Mapping of Agricultural Crops from Single High-Resolution Multispectral Images—Data-Driven Smoothing vs. Parcel-Based Smoothing

Abstract

Abstract:Mapping agricultural crops is an important application of remote sensing. However, in many cases it is based either on hyperspectral imagery or on multitemporal coverage, both of which are difficult to scale up to large-scale deployment at high spatial resolution. In the present paper, we evaluate the possibility of crop classification based on single images from very high-resolution (VHR) satellite sensors. The main objective of this work is to expose performance difference between state-of-the-art parcel-based smoothing and purely data-driven conditional random field (CRF) smoothing, which is yet unknown. To fulfill this objective, we perform extensive tests with four different classification methods (Support Vector Machines, Random Forest, Gaussian Mixtures, and Maximum Likelihood) to compute the pixel-wise data term; and we also test two different definitions of the pairwise smoothness term. We have performed a detailed evaluation on different multispectral VHR images (Ikonos, QuickBird, Kompsat-2). The main finding of this study is that pairwise CRF smoothing comes close to the state-of-the-art parcel-based method that requires parcel boundaries (average difference ≈ 2.5%). Our results indicate that a single multispectral (R, G, B, NIR) image is enough to reach satisfactory classification accuracy for six crop classes (corn, pasture, rice, sugar beet, wheat, and tomato) in Mediterranean climate. Overall, it appears that crop mapping using only one-shot VHR imagery taken at the right time may be a viable alternative, especially since high-resolution OPEN ACCESSRemote Sens. 2015, 7 5612 multitemporal or hyperspectral coverage as well as parcel boundaries are in practice often not available.

Optimal Timing Assessment for Crop Separation Using Multispectral Unmanned Aerial Vehicle (UAV) Data and Textural Features

“…When considering all of the crops in the study area, the accuracy of crop separation is highest in the mid-season temporal window between 1362 and 2016 AGDD but accuracy reaches a maximum at 1556 AGDD. This is in line with other studies that report best accuracies for crop separation with data sets acquired in July [2,40,41]. At this time of the growing season, the winter crops are in a senescence stage and the summer crops in their most productive stage.…”

“…Crop type separation is a crucial requirement for the planning [1], short-term monitoring [2], management [3], high-throughput phenotyping [4][5][6], and climate change modeling [7] of agricultural areas. Many of these tasks need up-to-date information, in particular before the end of the growing season.…”

“…Land cover crop maps are often based on satellite data because these platforms provide data sets multiple times per month and are suitable for both single-date or multitemporal classification tasks [11,12]. Moreover, several studies have demonstrated the ability to carry out early stage crop mapping [1,2,13,14]. However, due to fixed orbits and thus fixed observation dates, clouds can limit the amount of usable data.…”

VPRS-Based Regional Decision Fusion of CNN and MRF Classifications for Very Fine Resolution Remotely Sensed Images

“…These technical advances have resulted in immense growth in the available VFSR remotely sensed imagery typically acquired at sub-metre spatial resolution [2], such as QuickBird, GeoEye-1, Pleiades-1, and WorldView-2, 3, and 4. The fine spatial detail presented in VFSR images offer huge opportunities for extracting a higher quality and larger quantity of information, which may underpin a wide array of geospatial applications, including urban land use change monitoring [3], precision agriculture [4], and tree crown delineation [5], to name but a few. One of the bases of these applications is image classification where information embedded at the pixel level is captured, processed and classified into different land cover classes [6].…”

Crop Type Mapping From a Sequence of Terrasar-X Images With Dynamic Conditional Random Fields

“…They used HMM to model temporal context among crop phenology stages but lack a proper spatial context framework. Mono-temporal crop classification adopting spatial context also exist (Ozdarici-Ok et al, 2015;Roscher et al, 2010). Efforts to use both spatial and temporal context to classify crops from optical images is done in (Hoberg and Müller, 2011).…”