The goal of the article is research of ways to improve the quality of neural networks object detection. To achieve this goal we suggest to use synthetic image datasets. The algorithm of generating synthetic images, which uses the environment of the detected object, is described in the article. That algorithm could be applied in the control algorithm of the robotic system for luminaire replacement that is based on target object detection. 3D models and 3D camera images of detected objects, backgrounds, noise objects and different effects are used to create realistic images that will increase the quality of predictions. Quality tests were made with synthetic and real datasets. Results show that quality could be increased up to 16%. Ratio of real and synthetic data is 1:4.
L. Mylnikov, “Statistical methods of intelligent data analysis,” St. Petersburg: BHV-Petersburg, 2021, 240 p.
Z. Zou, Z. Shi, Y. Guo, and J. Ye, “Object Detection in 20 Years: A Survey,” arXiv, pp. 1-39, May 2019.
P. Slivnitsin, A. Bachurin, and L. Mylnikov, “Robotic system position control algorithm based on target object recognition, ” in Proceedings of International Conference on Applied Innovation in IT, vol. 8, no. 1, pp. 87-94, 2020.
P. A. Slivnitsin and A. A. Bachurin, “A modern way of outdoor lighting maintenance, ” in Journal of Physics: Conference Series, vol. 1415, no. 1, 2019.
T. Anwar, “Training a Custom Object Detector with DLIB & Making Gesture Controlled Applications,” 2020 [Online]. Available: https://www.learnopencv.com/training-a-custom- object-detector-with-dlib-making-gesture-controlled- applications/ [Accessed: 07-Dec-2020].
J. Li, P. L. Götvall, J. Provost, and K. Åkesson, “Training Convolutional Neural Networks with Synthesized Data for Object Recognition in Industrial Manufacturing,” IEEE Int. Conf. Emerg. Technol. Fact. Autom. ETFA, vol. 2019-Septe, pp. 1544-1547, 2019.
M. Andulkar, J. Hodapp, T. Reichling, M. Reichenbach, and U. Berger, “Training CNNs from Synthetic Data for Part Handling in Industrial Environments,” IEEE Int. Conf. Autom. Sci. Eng., vol. 2018-Augus, pp. 624–629, 2018.
D. Mas Montserrat, Q. Lin, J. P. Allebach, and E. J. Delp, “Scalable Logo Detection and Recognition with Minimal Labeling,” Proc. - IEEE 1st Conf. Multimed. Inf. Process. Retrieval, MIPR 2018, pp. 152-157, 2018.
G. Volk, S. Muller, A. Von Bernuth, D. Hospach, and O. Bringmann, “Towards Robust CNN-based Object Detection through Augmentation with Synthetic Rain Variations,” 2019 IEEE Intell. Transp. Syst. Conf. ITSC 2019, pp. 285-292, 2019.
G. Georgakis, A. Mousavian, A. C. Berg, and J. Košecká, “Synthesizing training data for object detection in indoor scenes,” Robot. Sci. Syst., vol. 13, 2017.
H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, and S. Savarese, “Generalized intersection over union: A metric and a loss for bounding box regression,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2019, vol. 2019-June, pp. 658-666.
G. T. U. A. Colleges, et al., “Microsoft COCO,” Eccv, no. June, pp. 740-755, 2014.
M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, “The pascal visual object classes (VOC) challenge,” Int. J. Comput. Vis., vol. 88, no. 2, pp. 303-338, 2010.
J. Redmon and A. Farhadi, “YOLO v.3,” Tech Rep., pp. 1-6, 2018.
W. He, Z. Huang, Z. Wei, C. Li, and B. Guo, “TF- YOLO: An improved incremental network for real- time object detection,” Appl. Sci., vol. 9, no. 16, 2019.
P. G. Doyle, “Grinstead and Snell's Introduction to Probability,” 2006, American Mathematical Society. 518 p
J. Redmon and A. Farhadi, “YOLO: Real-Time Object Detection,” 2018 [Online]. Available: https://pjreddie.com/darknet/yolo/. [Accessed: 25-Nov-2020].
·
This work is licensed under a
Creative Commons Attribution-ShareAlike 4.0 International License
