A visual positioning method for wedge support robot based on Pruned-Ghost-YOLOv3

Abstract

The wedge support robot is the core module of the intelligent dismantling equipment for the bolster spring and wedge of railroad wagon. In this paper, to address the problem of accurate positioning of bolster hole with abnormal geometry and large error in the complex background, a light-weight object detection model is proposed based on GhostNet and model pruning algorithm: Pruned-Ghost-YOLOv3. The proposed models and the original YOLOv3 model are trained and evaluated on the bolster hole custom dataset. The results show that the improved Pruned- Ghost-YOLOv3 model is smaller, has fewer parameters and is faster compared to the original YOLOv3 model. To meet the requirements of operational efficiency and reliability, a precise positioning algorithm based on the bounding box of the bolster hole and an indirect positioning process are proposed in this paper. The comparative experiments of bolster hole positioning and wedge support are conducted on the wedge support robot. The experimental results show that the proposed Pruned-Ghost-YOLOv3 model can meet the requirements of rapid detection and positioning of the bolster holes, and the proposed precise positioning algorithm and robot positioning process have high accuracy and reliability. The research results are successfully applied to the development of a railroad wagon wedge support robot, and it has a good reference value for the development of the intelligent positioning system of heterogeneous workpiece operation robots in the complex background of related industries.

Keywords

Wedge support bolster hole visual positioning YOLOv3 object detection light-weight neural network

Get full access to this article

View all access options for this article.

References

Fadol

SAM

. Summary of structural strength analysis of bogie frame based on finite element method. J Res Sci Eng 2021; 3: 89–92.

Liu

Jiang

, et al. MGBM-YOLO: a faster light-weight object detection model for robotic grasping of bolster spring based on image-based visual servoing. J Intell Robot Syst 2022; 104: 17.

Ibarguren

Martínez-Otzeta

Maurtua

Particle filtering for industrial 6DOF visual servoing. J Intell Robot Syst 2014; 74: 689–696.

Zhao

Wang

Zuo

, et al. Palletizing robot positioning bolt detection based on improved YOLO-V3. J Intell Robot Syst 2022; 104: 12.

Redmon

Divvala

Girshick

, et al. You only look once: unified, real-time object detection. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), Seattle, WA, Jun 27–30 2016, pp.779–788. New York: IEEE.

Liu

Anguelov

Erhan

, et al. SSD: single shot multibox detector. In: 14th European conference on computer vision (ECCV), Amsterdam, Netherlands, 8–16 October 2016, Computer vision - ECCV 2016, pt i, pp.21–37. Cham: Springer.

Lin

Goyal

Girshick

, et al. Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell2020; 42: 318–327.

Cheng

Bai

, et al. Tiny-retina net: a one-stage detector for real-time object detection. In: 11th international conference on graphics and image processing (ICGIP), Zhejiang Gongshang Univ, Hangzhou, Peoples Republic of China, 12–14 October 2019. Bellingham: Spie-Int Soc Optical Engineering.

Zhao

Sheng

Wang

, et al. M2Det: a single-shot object detector based on multi-level feature pyramid network. In: 33rd AAAI conference on artificial intelligence / 31st innovative applications of artificial intelligence conference / 9th AAAI symposium on educational advances in artificial intelligence, Honolulu, HI, 27 January–1 February 2019, pp.9259–9266. Palo Alto: Assoc Advancement Artificial Intelligence.

10.

Iandola

Moskewicz

Ashraf

, et al. Squeezenet: alexnet-level accuracy with 50x fewer parameters and <1mb model size. CoRR 2016; abs/1602.07360.

11.

Szegedy

Liu

Jia

, et al. Going deeper with convolutions. CoRR 2014; abs/1409.4842.

12.

Gholami

Kwon

, et al. Squeezenext: hardware-aware neural network design. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), Salt Lake City, UT, 18–22 June 2018, pp.1719–1728. New York: IEEE.

13.

Harjoseputro

Yuda

Danukusumo

KP.

MobileNets: efficient convolutional neural network for identification of protected birds. Int J Adv Sci Eng Inf Technol 2020; 10: 2290.

14.

Sandler

Howard

Zhu

, et al. MobileNetV2: inverted residuals and linear bottlenecks. In: 31st IEEE/CVF conference on computer vision and pattern recognition (CVPR), Salt Lake City, UT, 18–23 June 2018, pp.4510–4520. New York: IEEE.

15.

Howard

Sandler

Chu

, et al. Searching for MobileNetV3. In: IEEE/CVF international conference on computer vision (ICCV), Seoul, South Korea, 27 October–2 November 2019, pp.1314–1324. New York: IEEE.

16.

Zhang

Zhou

Lin

, et al. ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: 31st IEEE/CVF conference on computer vision and pattern recognition (CVPR), Salt Lake City, UT, 18–23 June 2018, pp.6848–6856. New York: IEEE.

17.

Zhang

Zheng

, et al. ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: 15th European conference on computer vision (ECCV), Munich, Germany, 8–14 September 2018, Computer vision - ECCV 2018, pt xiv, pp.122–138.

18.

Tan

. EfficientNet: rethinking model scaling for convolutional neural networks. In: 36th international conference on machine learning (ICML), Long Beach, CA, 9–15 June 2019, vol. 97.

19.

Han

Wang

Tian

, et al. GhostNet: more features from cheap operations. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), Electr Network, 14–19 June 2020, pp.1577–1586. New York: IEEE.

20.

Jacob

Kligys

Chen

, et al. Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: 31st IEEE/CVF conference on computer vision and pattern recognition (CVPR), Salt Lake City, UT, 18–23 June 2018, pp.2704–2713. New York: IEEE.

21.

Kadav

Durdanovic

, et al. Pruning filters for efficient convNets. CoRR 2016; abs/1608.08710.

22.

Liu

Shen

, et al. Learning efficient convolutional networks through network slimming. In: 16th IEEE international conference on computer vision (ICCV), Venice, Italy, 22–29 October 2017, pp.2755–2763. New York: IEEE.

23.

Shen

Sun

, et al. Squeeze-and-excitation networks. In: 31st IEEE/CVF conference on computer vision and pattern recognition (CVPR), Salt Lake City, UT, 18–23 June 2018, pp.7132–7141. New York: IEEE.

24.

Liu

Cong

. Vehicle detection method based on ghostNet-SSD. In: 2020 international conference on virtual reality and intelligent systems (ICVRIS), 18–19 July 2020, pp.200–203. New York: IEEE.

25.

Zhang

Ren

, et al. Delving deep into rectifiers: surpassing human-level performance on imagenet classification. IEEE i conf comp vis, 2015, pp.1026–1034. New York: IEEE. DOI: 10.1109/Iccv.2015.123.

26.

Han

Mao

Dally

WJ.

Deep compression: compressing deep neural network with pruning, trained quantization and huffman coding. CoRR 2015; abs/1510.00149.

27.

A tutorial for monocular visual servoing. Zidonghua Xuebao 2018; 44: 1729–1746.

28.

Iwatsuki

Okiyama

A new formulation of visual servoing based on cylindrical coordinate system. IEEE Trans Robot 2005; 21: 266–273.

29.

Pal

SK.

A review on image segmentation techniques. Pattern Recognit 1993; 26: 1277–1294.

30.

Tongloy

Boonsang

. An image-based visual servo control system based on an eye-in-hand monocular camera for autonomous robotic grasping. In: International conference on instrumentation, control and automation (ICA), Bandung, Indonesia, 29–31 August 2016, pp.132–136. New York: IEEE.

31.

Zhang

A flexible new technique for camera calibration. IEEE Trans Pattern Anal Mach Intell 2000; 22: 1330–1334.