期刊文献+

基于深度学习的输电线路杆塔鸟窝识别方法研究 被引量:1

下载PDF
导出
摘要 为实现输电线路杆塔中鸟窝的快速准确检测,提出一种基于RetinaNet深度学习模型的鸟窝识别方法,利用ResNet-50进行前期特征提取,通过FPN网络对前期标准特征进行加强,构建特征金字塔影像,以满足不同尺度大小的鸟窝目标检测,然后在特征金字塔的基础上构建了一个分类子网和回归子网,分别用于识别鸟窝和回归鸟窝的具体位置。通过与经典目标检测方法进行详细对比分析,利用F1-Score精度指标和检测速度指标对检测效果进行了量化分析,实验结果表明,所采用的鸟窝检测模型F1-Score指标可达0.932,优于其他三种经典方法,并能充分应对拍摄角度、遮挡等各种复杂场景问题。
出处 《机电信息》 2020年第24期22-23,共2页
  • 相关文献

参考文献1

二级参考文献15

  • 1Enzweiler M, Gavrila D M. Monocular Pedestrian Detection: Survey and Experiments [ J ]. IEEE Tran- sactions on Pattern Analysis and Machine Intelligence, 2009,31 (12) :2179-2195.
  • 2Zhang L, Nevatia R. Efficient Scan-window Based Object Detection Using GPGPU [ C ]//Proceedings of 2008 IEEE Computer Society Confence on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press ,2008 : 1-7.
  • 3Bauer S, Kohler S, Doll K, et al. FPGA-GPU Architecture for Kernel SVM Pedestrian Detection [ C ]// Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington D. C. ,USA:IEEE Press,2010:61-68.
  • 4Chen Yanping,Li Shaozi,Lin Xianming. Fast Hog Feature Computation Based on CUDA [ C ]//Proceedings of 2011 IEEE International Conference on Computer Science and Automation Engineering. Washington D.C., USA: IEEE Press ,2011:748-751.
  • 5Cao T P, Deng Guang. Real-time Vision-based Stop Sign Detection System on FPGA I C //Proceedings of DICTA' 08. Washington D. C. , USA : IEEE Press, 2008 : 465-471.
  • 6Kadota R, Sugano H, Hiromoto M, et al. Hardware Architecture for HOG Feature Extraction I C //Proceedings of the 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing. Washington D.C. , USA: IEEE Press ,2009 : 1330-1333.
  • 7Hiromoto M,Miyamoto R. Hardware Architecture for High- accuracy Real-time Pedestrian Detection with CoHOG Features [ C ]//Proceedings of the 12th International Conference on Computer Vision. Washington D. C. , USA: IEEE Press ,2009:894-899.
  • 8Negi K,Dohi K, Shibata Y, et al. Deep Pipelined Onechip FPGA Implementation of a Real-time Image-based Human Detection Algorithm I C ]//Proceedings of Inter- national Conference on Field-programmable Technology.Washington D. C. , USA : IEEE Press ,2011 : 1-8.
  • 9Mizuno K, Terachi Y, Takagi K, et al. Architectural Study of HOG Feature Extraction Processor for Real- time Object Detection [ C ]//Proceedings of 2012 IEEE Workshop on Signal Processing Systems (SiPS). Washington D. C. , USA : IEEE Press ,2012 : 197-202.
  • 10Hahnle M, Saxen F, Hisung M, et al. FPGA-based Real- time Pedestrian Detection on High-resolution Images[ C // Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Washington D. C., USA: IEEE Press ,2013:629-635.

共引文献73

同被引文献3

引证文献1

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部