Stay organized with collectionsSave and categorize content based on your preferences.
Convert an image to a feature collection by reducing homogeneous regions. Given an image containing a band of labeled segments and zero or more additional bands, runs a reducer over the pixels in each segment producing a feature per segment.
Either the reducer must have one fewer inputs than the image has bands, or it must have a single input and will be repeated for each band.
The input image. The first band is expected to be an integer type; adjacent pixels will be in the same segment if they have the same value in this band.
reducer
Reducer, default: null
The reducer to apply. Its inputs will be taken from the image's bands after dropping the first band. Defaults to Reducer.countEvery().
geometry
Geometry, default: null
The region over which to reduce data. Defaults to the footprint of the image's first band.
scale
Float, default: null
A nominal scale in meters of the projection to work in.
geometryType
String, default: "polygon"
How to choose the geometry of each generated feature; one of 'polygon' (a polygon enclosing the pixels in the segment), 'bb' (a rectangle bounding the pixels), or 'centroid' (the centroid of the pixels).
eightConnected
Boolean, default: true
If true, diagonally-connected pixels are considered adjacent; otherwise only pixels that share an edge are.
labelProperty
String, default: "label"
If non-null, the value of the first band will be saved as the specified property of each feature.
crs
Projection, default: null
The projection to work in. If unspecified, the projection of the image's first band is used. If specified in addition to scale, rescaled to the specified scale.
crsTransform
List, default: null
The list of CRS transform values. This is a row-major ordering of the 3x2 transform matrix. This option is mutually exclusive with 'scale', and replaces any transform already set on the projection.
bestEffort
Boolean, default: false
If the polygon would contain too many pixels at the given scale, compute and use a larger scale which would allow the operation to succeed.
maxPixels
Long, default: 10000000
The maximum number of pixels to reduce.
tileScale
Float, default: 1
A scaling factor used to reduce aggregation tile size; using a larger tileScale (e.g., 2 or 4) may enable computations that run out of memory with the default.
geometryInNativeProjection
Boolean, default: false
Create geometries in the pixel projection, rather than EPSG:4326.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2024-07-13 UTC."],[[["\u003cp\u003eThis function transforms raster images into vector features by grouping similar pixel regions.\u003c/p\u003e\n"],["\u003cp\u003eEach generated feature represents a segment in the image and includes calculated statistics or properties.\u003c/p\u003e\n"],["\u003cp\u003eUsers can customize the analysis by specifying the reducer function, geometry type, and scale.\u003c/p\u003e\n"],["\u003cp\u003eAdvanced options allow control over connectivity, labeling, projection, and memory management for complex processing.\u003c/p\u003e\n"]]],["The `Image.reduceToVectors` function converts an image into a feature collection by grouping homogeneous pixel regions. It uses a reducer to process each region, generating a feature per segment. The function's key actions include applying the reducer over pixel segments, determining feature geometry (polygon, bounding box, or centroid), and handling pixel connectivity. The first image band defines the segments, and the remaining bands provide reducer input. Users can configure scale, projection, pixel adjacency, and manage memory with `maxPixels` and `tileScale`.\n"],null,["# ee.Image.reduceToVectors\n\nConvert an image to a feature collection by reducing homogeneous regions. Given an image containing a band of labeled segments and zero or more additional bands, runs a reducer over the pixels in each segment producing a feature per segment.\n\n\u003cbr /\u003e\n\nEither the reducer must have one fewer inputs than the image has bands, or it must have a single input and will be repeated for each band.\n\n| Usage | Returns |\n|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------|\n| Image.reduceToVectors`(`*reducer* `, `*geometry* `, `*scale* `, `*geometryType* `, `*eightConnected* `, `*labelProperty* `, `*crs* `, `*crsTransform* `, `*bestEffort* `, `*maxPixels* `, `*tileScale* `, `*geometryInNativeProjection*`)` | FeatureCollection |\n\n| Argument | Type | Details |\n|------------------------------|----------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| this: `image` | Image | The input image. The first band is expected to be an integer type; adjacent pixels will be in the same segment if they have the same value in this band. |\n| `reducer` | Reducer, default: null | The reducer to apply. Its inputs will be taken from the image's bands after dropping the first band. Defaults to Reducer.countEvery(). |\n| `geometry` | Geometry, default: null | The region over which to reduce data. Defaults to the footprint of the image's first band. |\n| `scale` | Float, default: null | A nominal scale in meters of the projection to work in. |\n| `geometryType` | String, default: \"polygon\" | How to choose the geometry of each generated feature; one of 'polygon' (a polygon enclosing the pixels in the segment), 'bb' (a rectangle bounding the pixels), or 'centroid' (the centroid of the pixels). |\n| `eightConnected` | Boolean, default: true | If true, diagonally-connected pixels are considered adjacent; otherwise only pixels that share an edge are. |\n| `labelProperty` | String, default: \"label\" | If non-null, the value of the first band will be saved as the specified property of each feature. |\n| `crs` | Projection, default: null | The projection to work in. If unspecified, the projection of the image's first band is used. If specified in addition to scale, rescaled to the specified scale. |\n| `crsTransform` | List, default: null | The list of CRS transform values. This is a row-major ordering of the 3x2 transform matrix. This option is mutually exclusive with 'scale', and replaces any transform already set on the projection. |\n| `bestEffort` | Boolean, default: false | If the polygon would contain too many pixels at the given scale, compute and use a larger scale which would allow the operation to succeed. |\n| `maxPixels` | Long, default: 10000000 | The maximum number of pixels to reduce. |\n| `tileScale` | Float, default: 1 | A scaling factor used to reduce aggregation tile size; using a larger tileScale (e.g., 2 or 4) may enable computations that run out of memory with the default. |\n| `geometryInNativeProjection` | Boolean, default: false | Create geometries in the pixel projection, rather than EPSG:4326. |"]]
