Classifying agricultural land uses with time series of satellite images

North, Heather; Pairman, D.; Belliss, S.E.; Cuff, J.

doi:10.1109/igarss.2012.6352319

Cited by 8 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some spatial information is available but requires licensing, which is against the principles of publicly publishing any reporting data. Another method for determining cultivated land from publicly available data sources could be from sequential satellite imagery (North et al 2015). However, the effort required setting up new systems to automatically identify the cultivated land and report at appropriate time and space scales is significant and currently well beyond that judged reasonable.…”

Section: Indicators Of Pressures States and Impacts In Ecosystemsmentioning

confidence: 99%

An ecosystem services approach to choosing environmental indicators for state of environment reports

Dymond¹,

Ausseil²

2022

nzsr

View full text Add to dashboard Cite

show abstract

Section: Indicators Of Pressures States and Impacts In Ecosystemsmentioning

confidence: 99%

An ecosystem services approach to choosing environmental indicators for state of environment reports

Dymond¹,

Ausseil²

2022

nzsr

View full text Add to dashboard Cite

show abstract

“…The land-use classifications of the area in Fig. 6 (dated 2010−12) included images from Landsat-5 and -7, and SPOT-4 and -5 [8], and we now also use imagery from Sentinel-2A and -2B for current classifications. Fig.…”

Section: A Study Site and Land-use Mapping Applicationmentioning

confidence: 99%

“…described in Lilburne and North [5], North et al [6], [7], and in a technical report [8]. Such classification is increasingly carried out on a per-field rather than a per-pixel basis [2], [4], [8]. Agricultural statistics are more useful in this form for policy and monitoring, and classification techniques are more powerful and accurate when whole fields are classified as a unit [9], since, as an object, a field can be robustly characterized by its mean reflectance, and higher level features such as size, shape, and texture can also be considered.…”

mentioning

confidence: 96%

See 1 more Smart Citation

Boundary Delineation of Agricultural Fields in Multitemporal Satellite Imagery

North

Pairman

Belliss

2019

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Agricultural land-use statistics are more informative per-field than per-pixel. Land-use classification requires up-to-date field boundary maps potentially covering large areas containing thousands of farms. This kind of map is usually difficult to obtain. We have developed a new, automated method for deriving closed polygons around fields from time-series satellite imagery. We have been using this method operationally in New Zealand to map whole districts using imagery from several satellite sensors, with little need to vary parameters. Our method looks for boundarieseither step edges or linear features-surrounding regions of low variability throughout the time series. Local standard deviations from all image dates are combined, and the result is convolved with a series of extended directional edge filters. We propose that edge linearity over a long distance is a more important criterion than spectral difference for separating fields, so edge responses are thresholded primarily by length rather than strength. The resulting raster edge map (combined from all directions) is converted to vector (GIS) format and the final polygon topology is built. The method successfully segments parcels containing different crops and pasture, as well as those separated by boundaries such as roads and hedgerows. Here we describe the technique and demonstrate it for an agricultural study site (4000 km 2) using SPOT satellite imagery. We show that our result compares favorably with that from existing segmentation methods in terms of both quantitative quality metrics and suitability for land-use classification.

show abstract

“…This preserves the brightness and produces more natural looking image. PDE based enhanced image and the histogram equalized image was shown below in tal role in segmentation [14]. Color is an immediately perceivable visual feature [5].…”

Section: Pre-processingmentioning

confidence: 99%