A Circular Target Stability Detection Method Based on Deep Learning Image Super-resolution

被引：1

作者：

Cui H. ^{[1
]}

Xu Z. ^{[1
]}

Yang Y. ^{[2
]}

Meng Y. ^{[1
]}

Wang B. ^{[1
]}

机构：

[1] College of Mechanical & Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing

[2] Manufacturing Engineering Department, AVIC Xi'an Aircraft Industry Group Company Ltd., Xi'an

来源：

Zhongguo Jixie Gongcheng/China Mechanical Engineering | 2021年 / 32卷 / 23期

关键词：

Circular target; Deep learning; Object recognition; Super-resolution;

D O I：

10.3969/j.issn.1004-132X.2021.23.010

中图分类号：

学科分类号：

摘要：

In order to improve the recognition rate and location accuracy of circular targets under the conditions of long-distance and large deflection angle, a circular target stability detection method was proposed based on deep learning image super-resolution. The multi-angle and multi-distance image sets were constructed through a hybrid data set of real images and synthetic images, the pixel loss and perceptual loss were used to improve the loss function of image super-resolution model, so the super-resolution reconstruction of images might be realized and the image details of target contours might be enriched. By using the pretrained super-resolution model, the images were reconstructed. Finally, traditional detection algorithm was used to recognize and locate the circular targets. The experimental results show that the circular target recognition rate is increased by 40%, and the target location accuracy is increased by 8.47%. © 2021, China Mechanical Engineering Magazine Office. All right reserved.

引用

页码：2861 / 2867

页数：6

共 16 条

[1] JIANG Tao, CHENG Xiaosheng, CUI Haihua, A Calibration Strategy for Vision-guided Robot Assembly System of Large Cabin[J], Measurement, 163, (2020)
[2] WEN Zhuoman, WANG Yanjie, DI Nan, Et al., Fast Recognition of Cooperative Target Used for Position and Orientation Measurement of Space Station's Robot Arm, Acta Aeronautica et Astronautica Sinica, 36, 4, pp. 1330-1338, (2015)
[3] ZHANG Xiaodi, CUI Haihua, CHENG Xiaosheng, Et al., Design and Detection of Circular Coded Marker Based on Concentric Circles, Machine Building and Automation, 49, 2, pp. 133-136, (2020)
[4] OLSON E., AprilTag:a Robust and Flexible Visual Fiducial System[C], IEEE International Conference on Robotics and Automation, pp. 3400-3407, (2011)
[5] GARRIDO S, MUNOZ R, MADRID F J, Et al., Automatic Generation and Detection of Highly Reliable Fiducial Markers under Occlusion[J], Pattern Recognition, 47, 6, pp. 2280-2292, (2014)
[6] WANG Ying, ZHANG Rui, In-pipe Surface Circular Structured Light 3D Vision Inspection System, Infrared and Laser Engineering, 43, 3, pp. 891-896, (2014)
[7] ZHOU Shenjiang, YU Houyun, Research on Decode Algorithm of Coded Targets in Close-range Photogrammetry, Machine Building and Automation, 48, 3, pp. 182-184, (2019)
[8] SU Heng, ZHOU Jie, ZHANG Zhihao, Survey of Super-resolution Image Reconstruction Methods, Acta Automatica Sinica, 39, 8, pp. 1202-1213, (2013)
[9] ZHANG Zhizhuo, WAN Lili, XU Wanru, Et al., Estimating a 2D Pose from a Tiny Person Image with Super-resolution Reconstruction[J], Computers and Electrical Engineering, 93, 2, (2021)
[10] YANG Xianing, WANG Banghai, LI Zuolong, Super-resolution Reconstruction of Aerial Images Based on Hierarchical Feature Fusion Network, Computer Engineering and Applications

← 1 2 →