pkextractimg(1)

💖 pkextractimg 💖

okay bestie, welcome to pkextractimg — section 1 of the manual, the "general commands" girlies. this is the tool that pulls pixel values out of your raster using another raster as the map, and honestly? she ate. 🎀

---

✨ NAME ✨

pkextractimg — extract pixel values from a raster image using a raster sample 🦋

---

🌸 SYNOPSIS 🌸

pkextractimg -i input [-s sample] -o output [options]

like, that's it. that's the whole vibe. 👑

---

💅 DESCRIPTION 💅

so here's the tea, bestie: pkextractimg pulls pixel values out of an input raster dataset, based on the locations you hand her via a sample file. she needs you to give her those locations, okay? she's not a mind reader. 🙈

the sample should be a raster dataset with categorical (integer) values. the classic use case — the one everyone's obsessed with — is a land cover map that overlaps your input raster dataset. then the utility goes and extracts pixels from the input raster for the respective land cover classes. iconic behavior, no cap. ✨

want a random subset of the sample raster dataset instead of the whole thing? set the threshold option -t with a percentage value. and the way that you can even give a threshold value for each class (e.g. -t 80 -t 60)? yes ma'am, per-class thresholds, we love to see it. 💅 use value 100 to select all pixels for the selected class(es). periodt.

as output, a new copy of the vector file is created, with an extra attribute for the extracted pixel value. and for each raster band in the input image, a separate attribute is created. so, for instance — if the raster dataset contains three bands, then three attributes are created (b0, b1 and b2). math is math, bestie. 🧚

---

🎀 OPTIONS 🎀

• -i filename, --input filename — the raster input dataset containing band information. your main character. 💖
• -s sample, --sample sample — raster dataset with categorical values, used to sample the input raster dataset. the output will contain features with input band information included. 🦋
• -ln layer, --ln layer — layer name(s) in the sample. leave it empty to select all of them, girl, go wild. 🌸
• -rand number, --random number — create a simple random sample of points. just provide the number of points to generate. 🎲
• -grid size, --grid size — create a systematic grid of points. provide the cell grid size, in projected units (e.g. m). so organized, so systematic. 👑
• -o filename, --output filename — the output sample dataset. this is where the magic lands. ✨
• -c class, --class class — class(es) to extract from the input sample image. leave empty to extract all valid data pixels from the sample dataset. and bestie, listen: make sure to set classes if rule is set to mode, proportion or count. that part is not optional. 😭
• -t threshold, --threshold threshold — probability threshold for selecting samples (randomly). provide the probability in percentage (>0) or absolute (<0). use a single threshold per vector sample layer. if you're using raster land cover maps as a sample dataset, you can provide a threshold value for each class (e.g. -t 80 -t 60). use value 100 to select all pixels for the selected class(es). 💯
• -f format, --f format — the output sample dataset format. 🎀
• -ft fieldType, --ftype fieldType — field type. and it's giving... only Real or Integer, those are your two options. 💅
• -lt labelType, --ltype labelType — label type: In16 or String. pick your fighter. 🦋
• -b band, --band band — band index(es) to extract. leave empty to use all bands. all of them. every single one. 🌈
• -sband band, --startband band — start band sequence number. ⭐
• -eband band, --endband band — end band sequence number. 🏁
• -bndnodata band, --bndnodata band — band(s) in the input image to check if a pixel is valid (used for srcnodata). the vibe check, basically. ✅
• -srcnodata value, --srcnodata value — invalid value(s) for the input image. the ones we don't claim. 💀
• -bn attribute, --bname attribute — for single band input data, this extra attribute name will correspond to the raster values. for multi-band input data, multiple attributes with this prefix will be added (e.g. b0, b1, b2, etc.). so many babies. 🍼
• -cn attribute, --cname attribute — name of the class label in the output vector dataset. 🏷️
• -down value, --down value — down sampling factor. 🔍
• -v level, --verbose level — verbose mode if > 0. she will simply not stop talking and honestly? we support her. 🗣️

---

🌟 quick reminder, bestie: that's every flag, every default, every value. don't skip any of them or the pixels will simply not be extracted and we'll all be sad. 🫶

---

and that's the whole page, my love 💜 this was pkextractimg from the pkextractimg(1) manual, sourced and versioned as 01 January 2025, so go forth, extract those pixels, and slay the day away. mwah. 💖✨🎀🦋🌸💅👑🌈⭐