[1]吴雨泽,聂卓赟,周长新.注意力叠加与时序特征融合的目标检测方法[J].华侨大学学报(自然科学版),2022,43(5):650-657.[doi:10.11830/ISSN.1000-5013.202103034]
 WU Yuze,NIE Zhuoyun,ZHOU Changxin.Object Detection Method of Attention Superposition and Temporal Feature Fusion[J].Journal of Huaqiao University(Natural Science),2022,43(5):650-657.[doi:10.11830/ISSN.1000-5013.202103034]
点击复制

注意力叠加与时序特征融合的目标检测方法()
分享到:

《华侨大学学报(自然科学版)》[ISSN:1000-5013/CN:35-1079/N]

卷:
第43卷
期数:
2022年第5期
页码:
650-657
栏目:
出版日期:
2022-09-13

文章信息/Info

Title:
Object Detection Method of Attention Superposition and Temporal Feature Fusion
文章编号:
1000-5013(2022)05-0650-08
作者:
吴雨泽 聂卓赟 周长新
华侨大学 信息科学与工程学院, 福建 厦门 361021
Author(s):
WU Yuze NIE Zhuoyun ZHOU Changxin
College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
关键词:
目标检测网络 注意力机制 轨迹跟踪 时序特征
Keywords:
object detection network attention mechanism trajectory tracking temporal feature
分类号:
TP183;TP391.4
DOI:
10.11830/ISSN.1000-5013.202103034
文献标志码:
A
摘要:
提出一种基于注意力叠加与时序特征融合的目标检测方法.在端到端目标检测(DETR)网络的基础上,依据注意力机制特性,使用注意力权重叠加的方式提取目标物像素级标识,用于实例轨迹的划分.为使目标检测与轨迹跟踪协同作用,通过时序特征融合的方式融合之前轨迹跟踪信息,调整当前帧目标检测效果,从而充分利用视频载体提供的时间维度信息.在公开数据集上,对文中方法进行验证,结果表明:文中方法能有效识别被遮挡的目标物,具有较强鲁棒性.
Abstract:
An object detection method of attention superposition and temporal feature fusion is proposed. Based on the end-to-end object detection(DETR)network, attention weight superposition is used to extract the object pixel-level identification for the division of the instance trajectory according to the characteristics of the attention mechanism. In order to cooperate the object detection and trajectory tracking, the previous track tracking information is fused by the temporal feature fusion to adjust the effect of current frame object detection, so as to make full use of the temporal dimension information provided by the video carrier. The proposed method is experimentally tested on the public data set. The results show that the method in this paper can effectively detect the blocked object and has stronger robustness.

参考文献/References:

[1] 胡珉,周显威,高新闻.公路隧道视频预处理和病害识别算法[J].华侨大学学报(自然科学版),2020,41(5):595-604.DOI:10.11830/ISSN.1000-5013.202002024.
[2] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Columbus:IEEE Press,2014:580-587.DOI:10.1109/CVPR.2014.81.
[3] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.DOI:10.1109/TPAMI.2015.2389824.
[4] 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 Analysis and Machine Intelligence,2017,39(6):1137-1149.DOI:10.1109/TPAMI.2016.2577031.
[5] LIU Wei,ANGUELOV D,ERHAN D,et al.Ssd: Single shot multibox detector[C]//European Conference on Computer Vision.Amsterdam:Springer,2016:21-37.DOI:10.1007/978-3-319-46448-0_2.
[6] LIN T Y,GOYAL P,GIRSHICK R,et al.Focal loss for dense object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,42(2):318-326.
[7] ZHANG Shifeng,WEN Longyin,BIAN Xiao,et al.Single-shot refinement neural network for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE Press,2018:4203-4212.DOI:10.1109/CVPR.2018.00442.
[8] REN J,CHEN Xiaohao,LIU Jianbo,et al.Accurate single stage detector using recurrent rolling convolution[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE Press,2017:5420-5428.DOI:10.1109/CVPR.2017.87.
[9] JIAO Licheng,ZHANG Fan,LIU Fang,et al.A survey of deep learning-based object detection[J].IEEE Access,2019,7:128837-128868.
[10] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Les Vegas:IEEE Press,2016:779-788.DOI:10.1109/CVPR.2016.91.
[11] REDMON J,FARHADI A.YOLO9000: Better, faster, stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE Press,2017:7263-7271.DOI:10.1109/CVPR.2017.690.
[12] TIAN Zhi,SHEN Chunhua,CHEN Hao,et al.Fcos: Fully convolutional one-stage object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.Seoul:IEEE Press,2019: 9627-9636.
[13] CHOI J,CHUN D,KIM H,et al.Gaussian yolov3: An accurate and fast object detector using localization uncertainty for autonomous driving[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.Seoul:IEEE Press,2019:502-511.
[14] CARION N,MASSA F,SYNNAEVE G,et al.End-to-end object detection with transformers[C]//European Conference on Computer Vision.Glasgow:Springer,2020:213-229.
[15] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE Press,2016:770-778.DOI:10.1109/CVPR.2016.90.
[16] VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C]//Proceedings of the 31th International Conference on Neural Information Processing Systems.Long Beach:Curran Associates Inc,2017:6000-6010.
[17] ZHU Xizhou,HU Han,LIN S,et al.Deformable convnets v2: More deformable, better results[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach:IEEE Press,2019:9308-9316.
[18] XIANG Yu,ALAHI A,SAVARESE S.Learning to track: Online multi-object tracking by decision making[C]//Proceedings of the IEEE International Conference on Computer Vision.Santiago:IEEE Press,2015:4705-4713.DOI:10.1109/ICCV.2015.534.
[19] 陈柏生,陈锻生.联合时空特征的车辆跟踪[J].华侨大学学报(自然科学版),2008,29(2):222-224.DOI:10.11830/ISSN.1000-5013.2008.02.0222.
[20] KANG Kai,OUYANG Wanli,LI Hongsheng,et al.Object detection from video tubelets with convolutional neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE Press,2016:817-825.DOI:10.1109/CVPR.2016.95.
[21] CHU Qi,OUYANG Wanli,LI Hongsheng,et al.Online multi-object tracking using CNN-based single object tracker with spatial-temporal attention mechanism[C]//Proceedings of the IEEE International Conference on Computer Vision.Venice:IEEE Press,2017:4836-4845.DOI:10.1109/ICCV.2017.518.
[22] PANG Bo,LI Yizhuo,ZHANG Yifan,et al.Tubetk: Adopting tubes to track multi-object in a one-step training model[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE Press,2020: 6308-6318.
[23] NEUBECK A,VAN GOOL L.Efficient non-maximum suppression[C]//18th International Conference on Pattern Recognition.Hong Kong:IEEE Press,2006:850-855.DOI:10.1109/ICPR.2006.479.
[24] MNIH V,HEESS N,GRAVES A,et al.Recurrent models of visual attention[C]//Advances in Neural Information Processing Systems.New York:Curran Associates,2014:2204-2212.
[25] BAHDANAU D,CHOROWSKI J,SERDYUK D,et al.End-to-end attention-based large vocabulary speech recognition[C]//IEEE International Conference on Acoustics, Speech and Signal Processing.[S.l.]:IEEE Press,2016:4945-4949.
  

相似文献/References:

[1]贺凤,张洪博,杜吉祥,等.长短时记忆网络的自由体操视频自动描述方法[J].华侨大学学报(自然科学版),2020,41(6):808.[doi:10.11830/ISSN.1000-5013.201911047]
 HE Feng,ZHANG Hongbo,DU Jixiang,et al.Floor Exercise Video Automatic Description Method Using Long Short-Term Memory Network[J].Journal of Huaqiao University(Natural Science),2020,41(5):808.[doi:10.11830/ISSN.1000-5013.201911047]
[2]方娜,余俊杰,李俊晓,等.注意力机制下的EMD-GRU短期电力负荷预测[J].华侨大学学报(自然科学版),2021,42(6):817.[doi:10.11830/ISSN.1000-5013.202008003]
 FANG Na,YU Junjie,LI Junxiao,et al.Short-Term Power Load Forecasting Under EMD-GRU Attention Mechanism[J].Journal of Huaqiao University(Natural Science),2021,42(5):817.[doi:10.11830/ISSN.1000-5013.202008003]
[3]钟铭恩,谭佳威,袁彬淦,等.复杂交通环境下二轮机动车乘员头盔检测算法[J].华侨大学学报(自然科学版),2023,44(3):301.[doi:10.11830/ISSN.1000-5013.202212028]
 ZHONG Mingen,TAN Jiawei,YUAN Bingan,et al.Helmet Detection Algorithm of Two-Wheeled Motor Vehicle Occupant in Complex Traffic Environment[J].Journal of Huaqiao University(Natural Science),2023,44(5):301.[doi:10.11830/ISSN.1000-5013.202212028]
[4]方昱龙,王泽锦,王华珍,等.基于模板学习的智能侨情问句生成方法[J].华侨大学学报(自然科学版),2023,44(6):735.[doi:10.11830/ISSN.1000-5013.202304010]
 FANG Yulong,WANG Zejin,WANG Huazhen,et al.Intelligent Question Generation Method Based on Template Learning for Overseas Chinese Situation[J].Journal of Huaqiao University(Natural Science),2023,44(5):735.[doi:10.11830/ISSN.1000-5013.202304010]

备注/Memo

备注/Memo:
收稿日期: 2021-03-21
通信作者: 聂卓赟(1983-),男,副教授,博士,主要从事鲁棒控制及非线性系统的研究.E-mail:yezhuyun2004@sina.com.
基金项目: 国家自然科学基金资助项目(61403149); 福建省自然科学基金资助项目(2019J01053)
更新日期/Last Update: 2022-09-20