Evaluation of grapevine sucker segmentation algorithms for precision targeted spray

Xu Shasha, Li Wenbin, Kang Feng, Zheng Yongjun, Lan Yubin

Abstract


Chemical sucker control has been proven to be an effective substitute for manual and mechanical removals. Recognition and location of suckers is the key technology of precision targeted spray which can reduce spray volume than current spray pattern. The goal of this research was to develop a quick and effective segmentation algorithm of sucker images for real-time mobile targeted spray by evaluating and comparing seven segmentation algorithms categorized into segmentation based on color feature (ExG, ExGExR, and CIVE), K-means clustering segmentation in CIE L*a*b* space (K-Lab), and mean shift clustering segmentation based on color feature (ExG-MS, ExGExR-MS, and CIVE-MS) from time consuming and accuracy. The results indicated that ExGExR and CIVE took shorter time than other algorithms, and were more suitable for real-time operation. By further evaluating segmentation accuracy, ExGExR, CIVE, and mean shift algorithms were acceptable to kill suckers. And ExGExR was the best algorithm for sucker segmentation in consideration of time consuming and accuracy, next came CIVE.
Keywords: grapevine suckers; image segmentation; color feature; K-means; mean shift
DOI: 10.3965/j.ijabe.20150804.1527

Citation: Xu S S, Li W B, Kang F, Zheng Y J, Lan Y B. Evaluation of grapevine sucker segmentation algorithms for precision targeted spray. Int J Agric & Biol Eng, 2015; 8(4): 77－85.

Keywords


grapevine suckers; image segmentation; color feature; K-means; mean shift

Full Text:

PDF

References


Takeda F, Drane V, Saunders M S. Inhibiting sprouting in muscadine grapes. Proc. Fla. State Hort. Soc. 1982; 95: 127–128.

Smith R J, Klonsky K M, De Moura R L. Sample costs to establish a vineyard and produce wine grapes. Doctoral dissertation, University of California Cooperative Extension, California, USA, 2010.

Ahmedullah M, Wolfe W H. Control of sucker growth on Vitis vinifera L. cultivar Sauvignon Blanc with naphthaleneacetic acid. Am. J. Enol. Vitic. 1982; 33(4): 198–200.

Reynolds A G. Control of vegetative growth in Vitis by paclobutrazol-implications for winegrape quality. Acta Horticul. 1989; 239: 235–242.

Swetnam T L, Falk D A. Application of metabolic scaling theory to reduce error in local maxima tree segmentation from aerial LiDAR. Forest Ecol Manag. 2014; 323: 158–167. doi: 10.1016/j.foreco.2014.03.016.

Clark M L, Roberts D A. Species-level differences in hyper-spectral metrics among tropical rainforest tree as determined by a tree-based classifier. Remote Sens., 2012; 4(12): 1820–1855. doi: 10.3390/rs4061820.

Rathore V S, Kumar M S, Verma A. Colour based image segmentation using L*a*b* colour space based on genetic algorithm. IJETAE, 2012; 2(6): 156–162.

Peña-Barragán J M, Ngugi M K, Plant R E, Six J. Object-based crop identification using multiple vegetation indices, textural features and crop phenology. Remote Sens. Environ., 2011; 115(6): 1301–1316. doi:10.1016/j.rse. 2011.01.009.

Søgaard H T, Olsen H J. Determination of crop rows by image analysis without segmentation. Comp. Elect. Agric. 2003; 38(2): 141–158. doi: 10.1016/SO168-1699(02)0014-0.

Kang F, Wang H, Pierce F J, Zhang Q, Wang S. Sucker detection of grapevines for targeted spray using optical sensors. Trans. ASABE. 2012; 55(5): 2007–2014.

George E M, Camargo N J. Verification of color vegetation indices for automated crop imaging applications. Comp. Elect. Agric. 2008; 63(2): 282–293. doi:10.1016/j.compag. 2008.03.009.

Haw C L, Ismail W I W, Kairunniza-Bejo S, Putih A,

Shamshiri R. Colour vision to determine paddy maturity. Int J Agric & Biol Eng, 2014; 7(5): 55–63.

Hlaing S H, Khaing A S. Weed and crop segmentation and classification using area thresholding. IJRET. 2014; 3: 375–382. doi: 10.15623/ijret.2014.0303069.

Kang F. Research on automated grapevine trunk targeted precision sprayer and location and recognition for sucker. Doctoral dissertation. China Agricultural University, Beijing, China, 2011.

Neto J C. A combined statistical-soft computing approach for classification and mapping weed species in minimum-tillage systems. Doctoral dissertation. University of Nebraska-Lincoln, NE, USA, 2004.

Kataoka T, Kaneko T, Okamoto H, Hata S. Crop growth estimation system using machine vision. In Proceedings of IEEE/ASME International Conference on Advanced Intelligent Mechatronics 2003, 2003; 2: b1079–b1083. doi:10.1109/ATM.2003.1225492.

Bai X D, Cao Z G, Wang Y, Yu Z H, Zhang X F, Li C N. Crop segmentation from images by morphology modeling in the CIE L*a*b* color space. Comp. Elect. Agric., 2013; 9: 1–34. doi:10.1016/j.compag.2013.08.002.

Li Z, Hong T S, Zeng X Y, Zheng J B. Citrus red mite image target identification based on K-means clustering. Trans. CSAE, 2012; 23: 47–154. (in Chinese with English abstract)

Li G L, Ma Z H, Huang C, Chi Y W, Wang H G. Segmentation of color images of grape diseases using K-means clustering algorithm. Trans. CSAE, 2010; 26(14): 32–37. (in Chinese with English abstract)

Zheng L Y, Zhang J T, Wang Q Y. Mean-shift-based color segmentation of images containing green vegetation. Comp. Elect. Agric., 2009; 65(1): 93–98. doi:10.1016/j.compag. 2008.08.002.

Zheng L Y, Shi D M, Zhang J T. Segmentation of green vegetation of crop canopy images based on mean shift and Fisher linear discriminate. Pattern Recogn. Lett. 2010; 31(9): 920–925. doi:10.1016/j.patrec.2010. 01.016.

Si Y S, Liu G, Gao R. Segmentation algorithm for green apples recognition based on K-means algorithm. Trans. CSAM, 2009; 40: 100–104. (in Chinese with English abstract)

Comaniciu D, Meer P. Mean shift: a robust approach toward feature space analysis. PAMI 2002; 24: 603–619. doi:10.1109/34.1000236.

Zhang D B. Research on plant’s three-dimensional information detection and visual servo controlling technology. Doctoral dissertation, China Agricultural University, Beijing, China, 2014.




Copyright (c)



2023-2026 Copyright IJABE Editing and Publishing Office