目标检测的多尺度定位提升算法

doi:10.19665/j.issn1001-2400.2021.03.011

Abstract

Abstract:

For the target detection task,there are two problems in the one-stage network structure of the deep neural network model.First,whether the design of the anchor box hyperparameter is suitable or not will affect the training results of the whole network;second,a large down sampling factor will affect the positioning ability of the target.To solve these problems,this paper proposes a multi-location enhancement network.The structure of the one-stage network model is redesigned,and a better scheme for selecting the super parameters of the anchor frame is proposed.So the efficiency of the first stage network is ensured and the positioning accuracy is better than the previous one.A large number of experiments show that the multi-location enhancement network can achieve a higher positioning accuracy while ensuring real-time performance.The average accuracy of 82.5 is achieved on the public dataset (Pascal VOC 2007).

Key words: neural networks, multiscalepositioning, objectdetection, convolutional neural network

CLC Number:

TN957.52

WANG Ping,JIANG Yuze,ZHAO Guanghui. Object detection based on the multiscale location Enhancement network[J].Journal of Xidian University, 2021, 48(3): 85-90.

Figures/Tables 8

References 11

[1]	FU C Y, LIU W, RANGA A, et al. Dssd:Deconvolutional Single Shot Detector[J/OL]. [2019-12-02]. https://arxiv.org/pdf/1701.06659.pdf.
[2]	YI J, WU P, METAXAS D N. ASSD:Attentive Single Shot Multibox Detector[J/OL]. [2019-12-02]. https://arxiv.org/pdf/1909.12456.pdf.
[3]	REDMON J, FARHADI A. Yolov3:An Incremental Improvement[J/OL]. [2019-12-02]. https://arxiv.org/pdf/1804.02767.pdf.
[4]	ZHANG S, WEN L, BIAN X, et al. Single-shot Refinement Neural Network for Object Detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway:IEEE, 2018: 4203-4212.
[5]	LIU Z, DU J, TIAN F, et al. MR-CNN:A Multi-Scale Region-Based Convolutional Neural Network for Small Traffic Sign Recognition[J]. IEEE Access, 2019,7:57120-57128. doi: 10.1109/Access.6287639
[6]	TERMRITTHIKUN C, JAMTSHO Y, MUNEESAWANG P. An Improved Residual Network Model for Image Recognition Using a Combination of Snapshot Ensembles and the Cutout Technique[J/OL]. [2019-12-02]. https://ieexplore.ieee.org/stamp/stamp.jsp arnumer=8701699.
[7]	XIE S, GIRSHICK R, DOLLAR P, et al. Aggregated Residual Transformations for Deep Neural Networks[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway:IEEE, 2017: 1492-1500.
[8]	WU Y, TANG S, ZHANG S, et al. An Enhanced Feature Pyramid Object Detection Network for Autonomous Driving[J]. Applied Sciences, 2019,9(20):4363. doi: 10.3390/app9204363
[9]	ZHU Y, ZHAO C, WANG J, et al. Couplenet:Coupling Global Structure with Local Parts for Object Detection[C]// Proceedings of the 2017 IEEE International Conference on Computer Vision(ICCV).Piscataway:IEEE, 2017: 4146-4154.
[10]	许强, 李伟, 占荣辉, 等. 一种改进的卷据神经网络SAR目标识别算法[J]. 西安电子科技大学学报, 2018,45(5):177-183.
	XU Qiang, LI Wei, ZHAN Ronghui, et al. Improved Algorithm for SAR Target RecognitionBased on the Convolutional Neural Network[J]. Journal of Xidian University, 2018,45(5):177-183.
[11]	马苗, 许西丹, 武杰. 一种耦合深度信念网络的图像识别方法[J]. 西安电子科技大学学报, 2018,45(5):102-107.
	MA Miao, XU Xidan, WU Jie. Coupled-deep Belief NetworkBased Method for Image Recognition[J]. Journal of Xidian University, 2018,45(5):102-107.

平均精度 /%	锚框长宽比
平均精度 /%	1∶1	1∶2	1∶3	1∶4
82.1	√
82.3	√		√	√
82.4	√	√		√
82.5	√	√	√
82.5	√	√	√	√

方法	主干网络	输入尺寸/像素	FPS/(帧·s^-1)	VOC 2007,平均精度/%
MR-CNN	VGG-16	1 000×600	0.03	78.2
CoupleNet	ResNet-101	1 000×600	8.20	82.7
ASSD 512	VGG-16	512×512	19.00	80.0
DSSD 513	VGG-16	513×513	5.50	81.5
RefineDet 512	VGG-16	512×512	24.10	81.8
YOLOv 3-608	darknet	608×608	19.60	82.2
多尺度定位提升网络	VGG-16	512×512	22.10	82.5

[1]	LV Wenkai,YANG Pengfei,DING Yunqing,ZHANG Heyu,ZHENG Tianyang. JEDERL:A task scheduling optimization algorithm for heterogeneous computing platforms [J]. Journal of Xidian University, 2021, 48(6): 67-74.
[2]	YU Haoyang,YIN Liang,LI Shufang,LV Shun. Recognition algorithm for the little sample radar modulation signal based on the generative adversarial network [J]. Journal of Xidian University, 2021, 48(6): 96-104.
[3]	SUN Yanjing,WEI Li,ZHANG Nianlong,YUN Xiao,DONG Kaiwen,GE Min,CHENG Xiaozhou,HOU Xiaofeng. Person re-identification method combining the DD-GAN and Global feature in a coal mine [J]. Journal of Xidian University, 2021, 48(5): 201-211.
[4]	ZHOU Peng,YANG Jun. Semantic segmentation of remote sensing images based on neural architecture search [J]. Journal of Xidian University, 2021, 48(5): 47-57.
[5]	YANG Yunhang,MIN Lianquan. Multi-scalefusion sketch recognition model by dilated convolution [J]. Journal of Xidian University, 2021, 48(5): 92-99.
[6]	CHEN Changchuan,WANG Haining,HUANG Lian,HUANG Tao,LI Lianjie,HUANG Xiangkang,DAI Shaosheng. Facial expression recognition based on local representation [J]. Journal of Xidian University, 2021, 48(5): 100-109.
[7]	SONG Jianfeng,MIAO Qiguang,WANG Chongxiao,XU Hao,YANG Jin. Multi-scale single object tracking based on the attention mechanism [J]. Journal of Xidian University, 2021, 48(5): 110-116.
[8]	ZHANG Yuhao,CHENG Peitao,ZHANG Shuhao,WANG Xiumei. Lightweight image super-resolution with the adaptive weight learning network [J]. Journal of Xidian University, 2021, 48(5): 15-22.
[9]	HUI Haisheng,ZHANG Xueying,WU Zelin,LI Fenglian. Method for stroke lesion segmentation using the primary-auxiliary path attention compensation network [J]. Journal of Xidian University, 2021, 48(4): 200-208.
[10]	SONG Jianqiao,WANG Feng,NIU Jin,SHI Zezhou,MA Junhui. Potential emotion recognition based on the fusion of the spatio-temporal neural network and facial pulse signals [J]. Journal of Xidian University, 2021, 48(4): 159-167.
[11]	CAO Yi,CAI Xiaodong. Effective learning strategy for hard samples [J]. Journal of Xidian University, 2021, 48(3): 99-105.
[12]	GUO Zekun,TIAN Long,HAN Ning,WANG Penghui,LIU Hongwei,CHEN Bo. Radar HRRP based few-shot target recognition with CNN-SSD [J]. Journal of Xidian University, 2021, 48(2): 7-14.
[13]	ZHANG Shudong,GAO Haichang,CAO Xiwen,KANG Shuai. Adaptive fast and targeted adversarial attack for speech recognition [J]. Journal of Xidian University, 2021, 48(1): 168-175.
[14]	CHENG Lei,WANG Yue,TIAN Chunna. Residual attention mechanism for visual tracking [J]. Journal of Xidian University, 2020, 47(6): 148-157.
[15]	KONG Xin,CHEN Gang,GONG Guoliang,LU Huaxiang,Mao Wenyu. High performance multiply-accumulator for the convolutional neural networks accelerator [J]. Journal of Xidian University, 2020, 47(4): 55-63.

Object detection based on the multiscale location Enhancement network

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 11

Related Articles 15

Metrics

Comments

Recommended 10