Abstract
The motivation of this research was to explore the feasibility of detecting and locating fruits from different kinds of crops in natural scenarios. To this end, a unique, modular and easily adaptable multisensory system and a set of associated pre-processing algorithms are proposed. The offered multisensory rig combines a high resolution colour camera and a multispectral system for the detection of fruits, as well as for the discrimination of the different elements of the plants, and a Time-Of-Flight (TOF) camera that provides fast acquisition of distances enabling the localisation of the targets in the coordinate space. A controlled lighting system completes the set-up, increasing its flexibility for being used in different working conditions. The pre-processing algorithms designed for the proposed multisensory system include a pixel-based classification algorithm that labels areas of interest that belong to fruits and a registration algorithm that combines the results of the aforementioned classification algorithm with the data provided by the TOF camera for the 3D reconstruction of the desired regions. Several experimental tests have been carried out in outdoors conditions in order to validate the capabilities of the proposed system.
Highlights
Service robots are becoming a key part of many sectors of the society, including precision agriculture, where they are called to play an important role in improving competitiveness and sustainable production [1]
This paper presents the research carried out in order to assess the feasibility of detecting, discriminating and locating fruits and other plant elements from different kinds of crops in natural environments by utilising a unique modular and adaptable multisensory system and a set of associated pre-processing algorithms
This transformation only affects to the x and y coordinates, since z coordinate is always referenced to the TOF camera
Summary
Service robots are becoming a key part of many sectors of the society, including precision agriculture, where they are called to play an important role in improving competitiveness and sustainable production [1]. Precision agriculture oriented to the automatic harvesting of fruits requires the investigation of non-destructive sensors capable of collecting precise and unambiguous information for an efficient detection and localization of fruits. This task of detection and localisation in natural scenes is quite challenging, since most fruits are partially occluded by leaves, branches or overlapped with other fruits [2]. Colours of fruits cannot be rigidly defined because the high variability exhibited among the different cultivars within a same species and the different levels of ripeness. Fruits can be found in quite random positions and orientations in trees of various sizes, volumes and limb structures
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
