[1]赵文清,周震东,翟永杰.基于反卷积和特征融合的SSD小目标检测算法[J].智能系统学报,2020,15(2):310-316.[doi:10.11992/tis.201905035]
ZHAO Wenqing,ZHOU Zhendong,ZHAI Yongjie.SSD small target detection algorithm based on deconvolution and feature fusion[J].CAAI Transactions on Intelligent Systems,2020,15(2):310-316.[doi:10.11992/tis.201905035]
点击复制
ZHAO Wenqing,ZHOU Zhendong,ZHAI Yongjie.SSD small target detection algorithm based on deconvolution and feature fusion[J].CAAI Transactions on Intelligent Systems,2020,15(2):310-316.[doi:10.11992/tis.201905035]
基于反卷积和特征融合的SSD小目标检测算法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
15
期数:
2020年第2期
页码:
310-316
栏目:
学术论文—机器学习
出版日期:
2020-03-05
- Title:
- SSD small target detection algorithm based on deconvolution and feature fusion
- Keywords:
- small target detection; deconvolution; feature mapping; multi-scale; feature fusion; SSD model; PASCAL VOC dataset; KITTI dataset
- 分类号:
- TP18
- 摘要:
- 由于小目标的低分辨率和噪声等影响，大多数目标检测算法不能有效利用特征图中小目标的边缘信息和语义信息，导致其特征与背景难以区分，检测效果差。为解决SSD(single shot multibox detector)模型中小目标特征信息不足的缺陷，提出反卷积和特征融合的方法。先采用反卷积作用于浅层特征层，增大特征图分辨率，然后将SSD模型中卷积层conv11_2的特征图上采样，拼接得到新的特征层，最后将新的特征层与SSD模型中固有的4个尺度的特征层进行融合。通过将改进后的方法与VOC2007数据集和KITTI车辆检测数据集上的SSD和DSSD方法进行比较，结果表明：该方法降低了小目标的漏检率，并提升整体目标的平均检测准确率。
- Abstract:
- Given the low resolution and noise of small targets, most target detection algorithms cannot effectively utilize the edge and semantic information of small targets in feature maps, which makes it difficult to distinguish the features from the background. Thus, the detection effect is poor. To solve the problem of insufficient feature information of small and medium targets in the single shot MultiBox detector (SSD) model, we propose a method based on deconvolution and feature fusion. First, deconvolution is employed to process the shallow feature layer to increase the resolution of the feature graph. Then, the feature map of the convolution layer conv11_2 in the SSD model is sampled and spliced. Subsequently, a new layer of features is obtained. Finally, the new layer of features is combined with the feature layer of the four scales inherent in the SSD model. The improved method is compared with the SSD and DSSD methods on the VOC2007 dataset and KITTI vehicle detection dataset. The results show that the method reduced the missed detection rate of small targets and improved the average detection accuracy of all targets.
- 参考文献/References:
-
[1] 杨会成, 朱文博, 童英. 基于车内外视觉信息的行人碰撞预警方法[J]. 智能系统学报, 2019, 14(4): 752-760
YANG Huicheng, ZHU Wenbo, TONG Ying. Pedestrian collision warning system based on looking-in and looking-out visual information analysis[J]. CAAI transactions on intelligent systems, 2019, 14(4): 752-760
[2] 姚群力, 胡显, 雷宏. 深度卷积神经网络在目标检测中的研究进展[J]. 计算机工程与应用, 2018, 54(17): 1-9
YAO Qunli, HU Xian, LEI Hong. Application of deep convolutional neural network in object detection[J]. Computer engineering and applications, 2018, 54(17): 1-9
[3] 龙敏, 佟越洋. 应用卷积神经网络的人脸活体检测算法研究[J]. 计算机科学与探索, 2018, 12(10): 1658-1670
LONG Min, TONG Yueyang. Research on face liveness detection algorithm using convolutional neural network[J]. Journal of frontiers of computer science and technology, 2018, 12(10): 1658-1670
[4] 张慧, 王坤峰, 王飞跃. 深度学习在目标视觉检测中的应用进展与展望[J]. 自动化学报, 2017, 43(8): 1289-1305
ZHANG Hui, WANG Kunfeng, WANG Feiyue. Progress and prospect of application of deep learning in target vision detection[J]. Acta automatica sinica, 2017, 43(8): 1289-1305
[5] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA, 2014: 580-587.
[6] 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.
[7] HE Kaiming, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[C]//Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy, 2017: 2980-2988.
[8] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, The Netherland, 2016: 21-37.
[9] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016: 779-788.
[10] FU Chengyang, LIU Wei, RANGA A, et al. DSSD: deconvolutional single shot detector[C]//Computer Vision and Pattern Recognition, 2017.
[11] SINGH B, DAVIS L S. An analysis of scale invariance in object detection-SNIP[C]//Proceedings of 2018 IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018.
[12] BODLA N, SINGH B, CHELLAPPA R, et al. Soft-NMS-improving object detection with one line of code[C]//Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy, 2017: 5562-5570.
[13] LIU Songtao, HUANG Di, WANG Yunhong. Receptive field block net for accurate and fast object detection[C]//Proceedings of ECCV2018, 2018
[14] KIM S W, KOOK H K, SUN J Y, et al. Parallel feature pyramid network for object detection[C]//Proceedings of the 15th European Conference on Computer Vision-ECCV 2018. Munich, Germany, 2018: 239-256.
[15] 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.
[16] ZHU Chenchen, HE Yihui, SAVVIDES M. Feature selective anchor-free module for single-shot object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2019.
[17] 郭川磊, 何嘉. 基于转置卷积操作改进的单阶段多边框目标检测方法[J]. 计算机应用, 2018, 38(10): 2833-2838
GUO Chuanlei, HE Jia. Improved single shot multibox detector based on the transposed convolution[J]. Journal of computer applications, 2018, 38(10): 2833-2838
[18] 吴天舒, 张志佳, 刘云鹏, 等. 基于改进SSD的轻量化小目标检测算法[J]. 红外与激光工程, 2018, 47(7): 0703005
WU Tianshu, ZHANG Zhijia, LIU Yunpeng, et al. A lightweight small object detection algorithm based on improved SSD[J]. Infrared and laser engineering, 2018, 47(7): 0703005
- 相似文献/References:
-
[1]赵文清,孔子旭,赵振兵.隔级融合特征金字塔与CornerNet相结合的小目标检测[J].智能系统学报,2021,16(1):108.[doi:10.11992/tis.202004033]
ZHAO Wenqing,KONG Zixu,ZHAO Zhenbing.Small target detection based on a combination of feature pyramid and CornerNet[J].CAAI Transactions on Intelligent Systems,2021,16():108.[doi:10.11992/tis.202004033]
[2]毛莺池,唐江红,王静,等.基于Faster R-CNN的多任务增强裂缝图像检测方法[J].智能系统学报,2021,16(2):286.[doi:10.11992/tis.201910004]
MAO Yingchi,TANG Jianghong,WANG Jing,et al.Multi-task enhanced dam crack image detection based on Faster R-CNN[J].CAAI Transactions on Intelligent Systems,2021,16():286.[doi:10.11992/tis.201910004]
[3]齐鹏宇,王洪元,张继,等.基于改进FCOS的拥挤行人检测算法[J].智能系统学报,2021,16(4):811.[doi:10.11992/tis.202010012]
QI Pengyu,WANG Hongyuan,ZHANG Ji,et al.Crowded pedestrian detection algorithm based on improved FCOS[J].CAAI Transactions on Intelligent Systems,2021,16():811.[doi:10.11992/tis.202010012]
[4]李海丰,李纪霖,王怀超,等.复杂机场道面外来异物高精度实时检测算法[J].智能系统学报,2023,18(3):525.[doi:10.11992/tis.202110014]
LI Haifeng,LI Jilin,WANG Huaichao,et al.High-precision real-time detection algorithm for foreign object debris on complex airport pavements[J].CAAI Transactions on Intelligent Systems,2023,18():525.[doi:10.11992/tis.202110014]
[5]魏旋旋,黄子健,曹乐,等.采用轻量级姿态估计网络的脊柱侧弯筛查方法[J].智能系统学报,2023,18(5):1039.[doi:10.11992/tis.202203038]
WEI Xuanxuan,HUANG Zijian,CAO Le,et al.Scoliosis screening method using lightweight pose estimation network[J].CAAI Transactions on Intelligent Systems,2023,18():1039.[doi:10.11992/tis.202203038]
备注/Memo
收稿日期:2019-05-16。
基金项目:国家自然科学基金项目(61773160)
作者简介:赵文清，教授，博士，主要研究方向为人工智能与数据挖掘。发表学术论文50余篇;周震东，硕士研究生，主要研究方向为机器学习和基于深度学习的小目标检测;翟永杰，教授，博士，主要研究方向为模式识别与计算机视觉、机器学习与人工智能等。参与省级以上科研项目50余项。发表学术论文100余篇
通讯作者:赵文清.E-mail:jbzwq@126.com
更新日期/Last Update:
1900-01-01