Machine learning-based automatic reinforcing bar image analysis system in the internet of things
- 206 Downloads
Research on the analysis of reinforcing bar images has been conducted to count reinforcing bars moving along a conveyor belt at a bar production plant. It is relatively easy to analyze images at the plant, where the environment and light sources can be tightly controlled. At construction sites, the characteristics of images vary greatly depending on the environment, time of image acquisition, and weather conditions. Therefore, a method for correctly segregating the reinforcing bar area is needed. In this paper, we propose an automatic reinforcing bar image analysis system based on machine learning. Our proposed system accurately separates the bar area from the background and counts the number of bars in the image. Compared with existing method, the proposed system performs better on detection of reinforcing bars.
KeywordsReinforcing bar Machine learning Image analysis Internet of things Quantity management
This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. NRF-2017R1C1B5075856).
- 1.Achanta R et al. (2010) SLIC Superpixels. Technical report 149300 EPFLGoogle Scholar
- 2.Bahaa-Eldeen AM et al (2000) Edge detection of binary images using the method of masks. Comput Vision Patt Recogn Ain Shams Univ Facul Eng Sci Bull 35(3):349–355Google Scholar
- 7.Dietterich TG (2002) Ensemble learning. The handbook of brain theory and Neural NetworkGoogle Scholar
- 10.Gonzalez R, Woods R (2002) Digital image processing. Pearson Education, Upper Saddle River, NJ, pp 572–580Google Scholar
- 11.Ho T (1995) Random decision forests. Proc 3rd Int Conf Doc Anal Recogn: 278–282Google Scholar
- 12.Joshi A et al. (2015) A random forest approach to segmenting and classifying gestures. IEEE Int Conf Autom Face Gesture Recogn 1Google Scholar
- 13.Liu G, Li L, Liu B (2015) Study on recognition method of adhering bars based on support vector machine. Int J Sign Process Image Recogn Patt Recogn 8(9):363–370Google Scholar
- 15.Nie Z et al (2016) A novel algorithm of rebar counting on Conveyor Belt based on machine vision. J Inf Hiding Multimed Sign Process 7(2):425–437Google Scholar
- 19.Shapiro L, Stockman G (2001) Computer vision. Prentice Hall PTR, Upper Saddle River, NJGoogle Scholar
- 20.Zhang D et al. (2008) Bar section image enhancement and positioning method in on-line steel bar counting and automatic separating system. 2008 Congress Image Sign Process: 319–323Google Scholar
- 21.Zhao J et al. (2016) Design of real-time steel bars recognition system based on machine vision. 8th Intell Human-Mach Syst CybernetGoogle Scholar