一种新的输电线路异物检测网络结构——TLFOD Net
|
摘要
高压输电线路上悬挂的漂浮异物可能会对输电产生巨大危害,而现有的物体识别方法无法对不规则物体进行有效识别。为此,本文提出一种异物检测的新型网络结构:TLFOD Net(Transmission Line Foreign Object Detection Net)。针对异物特点设计的TLFOD Net网络结构,主要包括特征提取网络、区域生成网络和分类回归网络3个部分;优化了合适的候选框;并提出端到端的TLFOD Net联合训练方式以提高网络训练的性能。采用图像预处理技术,增加训练集的数量。通过实验结果分析表明,TLFOD Net比现有的网络在识别速度以及识别精度上均有显著提高。
Floating foreign bodies suspended on high voltage transmission lines may cause great harm to power transmission,but the existing object detection methods can not effectively identify irregular objects. This paper proposes a new network structure for foreign body detection: TLFOD Net( Transmission Line Foreign Object Detection Net). According to the characteristics of foreign bodies,this paper designs the TLFOD Net network structure,which mainly includes feature extraction network,region proposal network and classified regression network,optimizes suitable candidate boxes and proposes end-to-end joint training mode to improve the performance of TLFOD Net. Through image reversal technology,the number of training sets is increased. The experimental results show that TLFOD Net improves the detection speed and accuracy significantly compared with the existing networks.
Floating foreign bodies suspended on high voltage transmission lines may cause great harm to power transmission,but the existing object detection methods can not effectively identify irregular objects. This paper proposes a new network structure for foreign body detection: TLFOD Net( Transmission Line Foreign Object Detection Net). According to the characteristics of foreign bodies,this paper designs the TLFOD Net network structure,which mainly includes feature extraction network,region proposal network and classified regression network,optimizes suitable candidate boxes and proposes end-to-end joint training mode to improve the performance of TLFOD Net. Through image reversal technology,the number of training sets is increased. The experimental results show that TLFOD Net improves the detection speed and accuracy significantly compared with the existing networks.
引文
[1]邓益民,汤智谦,李红兵,等.基于LOD的大规模输电线路场景实时渲染算法优化[J].计算机与现代化,2017(1):115-118.
[2]宋璇坤,韩柳,鞠黄培,等.中国智能电网技术发展实践综述[J].电力建设,2016,37(7):1-11.
[3] WANG J J,WANG J H,SHAO J W,et al. Image recognition of icing thickness on power transmission lines based on a least squares Hough transform[J]. Energies,2017,10(4),doi:10. 3390/en10040415.
[4] BAKER L,MILLS S,LANGLOTZ T,et al. Power line detection using Hough transform and line tracing techniques[C]//Proceedings of the 2016 International Conference on Image and Vision Computing New Zealand(IVCNZ).2016,doi:10. 1109/IVCNZ. 2016. 7804438.
[5]赵永生,徐海青,吴立刚,等.基于霍夫直线变换的输电线路异物识别应用研究[J].数字技术与应用,2017(3):127-129.
[6]周封,任贵新.基于颜色空间变量的输电线图像分类及特征提取[J].电力系统保护与控制,2018,46(5):89-98.
[7]黄东芳.基于一种改进的Hough变换的输电线路图像中导线识别研究[D].南宁:广西大学,2016.
[8]黄习飞,刘柏宏,苏亮亮,等.基于多窗口中值滤波和迭代高斯滤波的去除图像椒盐噪声的方法[J].科技视界,2018(3):77-78.
[9]邱志祺.基于中值滤波与小波变换的图像去噪研究[D].唐山:华北理工大学,2015.
[10]余永龙.结合双边滤波与暗通道的图像去雾算法及应用研究[D].南昌:南昌航空大学,2015.
[11] YE H M,YAN S L,HUANG P L. 2D Otsu image segmentation based on cellular genetic algorithm[C]//Proceedings of the 2017 IEEE 9th International Conference on Communication Software and Networks(ICCSN). 2017:1313-1316.
[12] CHA Y J,YOU K S,CHOI W. Vision-based detection of loosened bolts using the Hough transform and support vector machines[J]. Automation in Construction,2016,71:181-188.
[13]孔媛媛.基于Hough变换定位与遗传算法的脑肿瘤分割方法研究[D].南昌:南昌航空大学,2018.
[14]石殷巧,刘守印,马超.基于深度学习的短视频中的物体检测与内容推荐系统研究[J].计算机与现代化,2018(11):69-76.
[15] REN X D,DU S P,ZHENG Y. Parallel RCNN:A deep learning method for people detection using RGB-D images[C]//Proceedings of the 2017 10th International Congress on Image and Signal Processing,Bio Medical Engineering and Informatics(CISP-BMEI). 2017,doi:10. 1109/CISPBMEI. 2017. 8302069.
[16] LI Y,STEVENSON R L. Multimodal image registration with line segments by selective search[J]. IEEE Transactions on Cybernetics,2017,47(5):1285-1298.
[17] PURKAIT P,ZHAO C,ZACH C. SPP-Net:Deep Absolute Pose Regression with Synthetic Views[DB/OL].(2017-12-09). https://arxiv. org/pdf/1712. 03452. pdf.
[18] QIAN R Q,LIU Q Y,YUE Y,et al. Road surface traffic sign detection with hybrid region proposal and fast R-CNN[C]//Proceedings of the 2016 12th International Conference on Natural Computation,Fuzzy Systems and Knowledge Discovery(ICNC-FSKD). 2016:555-559.
[19] EGGERT C,BREHM S,WINSCHEL A,et al. A closer look:Small object detection in faster R-CNN[C]//Proceedings of the 2017 IEEE International Conference on Multimedia and Expo(ICME). 2017:421-426.
[20] KONG T,YAO A B,CHEN Y R,et al. Hyper Net:Towards accurate region proposal generation and joint object detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016:845-853.
[21]张洪涛,路红英,刘腾飞,等.基于深度学习的显著性检测方法模型——SCS[J].计算机与现代化,2018(4):48-55.
[22] LIN T Y,DOLLR P,GIRSHICK R B,et al. Feature pyramid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017:936-944.
[23]王德宇,徐友春,李永乐,等.基于深度学习的车辆检测方法[J].计算机与现代化,2017(8):56-60.
[2]宋璇坤,韩柳,鞠黄培,等.中国智能电网技术发展实践综述[J].电力建设,2016,37(7):1-11.
[3] WANG J J,WANG J H,SHAO J W,et al. Image recognition of icing thickness on power transmission lines based on a least squares Hough transform[J]. Energies,2017,10(4),doi:10. 3390/en10040415.
[4] BAKER L,MILLS S,LANGLOTZ T,et al. Power line detection using Hough transform and line tracing techniques[C]//Proceedings of the 2016 International Conference on Image and Vision Computing New Zealand(IVCNZ).2016,doi:10. 1109/IVCNZ. 2016. 7804438.
[5]赵永生,徐海青,吴立刚,等.基于霍夫直线变换的输电线路异物识别应用研究[J].数字技术与应用,2017(3):127-129.
[6]周封,任贵新.基于颜色空间变量的输电线图像分类及特征提取[J].电力系统保护与控制,2018,46(5):89-98.
[7]黄东芳.基于一种改进的Hough变换的输电线路图像中导线识别研究[D].南宁:广西大学,2016.
[8]黄习飞,刘柏宏,苏亮亮,等.基于多窗口中值滤波和迭代高斯滤波的去除图像椒盐噪声的方法[J].科技视界,2018(3):77-78.
[9]邱志祺.基于中值滤波与小波变换的图像去噪研究[D].唐山:华北理工大学,2015.
[10]余永龙.结合双边滤波与暗通道的图像去雾算法及应用研究[D].南昌:南昌航空大学,2015.
[11] YE H M,YAN S L,HUANG P L. 2D Otsu image segmentation based on cellular genetic algorithm[C]//Proceedings of the 2017 IEEE 9th International Conference on Communication Software and Networks(ICCSN). 2017:1313-1316.
[12] CHA Y J,YOU K S,CHOI W. Vision-based detection of loosened bolts using the Hough transform and support vector machines[J]. Automation in Construction,2016,71:181-188.
[13]孔媛媛.基于Hough变换定位与遗传算法的脑肿瘤分割方法研究[D].南昌:南昌航空大学,2018.
[14]石殷巧,刘守印,马超.基于深度学习的短视频中的物体检测与内容推荐系统研究[J].计算机与现代化,2018(11):69-76.
[15] REN X D,DU S P,ZHENG Y. Parallel RCNN:A deep learning method for people detection using RGB-D images[C]//Proceedings of the 2017 10th International Congress on Image and Signal Processing,Bio Medical Engineering and Informatics(CISP-BMEI). 2017,doi:10. 1109/CISPBMEI. 2017. 8302069.
[16] LI Y,STEVENSON R L. Multimodal image registration with line segments by selective search[J]. IEEE Transactions on Cybernetics,2017,47(5):1285-1298.
[17] PURKAIT P,ZHAO C,ZACH C. SPP-Net:Deep Absolute Pose Regression with Synthetic Views[DB/OL].(2017-12-09). https://arxiv. org/pdf/1712. 03452. pdf.
[18] QIAN R Q,LIU Q Y,YUE Y,et al. Road surface traffic sign detection with hybrid region proposal and fast R-CNN[C]//Proceedings of the 2016 12th International Conference on Natural Computation,Fuzzy Systems and Knowledge Discovery(ICNC-FSKD). 2016:555-559.
[19] EGGERT C,BREHM S,WINSCHEL A,et al. A closer look:Small object detection in faster R-CNN[C]//Proceedings of the 2017 IEEE International Conference on Multimedia and Expo(ICME). 2017:421-426.
[20] KONG T,YAO A B,CHEN Y R,et al. Hyper Net:Towards accurate region proposal generation and joint object detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016:845-853.
[21]张洪涛,路红英,刘腾飞,等.基于深度学习的显著性检测方法模型——SCS[J].计算机与现代化,2018(4):48-55.
[22] LIN T Y,DOLLR P,GIRSHICK R B,et al. Feature pyramid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017:936-944.
[23]王德宇,徐友春,李永乐,等.基于深度学习的车辆检测方法[J].计算机与现代化,2017(8):56-60.