果对差异图的过分依赖，又能充分利用差异信息和时相图与差异图之间的共享信息，提高检测精度；并且在变化检测任务中首次引入整型推理量化技术，对深度网络模型进行模拟量化，减小模型复杂度并加速推理时间。
结果
2
在４组真实的SAR图像数据集上进行实验，从检测性能上看，IIQ-CNN与其他CNN方法相比，Kappa系数提高了4.23%～9.07%；从量化能力上看，对IIQ-CNN分别进行16、8和4位量化，仅在4位量化时检测结果有较明显下降，在16和8位量化时，模型都保持了较好的检测性能，并且推理时间明显减少。
结论
2
本文方法有效解决了伪标签质量对变化检测性能的影响，实现了加速推理的同时较好地保持模型检测精度的目的，促进了变化检测算法在嵌入式设备中的应用。
Objective
2
Multiple remote sensing （RS） imaging technologies-oriented synthetic aperture radar （SAR） have been developing dramatically nowadays. Compared to other related RS imaging techniques， SAR imaging technique has its high-resolution potentials for all-weather and all-day observation beyond atmospheric and sunlight conditions. SAR image is oriented to changeable detection in related to such land cover analyses and certain regional comparison via multi-temporal SAR images. It can be widely applied for such domains in the context of natural disaster analysis， agricultural monitoring， and public security surveillance. To get final binary dynamic detection map， conventional detection method consists of such three aspects like preprocessing image， generating difference image， and analyzing the difference map. The accuracy of conventional changeable detection results are greatly originated from data preprocessing and difference image quality. The information loss is related to preprocessing and generating the difference image， especially for the regions of slight changes， and it is very tough to detect the changeable information of this location subsequently. Recent neural network has been facilitating for effective feature learning method， and non-local structures are developed and highly robust to noise-relevant features extraction and invariance can be generated as well. In addition， deep neural network （DNN） based end-to-end structure of can effectively alleviate the constraints of changeable detection results on the difference image. In recent years， multiple variants of convolutional neural network （CNN） models have been developing intensively. The growth of complex network models is required to deal with much more computing resources. To optimize the complexity of neural network， there are two sort of problem-solving schemes mentioned below： the first scheme is developed based on the structure of the neural network model. It can optimize the complexity of the model and such computing resources can be assigned to a new type of operator for fully utilizing of memory and computing power. The second one is developed based on the storage profiling of network parameters. Generally， such neural networks-based learned parameters like weights and biases are involve d in and its activations are 32-bit floating-point values. To alleviate model complexity， it is still challenging for converting 32-bit floating-point numbers into low-bit integer representations. The change detection-relevant labeled data is called to be more sufficient for SAR images. To resolve the problem of time-consuming and costly for data collection， multiple expertise and prior knowledge are required to compare the corresponding optical images to be obtained. However， expertise-derived label accuracy is higher in comparison with the pseudo-labels-generated unsupervised methods. The problem solving is focused on， in which existing labeled data is used for cross-domain changeable detection. We develop an integer inference-based quantization CNN （IIQ-CNN） method for cross-domain change detection of SAR images.
Method
2
The problem of multiple scenario-related cross-domain change detection is challenged to be resolved， where the labeled source domain data is employed to detect unclear target domain data. Furthermore， to weaken the linkage of the detection results on the difference image and improve the detection accuracy， a sample construction method is designed to incorporate bi-temporal SAR images and the corresponding difference image. Finally， to alleviate the complexity of the model and accelerate the reasoning time， integer reasoning quantization technology is introduced to simulate and quantify the deep network model as well.
Result
2
Comparative experiments are carried out on four sets of real SAR image datasets. 1） For detection performance： compared to other related CNN methods， the Kappa coefficient of IIQ-CNN is optimized by 4.23% to 9.07%. 2） For quantization performance： IIQ-CNN can be quantized 16， 8 and 4 bits of each. The detection results are significantly reduced when only 4-bit quantization is performed. In 16-bit and 8-bit quantization， the model can preserve its detection performance and the reasoning time is accelerated significantly.
Conclusion
2
The pseudo-label quality on change detection performance is feasible and the purpose of accelerating reasoning is mutual benefited with the accuracy of model detection， which can promote the application of change detection algorithms in embedded devices.
SAR图像变化检测（CD）整型推理量化卷积神经网络（CNN）跨域检测
synthetic aperture radar （SAR） imagechange detection（CD）integer inference quantizationconvolutional neural network （CNN）cross domain detection
Banner R， Nahshan Y and Soudry D. 2019. Post training 4-bit quantization of convolutional networks for rapid-deployment//Proceedings of the 33rd International Conference on Neural Information Processing Systems. Vancouver， Canada： Curran Associates Inc.： #714
Bovolo F and Bruzzone L. 2005. A detail-preserving scale-driven approach to change detection in multitemporal SAR images. IEEE Transactions on Geoscience and Remote Sensing， 43（12）： 2963-2972 ［DOI： 10.1109/TGRS.2005.857987http://dx.doi.org/10.1109/TGRS.2005.857987］
Bruzzone L and Prieto D F. 2000. Automatic analysis of the difference image for unsupervised change detection. IEEE Transactions on Geoscience and Remote Sensing， 38（3）： 1171-1182 ［DOI： 10.1109/36.843009http://dx.doi.org/10.1109/36.843009］
Chen J W， Wang R F， Ding F， Liu B， Jiao L C and Zhang J. 2020. A convolutional neural network with parallel multi-scale spatial pooling to detect temporal changes in SAR images. Remote Sensing， 12（10）： #1619 ［DOI： 10.3390/rs12101619http://dx.doi.org/10.3390/rs12101619］
Congalton R G. 1991. A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment， 37（1）： 35-46 ［DOI： 10.1016/0034-4257（91）90048-Bhttp://dx.doi.org/10.1016/0034-4257（91）90048-B］
Cui S Y， Schwarz G and Datcu M. 2016. A benchmark evaluation of similarity measures for multitemporal SAR image change detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 9（3）： 1101-1118 ［DOI： 10.1109/JSTARS.2015.2486038http://dx.doi.org/10.1109/JSTARS.2015.2486038］
Fan W， Zhou M and Huang R. 2020. Multiscale deep features fusion for change detection. Journal of Image and Graphics， 25（4）： 669-678
樊玮， 周末， 黄睿. 2020. 多尺度深度特征融合的变化检测. 中国图象图形学报， 25（4）： 669-678 ［DOI： 10.11834/jig.190312http://dx.doi.org/10.11834/jig.190312］
Girshick R， Donahue J， Darrell T and Malik J. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus， USA： IEEE： 580-587 ［DOI： 10.1109/CVPR.2014.81http://dx.doi.org/10.1109/CVPR.2014.81］
Gong M G， Cao Y and Wu Q D. 2012. A neighborhood-based ratio approach for change detection in SAR images. IEEE Geoscience and Remote Sensing Letters， 9（2）： 307-311 ［DOI： 10.1109/LGRS.2011.2167211http://dx.doi.org/10.1109/LGRS.2011.2167211］
Gong M G， Zhao J J， Liu J， Miao Q G and Jiao L C. 2016. Change detection in synthetic aperture radar images based on deep neural networks. IEEE Transactions on Neural Networks and Learning Systems， 27（1）： 125-138 ［DOI： 10.1109/TNNLS.2015.2435783http://dx.doi.org/10.1109/TNNLS.2015.2435783］
He K M， Zhang X Y， Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas， USA： IEEE： 770-778 ［DOI： 10.1109/CVPR.2016.90http://dx.doi.org/10.1109/CVPR.2016.90］
Hou B， Wei Q， Zheng Y G and Wang S. 2014. Unsupervised change detection in SAR image based on Gauss-log ratio image fusion and compressed projection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 7（8）： 3297-3317 ［DOI： 10.1109/JSTARS.2014.2328344http://dx.doi.org/10.1109/JSTARS.2014.2328344］
Howard A G， Zhu M L， Chen B， Kalenichenko D， Wang W J， Weyandg T， Andreetto M and Adam H. 2017. MobileNets： Efficient Convolutional Neural Networks for Mobile Vision Applications ［EB/OL］. ［2021-12-16］. https://arxiv.org/pdf/1704.04861.pdfhttps://arxiv.org/pdf/1704.04861.pdf
Hu J， Shen L and Sun G. 2018. Squeeze-and-excitation networks//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City， USA： IEEE： 7132-7141 ［DOI： 10.1109/CVPR.2018.00745http://dx.doi.org/10.1109/CVPR.2018.00745］
Hubara I， Courbariaux M， Soudry D， El-Yaniv R and Bengio Y. 2016. Binarized neural networks//Proceedings of the 30th International Conference on Neural Information Processing Systems. Barcelona， Spain： Curran Associates Inc.： 4114-4122
Jacob B， Kligys S， Chen B， Zhu M L， Tang M， Howard A， Adam H and Kalenichenko D. 2018. Quantization and training of neural networks for efficient integer-arithmetic-only inference//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City， USA： IEEE： 2704-2713 ［DOI： 10.1109/CVPR.2018.00286http://dx.doi.org/10.1109/CVPR.2018.00286］
Krizhevsky A， Sutskever I and Hinton G E. 2017. ImageNet classification with deep convolutional neural networks. Communications of the ACM， 60（6）： 84-90 ［DOI： 10.1145/3065386http://dx.doi.org/10.1145/3065386］
Lecun Y， Bottou L， Bengio Y and Haffner P. 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE， 86（11）： 2278-2324 ［DOI： 10.1109/5.726791http://dx.doi.org/10.1109/5.726791］
Li F F， Liu B， Wang X X， Zhang B and Yan J C. 2016. Ternary weight networks ［EB/OL］. ［2022-11-20］. https://arxiv.org/pdf/1605.04711.pdfhttps://arxiv.org/pdf/1605.04711.pdf
Li Y Y， Peng C， Chen Y Q， Jiao L C， Zhou L H and Shang R H. 2019. A deep learning method for change detection in synthetic aperture radar images. IEEE Transactions on Geoscience and Remote Sensing， 57（8）： 5751-5763 ［DOI： 10.1109/TGRS.2019.2901945http://dx.doi.org/10.1109/TGRS.2019.2901945］
Long J， Shelhamer E and Darrell T. 2015. Fully convolutional networks for semantic segmentation//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston， USA： IEEE： 3431-3440 ［DOI： 10.1109/CVPR.2015.7298965http://dx.doi.org/10.1109/CVPR.2015.7298965］
Simonyan K and Zisserman A. 2015. Very deep convolutional networks for large-scale image recognition//Proceedings of the 3rd International Conference on Learning Representations. San Diego， USA： ［s.n.］
Szegedy C， Liu W， Jia Y Q， Sermanet P， Reed S， Anguelov D， Erhan D， Vanhoucke V and Rabinovich A. 2015. Going deeper with convolutions//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston， USA： IEEE： 1-9 ［DOI： 10.1109/CVPR.2015.7298594http://dx.doi.org/10.1109/CVPR.2015.7298594］
Tong G F， Li Y， Ding W L and Yue X Y. 2015. Review of remote sensing image change detection. Journal of Image and Graphics， 20（12）： 1561-1571
佟国峰， 李勇， 丁伟利， 岳晓阳. 2015. 遥感影像变化检测算法综述. 中国图象图形学报， 20（12）： 1561-1571 ［DOI： 10.11834/jig.20151201http://dx.doi.org/10.11834/jig.20151201］
Wang R F， Ding F， Jiao L C， Chen J W， Liu B， Ma W P and Wang M. 2020. A light-weighted convolutional neural network for bitemporal SAR image change detection ［EB/OL］. ［2021-12-16］. https://arxiv.org/pdf/2005.14376.pdfhttps://arxiv.org/pdf/2005.14376.pdf
Wang R F， Zhang J， Chen J W， Jiao L C and Wang M. 2019. Imbalanced learning-based automatic SAR images change detection by morphologically supervised PCA-net. IEEE Geoscience and Remote Sensing Letters， 16（4）： 554-558 ［DOI： 10.1109/LGRS.2018.2878420http://dx.doi.org/10.1109/LGRS.2018.2878420］
Wang Y H， Gao L R， Chen Z C and Zhang B. 2020. Deep learning and superpixel-based method for high-resolution remote sensing image change detection. Journal of Image and Graphics， 25（6）： 1271-1282
王艳恒， 高连如， 陈正超， 张兵. 2020. 结合深度学习和超像元的高分遥感影像变化检测. 中国图象图形学报， 25（6）： 1271-1282 ［DOI： 10.11834/jig.190319http://dx.doi.org/10.11834/jig.190319］
Yosinski J， Clune J， Bengio Y and Lipson H. 2014. How transferable are features in deep neural networks？//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal， Canada： MIT Press： 3320-3328
Yu F， Koltun V and Funkhouser T. 2017. Dilated residual networks//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu， USA： IEEE： 636-644 ［DOI： 10.1109/CVPR.2017.75http://dx.doi.org/10.1109/CVPR.2017.75］
相关作者
相关机构
京公网安备11010802024621