第3期 洪恺临，等：改进Center-.Net网络的自主喷涂机器人室内窗户检测 ·431· al of computer-aided design&computer graphics,2019, Conference on Computer Vision(ECCV).Munich,Ger 31(9):1494-1501 many,2018:765-781 [2]ALI H,SEIFERT C,JINDAL N,et al.Window detection [13]ZHANG Shifeng,CHI Cheng,YAO Yongqiang,et al. in facades[C]//14th International Conference on Image Bridging the gap between anchor-based and anchor-free Analysis and Processing (ICIAP 2007).Modena,Italy, detection via adaptive training sample selection[C]//Pro- 2007:837-842 ceedings of the IEEE/CVF Conference on Computer Vis- [3]孔倩倩，赵辽英，张莉.基于图像轮廓分析的室内窗户检 ion and Pattern Recognition.Seattle,USA,2020: 测[J.计算机与现代化.2018(4)：56-61 9756-9765. KONG Qiangian,ZHAO Liaoying,ZHANG Li.Indoor [14]DUAN Kaiwen,BAI Song,XIE Lingxi,et al.CenterNet: window detection based on image contour analysis[J]. keypoint triplets for object detection[C]//Proceedings of Computer and modernization,2018(4):56-61. the IEEE/CVF International Conference on Computer [4]缪君，储珺，张桂梅.基于图像边缘与玻璃属性约束的窗 Vision.Seoul,Korea(South),2019:6568-6577. 户检测U.图学学报，2015,36(5：776-782. [15]TIAN Zhi,SHEN Chunhua,CHEN Hao,et al.FCOS: MIAO Jun,CHU Jun,ZHANG Guimei.Window detec- fully convolutional one-stage object detection[C]//Pro- tion based on constraints of image edges and glass attrib- ceedings of the IEEE/CVF International Conference on utes[J]Journal of graphics,2015,36(5):776-782. Computer Vision.Seoul,Korea (South),2019:9626- [5]GIRSHICK R.Fast R-CNN[Cl/Proceedings of 2015 IEEE 9635. International Conference on Computer Vision.Santiago, [16]HAN Kai,WANG Yunhe,TIAN Qi,et al.GhostNet: Chile.2015:1440-1448. more features from cheap operations[C]//Proceedings of [6]REN Shaoqing,HE Kaiming,GIRSHICK R,et al.Faster the IEEE/CVF Conference on Computer Vision and Pat- R-CNN:towards real-time object detection with region tern Recognition.Seattle,USA,2020:1577-1586. proposal networks[J].IEEE transactions on pattern analys- [17]HU Jie,SHEN Li,SUN Gang.Squeeze-and-excitation is and machine intelligence,2017,39(6):1137-1149 networks[C]//Proceedings of the IEEE/CVF Conference [7]HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Spa- on Computer Vision and Pattern Recognition.Salt Lake tial pyramid pooling in deep convolutional networks for Ciy,USA,2018:7132-7141 visual recognition[J.IEEE transactions on pattern analys- [18]HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al. is and machine intelligence,2015,37(9):1904-1916 Deep residual learning for image recognition[Cl/Proceed- [8]REDMON J,DIVVALA S,GIRSHICK R,et al.You only ings of the IEEE Conference on Computer Vision and look once:unified,real-time object detection[C]//Proceed- Pattern Recognition.Las Vegas,USA,2016:770-778. ings of 2016 IEEE Conference on Computer Vision and [19]NEWELL A,YANG Kaiyu,DENG Jia.Stacked hour- Pattern Recognition.Las Vegas,USA,2016:779-788. glass networks for human pose estimation[C]//14th [9]LIU Wei,ANGUELOV D,ERHAN D,et al.SSD:single European Conference on Computer Vision.Amsterdam, shot MultiBox detector[C]//14th European Conference on The Netherlands,2016:483-499. Computer Vision.Amsterdam,The Netherlands,2016: [20]YU F,WANG Dequan,SHELHAMER E,et al.Deep lay- 21-37. er aggregation[C]//Proceedings of the IEEE/CVF Confer- [10]LIN T Y,GOYAL P,GIRSHICK R,et al.Focal loss for ence on Computer Vision and Pattern Recognition.Salt dense object detection[Cl//Proceedings of the IEEE Inter- Lake City,USA,2018:2403-2412. national Conference on Computer Vision.Venice,Italy, [21]HUANG Gao,LIU Shichen,VAN DER MAATEN L,et 2017:2999-3007. al.CondenseNet:an efficient DenseNet using learned [11]ZHU Chenchen,HE Yihui,SAVVIDES M.Feature se- group convolutions[C]//Proceedings of the IEEE/CVF lective anchor-free module for single-shot object detec- Conference on Computer Vision and Pattern Recognition. tion[C]//Proceedings of the IEEE/CVF Conference on Salt Lake City,USA,2018:2752-2761 Computer Vision and Pattern Recognition.Long Beach, [22]PAN Junting,SAYROL E,GIRO-I-NIETO X,et al.Shal- USA,2019:840-849 low and deep convolutional networks for saliency predic- [12]LAW H,DENG Jia.CornerNet:detecting objects as tion[C]//Proceedings of the IEEE Conference on Com- paired keypoints[C]//Proceedings of the 15th European puter Vision and Pattern Recognition.Las Vegas,USA,al of computer-aided design & computer graphics, 2019, 31(9): 1494–1501. ALI H, SEIFERT C, JINDAL N, et al. Window detection in facades[C]//14th International Conference on Image Analysis and Processing (ICIAP 2007). Modena, Italy, 2007: 837−842. [2] 孔倩倩, 赵辽英, 张莉. 基于图像轮廓分析的室内窗户检 测 [J]. 计算机与现代化, 2018(4): 56–61. KONG Qianqian, ZHAO Liaoying, ZHANG Li. Indoor window detection based on image contour analysis[J]. Computer and modernization, 2018(4): 56–61. [3] 缪君, 储珺, 张桂梅. 基于图像边缘与玻璃属性约束的窗 户检测 [J]. 图学学报, 2015, 36(5): 776–782. MIAO Jun, CHU Jun, ZHANG Guimei. Window detec￾tion based on constraints of image edges and glass attrib￾utes[J]. Journal of graphics, 2015, 36(5): 776–782. [4] GIRSHICK R. Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile, 2015: 1440−1448. [5] 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 analys￾is and machine intelligence, 2017, 39(6): 1137–1149. [6] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Spa￾tial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE transactions on pattern analys￾is and machine intelligence, 2015, 37(9): 1904–1916. [7] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceed￾ings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 779−788. [8] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//14th European Conference on Computer Vision. Amsterdam, The Netherlands, 2016: 21−37. [9] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE Inter￾national Conference on Computer Vision. Venice, Italy, 2017: 2999−3007. [10] ZHU Chenchen, HE Yihui, SAVVIDES M. Feature se￾lective anchor-free module for single-shot object detec￾tion[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA, 2019: 840−849. [11] LAW H, DENG Jia. CornerNet: detecting objects as paired keypoints[C]//Proceedings of the 15th European [12] Conference on Computer Vision (ECCV). Munich, Ger￾many, 2018: 765−781. ZHANG Shifeng, CHI Cheng, YAO Yongqiang, et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]//Pro￾ceedings of the IEEE/CVF Conference on Computer Vis￾ion and Pattern Recognition. Seattle, USA, 2020: 9756−9765. [13] DUAN Kaiwen, BAI Song, XIE Lingxi, et al. CenterNet: keypoint triplets for object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Seoul, Korea (South), 2019: 6568−6577. [14] TIAN Zhi, SHEN Chunhua, CHEN Hao, et al. FCOS: fully convolutional one-stage object detection[C]//Pro￾ceedings of the IEEE/CVF International Conference on Computer Vision. Seoul, Korea (South), 2019: 9626− 9635. [15] HAN Kai, WANG Yunhe, TIAN Qi, et al. GhostNet: more features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pat￾tern Recognition. Seattle, USA, 2020: 1577−1586. [16] HU Jie, SHEN Li, SUN Gang. Squeeze-and-excitation networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018: 7132−7141. [17] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//Proceed￾ings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 770−778. [18] NEWELL A, YANG Kaiyu, DENG Jia. Stacked hour￾glass networks for human pose estimation[C]//14th European Conference on Computer Vision. Amsterdam, The Netherlands, 2016: 483−499. [19] YU F, WANG Dequan, SHELHAMER E, et al. Deep lay￾er aggregation[C]//Proceedings of the IEEE/CVF Confer￾ence on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018: 2403−2412. [20] HUANG Gao, LIU Shichen, VAN DER MAATEN L, et al. CondenseNet: an efficient DenseNet using learned group convolutions[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018: 2752−2761. [21] PAN Junting, SAYROL E, GIRO-I-NIETO X, et al. Shal￾low and deep convolutional networks for saliency predic￾tion[C]//Proceedings of the IEEE Conference on Com￾puter Vision and Pattern Recognition. Las Vegas, USA, [22] 第 3 期 洪恺临，等：改进 Center-Net 网络的自主喷涂机器人室内窗户检测 ·431·