Precision farming or agriculture (PA) is a concept where agricultural practices are modulated according to intra-field crop variability. Multispectral sensors have standing use in remote sensing, onboard aircraft and satellites for mapping biomass. With increased miniaturization of sensors, Unmanned Aerial Systems (UAS) become more widely used for multispectral imaging. UAS offer several advantages for PA, such as a relative insensitivity to weather conditions, especially to cloud cover. Most UAS images are acquired in cloudless conditions or with a complete cloud cover to reduce the impact of changing luminosity. This work quantifies the ability to correct luminosity variations on images from UAS flights under varying weather conditions. Measurements were performed with the Parrot Sequoia multispectral camera paired with its Sunshine sensor. Control ground measurements were repeated over two hours on a series of five targets of increasing gray levels. These measurements correlate with corresponding reference spectra from a Spectral Evolution SR-3500 field spectroradiometer. In a second experiment, the camera recorded images every thirty seconds in time-lapse mode, for over an hour, above a reference reflectance target, in order to analyze the evolution of the reflectance over time as a function of the variations of illumination. Finally two different types of UAS carried out several series of flights: a fixed-wing senseFly eBee and an Innovadrone hexacopter rotary wing. This paper presents data analysis with and without the Sunshine sensor correction to quantify the improvement in the quality of reflectance measurements and biomass estimates.
We describe here a knowledge-based system, NEXSYS (Nextwork EXtraction SYStem) which was designed for the recognition of communication networks in SPOT satellite images. NEXSYS is a frame-based system and uses a co-operative and distributed structure based on a blackboard architecture. Communication networks in SPOT images are composed of thin linear segments. Segments are extracted using mathematical morphology and a Hough transform. An intermediate image representation composed of geometric primitives is obtained. Then an expert module is able to process the segments at the symbolic level trying to recognize networks.
The purpose of this paper is to describe a knowledge-based system for detection and interpretation of thin linear networks in remote sensing images. The proposed system : NEXSYS (Network Extraction System) is based on a mixed object-oriented / rule-based approach. It is built on a frame-based representation and contains three levels of processing:
a) A low level for segmentation, using mathematical morphology.
b) An intermediate level for line tracking guided by a Hough transform.
c) A high level for interpretation.
A prototype implementation has been written in LISP, C, using the Knowledge Engineering Environment (KEE), on a Sun Sparc IPC 4/40 station.