A smart-vision algorithm for counting whiteflies and thrips on sticky traps using two-dimensional Fourier transform spectrum. (January 2017)

• Record Type: Journal Article
• Authors: Sun, Yurui; Cheng, Hong; Cheng, Qiang; Zhou, Haiyang; Li, Menghua; Fan, Youheng; Shan, Guilin; Damerow, Lutz; Schulze Lammers, Peter; Jones, Scott B.
• Is Part Of: Biosystems engineering. Volume 153(2017)
• Page Start: 82
• Page End: 88
• Publication Date: 2017-01
• Subjects: Pest counting -- Sticky trap -- Whitefly -- Thrips -- Two-dimensional Fourier transform; Bioengineering -- Periodicals; Agricultural engineering -- Periodicals; Biological systems -- Periodicals; Génie rural -- Périodiques; Systèmes biologiques -- Périodiques; 631
• DOI: 10.1016/j.biosystemseng.2016.11.001
• Languages: English
• ISSNs: 1537-5110

Abstract

Abstract : Although sticky traps are reliable indicators of pest population dynamics but pest counting by humans is time-consuming and menial labour. A novel smart vision algorithm based on two-dimensional Fourier transform (2DFT) spectrum is presented. Rather than directly counting the pests captured on the traps, the novel concept is to treat trapped pests as noise in a two-dimensional (2D) image with 2DFT serving as a specific noise collector. The research objectives included comparing human and 2DFT counting in two proof-of-principle tests: (i) simulated pests with various quantities and distributions arrayed on two series of templates using both ordered and random patterns; (ii) sweet potato whiteflies [ Bemisia tabaci (Gennadius), Hemiptera: Aleyrodidae] on yellow sticky traps (YSTs) and western flower thrips [ Frankliniella occidentalis (Pergande), Thysanoptera: Thripidae] on blue sticky traps (BSTs). Tests of simulated pests (2–512) on eight templates verified that the 2DFT-based index provides accurate estimates of pests captured on the traps (R 2 = 1), independent of pest distribution pattern. High correlations were obtained from count results of whiteflies on 34 YSTs (R 2 = 0.9994) and thrips on 33 BSTs (R 2 = 0.9989). Measurement errors were addressed. Highlights: Two-dimensional Fourier Transform spectrum used for pest counting. Proof-of-principle test using simulated pest to verify the proposed method. Experimental results from whiteflies and thrips captured on sticky traps.