第6期 伍锡如，等：改进Faster R-CNN的汽车仪表指针实时检测 ·1063· 交通模糊图像增强).智能系统学报，2020,15(3)： on Faster R-CNN method[J].IEEE access,2020,8: 491-498 21804-21812. CAO Jingang,LI Jinhua,ZHENG Guping.Enhance- [23]CHENG Gong,HAN Junwei,ZHOU Peicheng,et al. ment of blurred road-traffic images based on generative Learning rotation-invariant and Fisher discriminative adversarial network[J].CAAI transactions on intelligent convolutional neural networks for object detection[. systems,2020,15(3):491-498. IEEE transactions on image processing,2019,28(1): [17刀曲仕茹，席玉玲，丁松涛.基于深度学习的交通场景语 265-278. 义描述U.西北工业大学学报，2018,36(3)522-527. [24]刘召，张黎明，耿美晓，等.基于改进的Faster R- QU Shiru,XI Yuling,DING Songtao.Image caption de- CNN高压线缆目标检测方法J].智能系统学报， scription of traffic scene based on deep learning[J]. 2019.144):627-634 Journal of Northwestern Polytechnical University,2018, LIU Zhao,ZHANG Liming,GENG Meixiao,et al.Ob- 36(3):522-527 ject detection of high-voltage cable based on improved [18]REN Shaoqing.HE Kaiming,GIRSHICK R,et al.Faster Faster R-CNN[J].CAAI transactions on intelligent sys- R-CNN:towards real-time object detection with region tems,2019,144):627-634 proposal networks[J].IEEE transactions on pattern ana- [25]EVERINGHAM M.VAN GOOL L,WILLIAMS C K I. lysis and machine intelligence,2017,39(6):1137-1149. [19]WU Wenqi,YIN Yingjie,WANG Xingang,et al.Face et al.The PASCAL visual object classes (VOC)chal- detection with different scales based on Faster R- lenge[J].International journal of computer vision,2010, CNN[J].IEEE transactions on cybernetics,2019,49(11): 882:303-338. 4017-4028. 作者简介： [20]徐岩，陶慧青，虎丽丽.基于Faster R-CNN网络模型的 伍锡如.教授.博士，主要研究方 铁路异物侵限检测算法研究「J几.铁道学报，2020. 向为深度学习、复杂网络、机器人控制。 42(5):91-98. XU Yan,TAO Huiqing,HU Lili.Railway foreign body intrusion detection based on Faster R-CNN network model[J].Journal of the China railway society,2020, 42(5):91-98. [21]FANG Fen,LI Liyuan,ZHU Hongyuan,et al.Combin- 邱涛涛，硕士研究生，主要研究方 向为深度学习、图像处理、计算机视觉。 ing Faster R-CNN and model-driven clustering for elongated object detection[J].IEEE transactions on im- age processing,2019,29:2052-2065. [22]LIU Xiaobo,WANG Huaiyuan,JING Hongdi,et al.Re- search on intelligent identification of rock types based交通模糊图像增强 [J]. 智能系统学报, 2020, 15(3): 491–498. CAO Jingang, LI Jinhua, ZHENG Guping. Enhance￾ment of blurred road-traffic images based on generative adversarial network[J]. CAAI transactions on intelligent systems, 2020, 15(3): 491–498. 曲仕茹, 席玉玲, 丁松涛. 基于深度学习的交通场景语 义描述 [J]. 西北工业大学学报, 2018, 36(3): 522–527. QU Shiru, XI Yuling, DING Songtao. Image caption de￾scription of traffic scene based on deep learning[J]. Journal of Northwestern Polytechnical University, 2018, 36(3): 522–527. [17] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern ana￾lysis and machine intelligence, 2017, 39(6): 1137–1149. [18] WU Wenqi, YIN Yingjie, WANG Xingang, et al. Face detection with different scales based on Faster R￾CNN[J]. IEEE transactions on cybernetics, 2019, 49(11): 4017–4028. [19] 徐岩, 陶慧青, 虎丽丽. 基于 Faster R-CNN 网络模型的 铁路异物侵限检测算法研究 [J]. 铁道学报, 2020, 42(5): 91–98. XU Yan, TAO Huiqing, HU Lili. Railway foreign body intrusion detection based on Faster R-CNN network model[J]. Journal of the China railway society, 2020, 42(5): 91–98. [20] FANG Fen, LI Liyuan, ZHU Hongyuan, et al. Combin￾ing Faster R-CNN and model-driven clustering for elongated object detection[J]. IEEE transactions on im￾age processing, 2019, 29: 2052–2065. [21] LIU Xiaobo, WANG Huaiyuan, JING Hongdi, et al. Re￾search on intelligent identification of rock types based [22] on Faster R-CNN method[J]. IEEE access, 2020, 8: 21804–21812. CHENG Gong, HAN Junwei, ZHOU Peicheng, et al. Learning rotation-invariant and Fisher discriminative convolutional neural networks for object detection[J]. IEEE transactions on image processing, 2019, 28(1): 265–278. [23] 刘召, 张黎明, 耿美晓, 等. 基于改进的 Faster R￾CNN 高压线缆目标检测方法 [J]. 智能系统学报, 2019, 14(4): 627–634. LIU Zhao, ZHANG Liming, GENG Meixiao, et al. Ob￾ject detection of high-voltage cable based on improved Faster R-CNN[J]. CAAI transactions on intelligent sys￾tems, 2019, 14(4): 627–634. [24] EVERINGHAM M, VAN GOOL L, WILLIAMS C K I, et al. The PASCAL visual object classes (VOC) chal￾lenge[J]. International journal of computer vision, 2010, 88(2): 303–338. [25] 作者简介： 伍锡如，教授，博士，主要研究方 向为深度学习、复杂网络、机器人控制。 邱涛涛，硕士研究生，主要研究方 向为深度学习、图像处理、计算机视觉。 第 6 期 伍锡如，等：改进 Faster R-CNN 的汽车仪表指针实时检测 ·1063·