Abstract
Machine vision systems are becoming increasingly common onboard agricultural vehicles (autonomous and non-autonomous) for different tasks. This paper provides guidelines for selecting machine-vision systems for optimum performance, considering the adverse conditions on these outdoor environments with high variability on the illumination, irregular terrain conditions or different plant growth states, among others. In this regard, three main topics have been conveniently addressed for the best selection: (a) spectral bands (visible and infrared); (b) imaging sensors and optical systems (including intrinsic parameters) and (c) geometric visual system arrangement (considering extrinsic parameters and stereovision systems). A general overview, with detailed description and technical support, is provided for each topic with illustrative examples focused on specific applications in agriculture, although they could be applied in different contexts other than agricultural. A case study is provided as a result of research in the RHEA (Robot Fleets for Highly Effective Agriculture and Forestry Management) project for effective weed control in maize fields (wide-rows crops), funded by the European Union, where the machine vision system onboard the autonomous vehicles was the most important part of the full perception system, where machine vision was the most relevant. Details and results about crop row detection, weed patches identification, autonomous vehicle guidance and obstacle detection are provided together with a review of methods and approaches on these topics.
Highlights
The incorporation of machine vision systems in agricultural environments is becoming more and more common, and is undergoing a period of continuous boom and growth, onboard agricultural vehicles, but not limited to this case
Crop rows detection and weeds identification are common tasks in precision agriculture where image processing techniques are used for site-specific treatments [4,5,6,7,8,9,10,11,12,13,14,15,16], guidance based on crop lines following [17,18,19,20], obstacle detection for security purposes [21,22,23,24,25] or mapping the environment in olive trees [26], among others
Containing information about the sensor sensitivity measured in terms of Manufacturers of camera-based sensors (CCD, CMOS) provide for each device a data-sheet absolute Quantum Efficiency (QE) or Relative Response (RR) [31]
Summary
The incorporation of machine vision systems in agricultural environments is becoming more and more common, and is undergoing a period of continuous boom and growth, onboard agricultural vehicles (autonomous and non-autonomous), but not limited to this case These systems can be used for different agricultural tasks, including crop (patches, rows) detection, weed identification for site-specific treatments, monitoring or canopy identification, among others, where precise guidance is required and the security and surveillance in the area of influence become crucial issues. Regarding the above considerations this paper addresses three main issues concerning the machine vision systems onboard agricultural vehicles, namely: (a) spectral-band selection; (b) imagers sensors and optical systems and (c) geometric system pose and arrangement. The main contribution of this paper involves such issues, which are to be considered before a machine vision system is selected to be installed onboard an agricultural vehicle for specific tasks in agriculture. An additional appendix provides the basic concepts for camera system geometry
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
