Upper limit for context–based crop classification in robotic weeding applications. (June 2016)

• Record Type: Journal Article
• Authors: Midtiby, Henrik Skov; Åstrand, Björn; Jørgensen, Ole; Jørgensen, Rasmus Nyholm
• Is Part Of: Biosystems engineering. Volume 146(2016:Jun.)
• Page Start: 183
• Page End: 192
• Publication Date: 2016-06
• Subjects: Crop recognition -- Row structure -- Weeding robots; Bioengineering -- Periodicals; Agricultural engineering -- Periodicals; Biological systems -- Periodicals; Génie rural -- Périodiques; Systèmes biologiques -- Périodiques; 631
• DOI: 10.1016/j.biosystemseng.2016.01.012
• Languages: English
• ISSNs: 1537-5110

Abstract

Abstract : Knowledge of the precise position of crop plants is a prerequisite for effective mechanical weed control in robotic weeding application such as in crops like sugar beets which are sensitive to mechanical stress. Visual detection and recognition of crop plants based on their shapes has been described many times in the literature. In this paper the potential of using knowledge about the crop seed pattern is investigated based on simulated output from a perception system. The reliability of position–based crop plant detection is shown to depend on the weed density ( ρ, measured in weed plants per square metre) and the crop plant pattern position uncertainty (σx and σy, measured in metres along and perpendicular to the crop row, respectively). The recognition reliability can be described with the positive predictive value (PPV), which is limited by the seeding pattern uncertainty and the weed density according to the inequality: PPV ≤ (1 + 2πρσx σy ) −1 . This result matches computer simulations of two novel methods for position–based crop recognition as well as earlier reported field–based trials. Highlights: Derivation of classification limits for context based classifiers. Variables weed pressure and the uncertainty of crop plant position. Testing of two novel context based crop recognition methods described. Predicted upper limit for classifiers agreed well with results from real field data.