Initial import: World-UAV prepro

Add dataloaders (v1/v2), analysis scripts, and documentation for working with UAV-GeoLoc (World-UAV).

Co-authored-by: Cursor <cursoragent@cursor.com>

analyze/analyze_crop_scheme.py

@@ -0,0 +1,117 @@
+"""
+Анализ схемы нарезки спутниковых снимков в датасете UAV-GeoLoc.
+
+Скрипт определяет crop_size, stride и overlap для каждой сцены,
+сопоставляя кропы с исходным merge.tif через попиксельное сравнение.
+
+Результат: stride = crop_size // 2 (50% overlap) для всех сцен.
+Naming: crop_X_Y.png — X по ширине (col), Y по высоте (row).
+Позиция в merge.tif: merge[Y*stride : Y*stride+crop_size, X*stride : X*stride+crop_size]
+"""
+
+import glob
+import os
+
+import numpy as np
+from PIL import Image
+
+Image.MAX_IMAGE_PIXELS = None  # некоторые merge.tif очень большие
+
+
+def analyze_scene(scene_db_dir: str) -> dict:
+    """Определяет параметры нарезки для одной сцены.
+
+    Args:
+        scene_db_dir: путь к папке DB сцены (содержит merge.tif и img/).
+
+    Returns:
+        dict с ключами: merge_size, crop_size, grid, stride, overlap.
+    """
+    merge_path = os.path.join(scene_db_dir, "merge.tif")
+    img_dir = os.path.join(scene_db_dir, "img")
+
+    merge = np.array(Image.open(merge_path))
+    mh, mw = merge.shape[:2]
+
+    # Размер кропа
+    c00 = np.array(Image.open(os.path.join(img_dir, "crop_0_0.png")))
+    ch, cw = c00.shape[:2]
+
+    # Размер сетки
+    crops = os.listdir(img_dir)
+    xs, ys = [], []
+    for name in crops:
+        parts = name.replace("crop_", "").replace(".png", "").split("_")
+        xs.append(int(parts[0]))
+        ys.append(int(parts[1]))
+    grid_x, grid_y = max(xs) + 1, max(ys) + 1
+
+    # Проверяем что crop_0_0 начинается с (0, 0)
+    assert np.array_equal(c00, merge[0:ch, 0:cw, :3]), "crop_0_0 не совпадает с merge[0:ch, 0:cw]"
+
+    # Ищем stride по X: сдвигаем crop_1_0 вдоль ширины merge
+    c10 = np.array(Image.open(os.path.join(img_dir, "crop_1_0.png")))
+    stride_x = None
+    for s in range(1, cw + 1):
+        if s + cw <= mw and np.array_equal(c10, merge[0:ch, s:s + cw, :3]):
+            stride_x = s
+            break
+    assert stride_x is not None, "Не удалось найти stride по X"
+
+    # Ищем stride по Y: сдвигаем crop_0_1 вдоль высоты merge
+    c01 = np.array(Image.open(os.path.join(img_dir, "crop_0_1.png")))
+    stride_y = None
+    for s in range(1, ch + 1):
+        if s + ch <= mh and np.array_equal(c01, merge[s:s + ch, 0:cw, :3]):
+            stride_y = s
+            break
+    assert stride_y is not None, "Не удалось найти stride по Y"
+
+    return {
+        "merge_size": (mw, mh),
+        "crop_size": (cw, ch),
+        "grid": (grid_x, grid_y),
+        "stride": (stride_x, stride_y),
+        "overlap": (cw - stride_x, ch - stride_y),
+    }
+
+
+def main():
+    base = os.path.dirname(os.path.abspath(__file__))
+
+    patterns = [
+        os.path.join(base, "Country", "*", "*", "*", "DB"),
+        os.path.join(base, "Terrain", "*", "*", "DB"),
+    ]
+
+    scene_dirs = []
+    for pat in patterns:
+        scene_dirs.extend(sorted(glob.glob(pat)))
+
+    print(f"{'Scene':<50} {'merge WxH':>14} {'crop':>8} {'grid':>8} {'stride':>8} {'overlap':>8}")
+    print("-" * 100)
+
+    for scene_db in scene_dirs:
+        if not os.path.isfile(os.path.join(scene_db, "merge.tif")):
+            continue
+
+        # Короткое имя сцены
+        rel = os.path.relpath(scene_db, base)
+        name = rel.replace("/DB", "")
+
+        try:
+            info = analyze_scene(scene_db)
+            mw, mh = info["merge_size"]
+            cw, ch = info["crop_size"]
+            gx, gy = info["grid"]
+            sx, sy = info["stride"]
+            ox, oy = info["overlap"]
+            print(
+                f"{name:<50} {mw:>6}x{mh:<6} {cw:>3}x{ch:<4} {gx:>3}x{gy:<4} {sx:>3}x{sy:<4} {ox:>3}x{oy:<4}"
+            )
+        except Exception as e:
+            print(f"{name:<50} ERROR: {e}")
+
+
+if __name__ == "__main__":
+    main()