计算机科学 ›› 2023, Vol. 50 ›› Issue (1): 98-104.doi: 10.11896/jsjkx.211100149
马玮琦, 袁家斌, 查可可, 范利利
MA Weiqi, YUAN Jiabin, ZHA Keke, FAN Lili
摘要： 深空环境下对星体表面进行岩石障碍物检测是保障巡视器安全探测的重要前提。由于星载计算设备存储容量和数据处理能力受限,大规模复杂计算并不适用于遥远的深空环境;此外,传统的岩石检测算法存在复杂度较高、能耗过大等问题。因此,文中提出了一种多分类语义分割算法Spiking-Unet,利用深度脉冲神经网络实现星体表面岩石的有效检测。首先针对星体表面岩石图像中存在的类不平衡问题,构建LovaszS_CE损失函数并训练Unet网络模型;其次,获取Unet网络模型参数,并通过参数归一化方法将其映射到Spiking-Unet网络;最后,使用基于脉冲发放频率的S-softmax函数实现岩石图像像素级分类。在公开数据集Artificial Lunar Landscape上对所提算法进行了实验,结果表明,Spiking-Unet与拓扑结构相同的Unet模型相比,在精度相近的情况下,Flops减少为原来的1/1000左右,能耗降低为原来的1/600左右。
中图分类号:
| [1]CASTANO R,ESTLIN T,GAINES D,et al.Onboard autonomous rover science[C]//2007 IEEE Aerospace Conference.IEEE,2007:1-13. [2]BURLM C,THOMPSON D R.Rockster:Onboard rock segmentation through edge regrouping[J].Journal of Aerospace Information Systems,2016,13(8):329-342. [3]CASTANO R,JUDD M,ESTLIN T,et al.Current results from a rover science data analysis system[C]//2005 IEEE Aerospace Conference.IEEE,2005:356-365. [4]COMANICIU D,MEER P.Mean shift:A robust approach to-ward feature space analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619. [5]FELZENSZWALB P F,HUTTENLOCHER D P.Efficientgraph-based image segmentation[J].International Journal of Computer Vision,2004,59(2):167-181. [6]SHI J,MALIK J.Normalized cuts and image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):888-905. [7]ACHANTA R,SHAJI A,SMITH K,et al.SLIC superpixelscompared to state-of-the-art superpixel methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2282. [8]GONG X,LIU J.Rock detection via superpixel graph cuts[C]//2012 19th IEEE International Conference on Image Processing.IEEE,2012:2149-2152. [9]DUNLOP H,THOMPSON D R,WETTERGREEN D.Multi-scale features for detection and segmentation of rocks inmars images[C]//2007 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2007:1-7. [10]BOYKOV Y,KOLMOGOROV V.An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(9):1124-1137. [11]MAASS W.Networks of spiking neurons:The third generation of neural network models[J].Neural Networks,1997,10(9):1659-1671. [12]MAASS W,BISHOP C M.Pulsed neural networks[M]//Massachusetts:MIT Press.1999:55-81. [13]MEFTAH B,LEZORAY O,BENYETTOU A.Segmentationand edge detection based on spiking neural network model [J].Neural Processing Letters,2010,32(2):131-146. [14]MEFTAH B,LEZORAY O,LECLUSE M,et al.Cell microscopic segmentation with spiking neuron networks[C]//International Conference on Artificial Neural Networks.Berlin:Springer,2010:117-126. [15]BUHMANN J,LANGE T,RAMACHER U.Image segmentation by networks of spiking neurons [J].Neural Computation.2005,17(5):1010-1031. [16]WU Q X,MCGINNITY T M,MAGUIRE L,et al.Colour image segmentation based on a spiking neural network model inspired by the visual system[C]//International Conference on Intelligent Computing.Berlin:Springer,2010:49-57. [17]KERR D,COLEMAN S,MCGINNITY M,et al.Biologically inspired edge detection[C]//2011 11th International Conference on Intelligent Systems Design and Applications.IEEE,2011:802-807. [18]BERMAN M,TRIKI A R,BLASCHKO M B.The Lovasz-Softmax Loss:A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2018. [19]CAO Y,CHEN Y,KHOSLA D.Spiking deep convolutional neural networks for energy-efficient object recognition[J].International Journal of Computer Vision,2015,113(1):54-66. [20]IZHIKEVICH E M.Which model to use for cortical spikingneurons?[J].IEEE Transactions on Neural Networks,2004,15(5):1063-1070. [21]LIU Y H,WANG X J.Spike-frequency adaptation of a genera-lized leaky integrate-and-fire model neuron[J].Journal of Computational Neuroscience,2001,10(1):25-45. [22]GUO S,WANG L,CHEN B,et al.An overhead-free max-pooling method for snn[J].IEEE Embedded Systems Letters,2019,12(1):21-24. [23]HOROWITZ M.1.1 computing's energy problem(and what we can do about it)[C]//2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers(ISSCC).IEEE,2014:10-14. [24]CHAURASIA A,CULURCIELLO E.Linknet:Exploiting encoder representations for efficient semantic segmentation[C]//2017 IEEE Visual Communications and Image Processing(VCIP).IEEE,2017:1-4. [25]ZHAO H,SHI J,QI X,et al.Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2881-2890. [26]LIN T Y,DOLLÁR P,GIRSHICK R,et al.Feature pyramidnetworks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2117-2125. [27]RONNEBERGER O,FISCHER P,BROX T.U-net:Convolu-tional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Compu-ter-assisted Intervention.Cham:Springer,2015:234-241. |
| [1] | 黄泽南, 刘晓捷, 赵晨晖, 邓亚彬, 郭东辉. 类脑计算脉冲神经网络模型及其学习算法研究进展 Spiking Neural Network Model for Brain-like Computing and Progress of Its Learning Algorithm 计算机科学, 2023, 50(1): 229-242. https://doi.org/10.11896/jsjkx.220100058 |
| [2] | 程成, 降爱莲. 基于多路径特征提取的实时语义分割方法 Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction 计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157 |
| [3] | 胡伏原, 万新军, 沈鸣飞, 徐江浪, 姚睿, 陶重犇. 深度卷积神经网络图像实例分割方法研究进展 Survey Progress on Image Instance Segmentation Methods of Deep Convolutional Neural Network 计算机科学, 2022, 49(5): 10-24. https://doi.org/10.11896/jsjkx.210200038 |
| [4] | 祁颖, 柴艳妹. 基于改进的SLIC和聚类算法结合的高分辨率遥感海冰图像分割 High-resolution Remote Sensing Sea Ice Image Segmentation Based on Combination of ImprovedSLIC Algorithm and Clustering Algorithm 计算机科学, 2022, 49(11A): 211200100-6. https://doi.org/10.11896/jsjkx.211200100 |
| [5] | 金玉杰, 初旭, 王亚沙, 赵俊峰. 变分推断域适配驱动的城市街景语义分割 Variational Domain Adaptation Driven Semantic Segmentation of Urban Scenes 计算机科学, 2022, 49(11): 126-133. https://doi.org/10.11896/jsjkx.220500193 |
| [6] | 张福昌, 仲国强, 毛玉旭. 面向轻量化医学图像分割网络的神经结构搜索 Neural Architecture Search for Light-weight Medical Image Segmentation Network 计算机科学, 2022, 49(10): 183-190. https://doi.org/10.11896/jsjkx.210800052 |
| [7] | 祝一帆, 王海涛, 李可, 吴贺俊. 一种高精度路面裂缝检测网络结构:Crack U-Net Crack U-Net:Towards High Quality Pavement Crack Detection 计算机科学, 2022, 49(1): 204-211. https://doi.org/10.11896/jsjkx.210100128 |
| [8] | 叶中玉, 吴梦麟. 融合时序监督和注意力机制的脉络膜新生血管分割 Choroidal Neovascularization Segmentation Combining Temporal Supervision and Attention Mechanism 计算机科学, 2021, 48(8): 118-124. https://doi.org/10.11896/jsjkx.200600150 |
| [9] | 金海燕, 彭晶, 周挺, 肖照林. 基于Graph Cuts多特征选择的双目图像分割方法 Binocular Image Segmentation Based on Graph Cuts Multi-feature Selection 计算机科学, 2021, 48(8): 150-156. https://doi.org/10.11896/jsjkx.200800221 |
| [10] | 王施云, 杨帆. 基于U-Net特征融合优化策略的遥感影像语义分割方法 Remote Sensing Image Semantic Segmentation Method Based on U-Net Feature Fusion Optimization Strategy 计算机科学, 2021, 48(8): 162-168. https://doi.org/10.11896/jsjkx.200700182 |
| [11] | 许华杰, 张晨强, 苏国韶. 基于深层卷积残差网络的航拍图建筑物精确分割方法 Accurate Segmentation Method of Aerial Photography Buildings Based on Deep Convolutional Residual Network 计算机科学, 2021, 48(8): 169-174. https://doi.org/10.11896/jsjkx.200500096 |
| [12] | 杨秀璋, 武帅, 夏换, 于小民. 基于自适应图像增强技术的水族文字提取与识别研究 Research on Shui Characters Extraction and Recognition Based on Adaptive Image Enhancement Technology 计算机科学, 2021, 48(6A): 74-79. https://doi.org/10.11896/jsjkx.200900070 |
| [13] | 詹瑞, 雷印杰, 陈训敏, 叶书函. 基于多重差异特征网络的街景变化检测 Street Scene Change Detection Based on Multiple Difference Features Network 计算机科学, 2021, 48(2): 142-147. https://doi.org/10.11896/jsjkx.200500158 |
| [14] | 曹林, 于威威. 基于图像分割的自适应窗口双目立体匹配算法研究 Adaptive Window Binocular Stereo Matching Algorithm Based on Image Segmentation 计算机科学, 2021, 48(11A): 314-318. https://doi.org/10.11896/jsjkx.201200264 |
| [15] | 顾兴健, 朱剑峰, 任守纲, 熊迎军, 徐焕良. 多尺度U网络实现番茄叶部病斑分割与识别 Multi-scale U Network Realizes Segmentation and Recognition of Tomato Leaf Disease 计算机科学, 2021, 48(11A): 360-366. https://doi.org/10.11896/jsjkx.201000166 |
|
||
首页