李梅等：基于TATLNet的输电场景威胁检测 515· 示，会产生一定的误报警.在后续的研究中将会对 [12]Jiao L,Zhang F,Liu F,et al.A survey of deep learning-based 系统进行进一步延伸，实现大型机械与输电线路 object detection.IEEE Access,2019(7):128837 相对距离的检测，从而消除大型机械在输电线路 [13]Zou Z,Shi Z,Guo Y,et al Object detection in 20 years:a survey[J/OL].arXiv preprint (2019-05-13)[2019-09-15]. 威胁距离以外时产生的报警 https://arxiv.org/abs/1905.05241 参考文献 [14]Liu W,Anguelov D,Erhan D,et al.SSD:single shot multibox detector /European Conference on Computer Vision.Amsterdam, [1]Minker G A.Transmission Line Safery Monitoring System:U.S. 2016:21 Patent,,6377184.2002-4-23 [15]Redmon J,Divvala S,Girshick R,et al.You only look once: [2]Luo X,Zhang L Y,Luo W J,et al.Research on UAV patrol unified,real-time object detection /Proceedings of the IEEE control system based on pyroelectric infrared sensor.Technol Conference on Computer Vision and Pattern Recognition Econom Guide,2019,27(8):3 Amsterdam,2016:779 (罗霞，张良勇，罗文金，等.基于热释电红外传感器的无人机巡 [16]Law H,Deng J.CornerNet:detecting objects as paired keypoints// 检控制系统研究.科技经济导刊，2019,27(8)：3) Proceedings of the European Conference on Computer Vision. [3]Lu Y X,Kumar A,Zhai S F,et al.Fully-adaptive feature sharing Munich,2018:734 in multi-task networks with applications in person attribute [17]Girshick R,Donahue J,Darrell T,et al.Rich feature hierarchies for classification l Proceedings of the IEEE Conference on Computer accurate object detection and semantic segmentation / Vision and Pattern Recognition.Honolulu,2017:5334 Proceedings of the IEEE Conference on Computer Vision and [4]He Y H,Zhang X Y,Sun J.Channel pruning for accelerating very Pattern Recognition.Columbus,2014:580 deep neural networks l Proceedings of the IEEE International [18]Girshick R.Fast R-CNN Proceedings of the IEEE International Conference on Computer Vision.Venice,2017:1389 Conference on Computer Vision.Santiago,2015:1440 Han S,Mao HZ.Dally WJ.Deep compression:compressing deep [19]Ren S Q,He K M,Girshick R,et al.Faster R-CNN:towards real- neural networks with pruning,trained quantization and huffman time object detection with region proposal networks /Advances in coding[J/OL].arXiv preprint (2016-02-15)[2019-09-15] Neural Information Processing Systems.Montreal,2015:91 https://arxiv.org/abs/1510.00149 [20]He K M,Gkioxari G,Dollar P,et al.Mask R-CNN /Proceedings [6]Goodfellow I,Pouget-Abadie J,Mirza M,et al.Generative of the IEEE International Conference on Computer Vision adversarial nets l/Advances in Neural Information Processing Honolulu,2017:2961 Systems.Montreal,2014:2672 [21]Huang R,Pedoeem J,Chen C X.YOLO-LITE:a real-time object [7]Duan S Z,Wei K Q.Research on active early warning monitoring detection algorithm optimized for non-GPU computers //2018 system for preventing exteral force damage of transmission lines. IEEE International Conference on Big Data (Big Data).Seattle, Theor Res Urban Constr,2017(15):6 2018:2503 (段树忠，魏可强.输电线路主动预警式防外力破坏监控系统研 [22]Howard A G,Zhu M,Chen B,et al.MobileNets:efficient 究.城市建设理论研究，2017(15)：6) convolutional neural networks for mobile vision [8]Guo S,Zeng Y H,Zhang J B,et al.Application of intelligent applications[J/OL].arXiv preprint (2017-04-17)[2019-09-15]. monitoring system for external force damage prevention for https://arxiv.org/abs/1704.04861 transmission lines.Guangdong Electr Power,2018,31(4):139 [23]Zhang X Y,Zhou X Y,Lin M X,et al.ShuffleNet:an extremely (郭圣，曾懿辉，张纪宾，等.输电线路防外力破坏智能监控系统 efficient convolutional neural network for mobile devices / 的应用.广东电力，2018,31(4)：139) Proceedings of the IEEE Conference on Computer Vision and [9]LeCun Y,Bengio Y,Hinton G.Deep learning.Nature,2015, Pattern Recognition.Salt Lake City,2018:6848 521(7553):436 [24]Radford A,MetzL,Chintala S.Unsupervised representation [10]Krizhevsky A,Sutskever I,Hinton G E.ImageNet classification learning with deep convolutional generative adversarial with deep convolutional neural networks /Advances in Neural networks[J/OL].arXiv preprint (2016-01-07)[2019-09-15] Information Processing Systems.Lake Tahoe,2012:1097 https://arxiv.org/abs/1511.06434 [11]Papageorgiou C P,Oren M,Poggio T.A general framework for [25]Lin T Y,Dollar P,Girshick R,et al.Feature pyramid networks for object detection ll Sixth International Conference on Computer object detection Proceedings of the IEEE Conference on Vision.Tampa,1998:555 Computer Vision and Pattern Recognition.Honolulu,2017:2117示，会产生一定的误报警. 在后续的研究中将会对 系统进行进一步延伸，实现大型机械与输电线路 相对距离的检测，从而消除大型机械在输电线路 威胁距离以外时产生的报警. 参    考    文    献 Minker  G  A. Transmission Line Safety Monitoring System:  U.S. Patent, 6377184. 2002-4-23 [1] Luo  X,  Zhang  L  Y,  Luo  W  J,  et  al.  Research  on  UAV  patrol control  system  based  on  pyroelectric  infrared  sensor. Technol Econom Guide, 2019, 27（8）: 3 （罗霞, 张良勇, 罗文金, 等. 基于热释电红外传感器的无人机巡 检控制系统研究. 科技经济导刊, 2019, 27（8）：3） [2] Lu Y X, Kumar A, Zhai S F, et al. Fully-adaptive feature sharing in  multi-task  networks  with  applications  in  person  attribute classification // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, 2017: 5334 [3] He Y H, Zhang X Y, Sun J. Channel pruning for accelerating very deep  neural  networks  // Proceedings of the IEEE International Conference on Computer Vision. Venice, 2017: 1389 [4] Han S, Mao H Z, Dally W J. Deep compression: compressing deep neural  networks  with  pruning,  trained  quantization  and  huffman coding[J/OL]. arXiv preprint (2016-02-15)[2019-09-15]. https://arxiv.org/abs/1510.00149 [5] Goodfellow  I,  Pouget-Abadie  J,  Mirza  M,  et  al.  Generative adversarial  nets  // Advances in Neural Information Processing Systems. Montreal, 2014: 2672 [6] Duan S Z, Wei K Q. Research on active early warning monitoring system for preventing external force damage of transmission lines. Theor Res Urban Constr, 2017（15）: 6 （段树忠, 魏可强. 输电线路主动预警式防外力破坏监控系统研 究. 城市建设理论研究, 2017（15）：6） [7] Guo  S,  Zeng  Y  H,  Zhang  J  B,  et  al.  Application  of  intelligent monitoring  system  for  external  force  damage  prevention  for transmission lines. Guangdong Electr Power, 2018, 31（4）: 139 （郭圣, 曾懿辉, 张纪宾, 等. 输电线路防外力破坏智能监控系统 的应用. 广东电力, 2018, 31（4）：139） [8] LeCun  Y,  Bengio  Y,  Hinton  G.  Deep  learning. Nature,  2015, 521（7553）: 436 [9] Krizhevsky  A,  Sutskever  I,  Hinton  G  E.  ImageNet  classification with  deep  convolutional  neural  networks  // Advances in Neural Information Processing Systems. Lake Tahoe, 2012: 1097 [10] Papageorgiou  C  P,  Oren  M,  Poggio  T.  A  general  framework  for object  detection  // Sixth International Conference on Computer Vision. Tampa, 1998: 555 [11] Jiao  L,  Zhang  F,  Liu  F,  et  al.  A  survey  of  deep  learning-based object detection. IEEE Access, 2019（7）: 128837 [12] Zou  Z,  Shi  Z,  Guo  Y,  et  al  Object  detection  in  20  years:  a survey[J/OL]. arXiv preprint (2019-05-13)[2019-09-15]. https://arxiv.org/abs/1905.05241 [13] Liu  W,  Anguelov  D,  Erhan  D,  et  al.  SSD:  single  shot  multibox detector // European Conference on Computer Vision. Amsterdam, 2016: 21 [14] Redmon  J,  Divvala  S,  Girshick  R,  et  al.  You  only  look  once: unified,  real-time  object  detection  // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Amsterdam, 2016: 779 [15] Law H, Deng J. CornerNet: detecting objects as paired keypoints // Proceedings of the European Conference on Computer Vision. Munich, 2018: 734 [16] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate  object  detection  and  semantic  segmentation  // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus, 2014: 580 [17] Girshick R. Fast R-CNN // Proceedings of the IEEE International Conference on Computer Vision. Santiago, 2015: 1440 [18] Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real￾time object detection with region proposal networks // Advances in Neural Information Processing Systems. Montreal, 2015: 91 [19] He K M, Gkioxari G, Dollár P, et al. Mask R-CNN // Proceedings of the IEEE International Conference on Computer Vision. Honolulu, 2017: 2961 [20] Huang R, Pedoeem J, Chen C X. YOLO-LITE: a real-time object detection  algorithm  optimized  for  non-GPU  computers  //  2018 IEEE International Conference on Big Data (Big Data).  Seattle, 2018: 2503 [21] Howard  A  G,  Zhu  M,  Chen  B,  et  al.  MobileNets:  efficient convolutional  neural  networks  for  mobile  vision applications[J/OL]. arXiv preprint (2017-04-17)[2019-09-15]. https://arxiv.org/abs/1704.04861 [22] Zhang X Y, Zhou X Y, Lin M X, et al. ShuffleNet: an extremely efficient  convolutional  neural  network  for  mobile  devices  // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 6848 [23] Radford  A,  Metz  L,  Chintala  S.  Unsupervised  representation learning  with  deep  convolutional  generative  adversarial networks[J/OL]. arXiv preprint (2016-01-07)[2019-09-15]. https://arxiv.org/abs/1511.06434 [24] Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object  detection  // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, 2017: 2117 [25] 李    梅等： 基于 TATLNet 的输电场景威胁检测 · 515 ·