为解决新型的双源无轨电车的集电杆自动识别集电盒并快速并网的问题,通过改进YOLO-V4(you only look once version 4)网络模型,得到SE-YOLO-POLY(squeeze and excitation networks-you only look once version 4-POLY)网络架构。采用该...为解决新型的双源无轨电车的集电杆自动识别集电盒并快速并网的问题,通过改进YOLO-V4(you only look once version 4)网络模型,得到SE-YOLO-POLY(squeeze and excitation networks-you only look once version 4-POLY)网络架构。采用该网络架构,解决了由于集电盒的大小不一致、高度不一致、拍照角度不一致导致识别的集电盒出现异动的形变和尺寸变化、无法顺利并网的问题。通过SE-YOLO-POLY网络的数据集的生成、模型的设计、训练环境、实际运行反标定方式的搭建等步骤完成网络的部署。改进的模型无论在训练时间、模型大小、识别精度还是在处理速度等方面,都优于传统网络,实现了复杂环境下新型的双源无轨电车的智能并网。展开更多
In this paper, we propose a SAR image ship detection model SSE-Ship that combines image context to extend the detection field of view domain and effectively enhance feature extraction information. This method aims to ...In this paper, we propose a SAR image ship detection model SSE-Ship that combines image context to extend the detection field of view domain and effectively enhance feature extraction information. This method aims to solve the problem of low detection rate in SAR images with ship combination and ship fusion scenes. Firstly, we propose STCSPB network to solve the problem of ship and non-ship object fusion by combining image contextual feature information to distinguish ship and non-ship objects. Secondly, we combine SE Attention to enhance the effective feature information and effectively improve the detection accuracy in combined ship driving scenes. Finally, we conducted extensive experiments on two standard base datasets, SAR-Ship and SSDD, to verify the effectiveness and stability of our proposed method. The experimental results show that the SSE-Ship model has P = 0.950, R = 0.946, mAP_0.5:0.95 = 0.656 and FPS = 50 on the SAR-Ship dataset and mAP_0.5 = 0.964 and R = 0.940 on the SSDD dataset.展开更多
文摘为解决新型的双源无轨电车的集电杆自动识别集电盒并快速并网的问题,通过改进YOLO-V4(you only look once version 4)网络模型,得到SE-YOLO-POLY(squeeze and excitation networks-you only look once version 4-POLY)网络架构。采用该网络架构,解决了由于集电盒的大小不一致、高度不一致、拍照角度不一致导致识别的集电盒出现异动的形变和尺寸变化、无法顺利并网的问题。通过SE-YOLO-POLY网络的数据集的生成、模型的设计、训练环境、实际运行反标定方式的搭建等步骤完成网络的部署。改进的模型无论在训练时间、模型大小、识别精度还是在处理速度等方面,都优于传统网络,实现了复杂环境下新型的双源无轨电车的智能并网。
文摘In this paper, we propose a SAR image ship detection model SSE-Ship that combines image context to extend the detection field of view domain and effectively enhance feature extraction information. This method aims to solve the problem of low detection rate in SAR images with ship combination and ship fusion scenes. Firstly, we propose STCSPB network to solve the problem of ship and non-ship object fusion by combining image contextual feature information to distinguish ship and non-ship objects. Secondly, we combine SE Attention to enhance the effective feature information and effectively improve the detection accuracy in combined ship driving scenes. Finally, we conducted extensive experiments on two standard base datasets, SAR-Ship and SSDD, to verify the effectiveness and stability of our proposed method. The experimental results show that the SSE-Ship model has P = 0.950, R = 0.946, mAP_0.5:0.95 = 0.656 and FPS = 50 on the SAR-Ship dataset and mAP_0.5 = 0.964 and R = 0.940 on the SSDD dataset.
