Geometric Calibration of Artificial Compound Eye System for Large Field of View Three-Dimensional Detection

Jian Huijie1 He Jianzheng1 Wang Keyi1

(1.Department of Precision Machinery and Precision Instrumentation, University of Science and Technology of China, Hefei, Anhui, China 230027)

【Abstract】In order to achieve three-dimensional detection of artificial compound eye system and solve such problems as large field of view and complex imaging process, a global geometric calibration method based on two-cylinder and back-propagation (BP) neural network is proposed. In this method, the powerful mapping ability for arbitrary complex nonlinear relationship of BP neural network is used to take implicit calibration on two cylinders respectively, which set up the mapping relationship between the two-dimensional image coordinates and the cylindrical coordinates. In the three-dimensional measurement, the points on an image are mapped to two points on both the front and the back cylinders. Linking the two points we get a space line, and the intersections of multiple spatial lines are solved by the least square method. The coordinates in the three-dimensional target are then obtained. The experimental results show that the angle error of the artificial compound eye system is within 1 mrad at the field of view of 60° × 30°, and the relative radial error is about 0.6%. Compared with traditional calibration methods based on pore model, this method does not need to consider compound eye imaging model and its parameters. Since the whole calibration process is conducted in the same world coordinates, the direction and location relationships between each eye need not to be accurately known. This method is fully applicable to geometric calibration of artificial compound eye systems, and it can meet the requirements of wide field of view and high precision calibration.

【Keywords】 machine vision; three-dimensional detection; artificial compound eye; calibration; back-propagation neural network; least square method;


【Funds】 National Natural Science Foundation of China (61275011)

Download this article

(Translated by caizhijian)


    [1]Ma M, Guo F, Cao Z, et al. Development of an artificial compound eye system for three-dimensional object detection[J]. Applied Optics, 2014, 53(6): 1166–1172.

    [2]Guo Fang, Wang Keyi, Wu Qinglin. Development of target positioning instrument with multi-channels and large field of view[J]. Optics and Precision Engineering, 2013, 21(1): 26–33(in Chinese).

    [3]Tsai R Y. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses[J]. IEEE Journal on Robotics and Automation, 1987, 3(4): 323–344.

    [4]Zhang Z. A flexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(11): 1330–1334.

    [5]Abdelaziz Y I, Karara H, Hauck M, etal. Direct Linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry[J]. Photogrammetric Engineering and Remote Sensing, 2015, 81(2): 103–107.

    [6]Li Guangle, Huang Wenyou, Liu Qingsong, et al. Improved Zhang′s calibration method and experiments for underwater binocular stereo-vision[J]. Acta Optica Sinica, 2014, 34(12): 1215006(in Chinese).

    [7]Tian Zhen, Zhang Qi, Xiong Jiulong, et al. Large-scale camera calibration with neural network[J]. Acta Optica Sinica, 2011, 31(4): 0415001(in Chinese).

    [8]Cai Sheng, Li Qing′an, Qiao Yanfeng. Camera calibration of attitude measurement system based on BP neural network[J]. Journal of Optoelectronics·Laser, 2007, 18(7): 832–834(in Chinese).

    [9]Jin Weilong, Zhou Meiying. Study on calibration of binocular stereovision based on BP neural network with different layers[J]. Optical Technique, 2015, 41(1): 72–76(in Chinese).

    [10]Tian Xiaochao, Li Zhongke. Binocularvision 3D measurement system calibrated by dual plane method[J]. Electronics Optics&Control, 2015, 22(3): 54–57(in Chinese).

    [11]Wen Tao, Zuo Dongguang, Li Zhongke, et al. Robust accurate camera calibration method[J]. Application Research of Computers, 2015, 32(11): 3489–3491(in Chinese).

    [12]Long Changyu, Zhu Jigui, Guo Yin, et al. Study on close-range photogrammetry based on nonparametric measurement model[J]. Acta Optica Sinica, 2014, 34(12): 1215004(in Chinese).

    [13]Guo Fang, Wang Keyi, Yan Peizheng, et al. Calibration of compound eye system for target positioning with large field of view[J]. Optics and Precision Engineering, 2012, 20(5): 913–920(in Chinese).

    [14]Ma Mengchao. Research onartificial compound eye system for 3D object detection[D]. Hefei: University of Science and Technology of China, 2014(in Chinese).

    [15]Guo F, Yan P Z, Wang K Y. Lenses matching of compound eye for target positioning[C]. SPIE, 2012, 8420: 84200B.

    [16]Ma M, Wang K. Improvement on object detection accuracy by using two compound eye systems[C]. SPIE, 2014, 9282: 92820G.

This Article


CN: 31-1252/O4

Vol 37, No. 02, Pages 174-182

February 2017


Article Outline


  • 1 Introduction
  • 2 Fundamental principles
  • 3 Establishment of cylindrical coordinate system and calibration of eyes
  • 4 Experiments and results analysis
  • 5 Conclusions
  • References