Manually plot boxes, rather than using `r.plot()`

.python-version

@@ -1 +1 @@
-3.10.5
+3.10.5

.vscode/launch.json

@@ -1,15 +1,15 @@
-{
-    // Use IntelliSense to learn about possible attributes.
-    // Hover to view descriptions of existing attributes.
-    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
-    "version": "0.2.0",
-    "configurations": [
-        {
-            "name": "Python: Module",
-            "type": "python",
-            "request": "launch",
-            "module": "src",
-            "justMyCode": true
-        }
-    ]
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python: Module",
+            "type": "python",
+            "request": "launch",
+            "module": "src",
+            "justMyCode": true
+        }
+    ]
 }

pyproject.toml

@@ -1,59 +1,59 @@
-[tool.poetry]
-name = "set-detect-notify"
-version = "0.1.0"
-description = "Detect all the things"
-authors = ["slashtechno <77907286+slashtechno@users.noreply.github.com>"]
-license = "MIT"
-readme = "README.md"
-packages = [{include = "set-detect-notify"}]
-
-[tool.poetry.dependencies]
-python = "^3.10"
-python-dotenv = "^1.0.0"
-httpx = "^0.25.0"
-opencv-python = "^4.8.1.78"
-ultralytics = "^8.0.190"
-hjson = "^3.1.0"
-numpy = "^1.23.2"
-# torch = [
-#   { version = "^2.0.0+cu118", source = "torch_cu118", markers = "extra=='cuda'" },
-#   { version = "^2.0.0+cpu", source = "torch_cpu", markers = "extra!='cuda'" },
-# ]
-# torchaudio = [
-#   { version = "^2.0.0+cu118", source = "torch_cu118", markers = "extra=='cuda'" },
-#   { version = "^2.0.0+cpu", source = "torch_cpu", markers = "extra!='cuda'" },
-# ]
-# torchvision = [
-#   { version = "^0.15+cu118", source = "torch_cu118", markers = "extra=='cuda'" },
-#   { version = "^0.15+cpu", source = "torch_cpu", markers = "extra!='cuda'" },
-# ]
-torch = "^2.1.0"
-
-
-[tool.poetry.group.dev.dependencies]
-black = "^23.9.1"
-ruff = "^0.0.291"
-ipykernel = "^6.25.2"
-
-
-# [[tool.poetry.source]]
-# name = "torch_cpu"
-# url = "https://download.pytorch.org/whl/cpu"
-# priority = "supplemental"
-# 
-# [[tool.poetry.source]]
-# name = "torch_cu118"
-# url = "https://download.pytorch.org/whl/cu118"
-# priority = "supplemental"
-# 
-# [tool.poetry.extras]
-# cuda = []
-# 
-# [[tool.poetry.source]]
-# name = "PyPI"
-# priority = "primary"
-
-[build-system]
-requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"
-
+[tool.poetry]
+name = "set-detect-notify"
+version = "0.1.0"
+description = "Detect all the things"
+authors = ["slashtechno <77907286+slashtechno@users.noreply.github.com>"]
+license = "MIT"
+readme = "README.md"
+packages = [{include = "set-detect-notify"}]
+
+[tool.poetry.dependencies]
+python = "^3.10"
+python-dotenv = "^1.0.0"
+httpx = "^0.25.0"
+opencv-python = "^4.8.1.78"
+ultralytics = "^8.0.190"
+hjson = "^3.1.0"
+numpy = "^1.23.2"
+# torch = [
+#   { version = "^2.0.0+cu118", source = "torch_cu118", markers = "extra=='cuda'" },
+#   { version = "^2.0.0+cpu", source = "torch_cpu", markers = "extra!='cuda'" },
+# ]
+# torchaudio = [
+#   { version = "^2.0.0+cu118", source = "torch_cu118", markers = "extra=='cuda'" },
+#   { version = "^2.0.0+cpu", source = "torch_cpu", markers = "extra!='cuda'" },
+# ]
+# torchvision = [
+#   { version = "^0.15+cu118", source = "torch_cu118", markers = "extra=='cuda'" },
+#   { version = "^0.15+cpu", source = "torch_cpu", markers = "extra!='cuda'" },
+# ]
+torch = "^2.1.0"
+
+
+[tool.poetry.group.dev.dependencies]
+black = "^23.9.1"
+ruff = "^0.0.291"
+ipykernel = "^6.25.2"
+
+
+# [[tool.poetry.source]]
+# name = "torch_cpu"
+# url = "https://download.pytorch.org/whl/cpu"
+# priority = "supplemental"
+# 
+# [[tool.poetry.source]]
+# name = "torch_cu118"
+# url = "https://download.pytorch.org/whl/cu118"
+# priority = "supplemental"
+# 
+# [tool.poetry.extras]
+# cuda = []
+# 
+# [[tool.poetry.source]]
+# name = "PyPI"
+# priority = "primary"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+

set-detect-notify/__main__.py

@@ -13,6 +13,7 @@ from ultralytics import YOLO
 import argparse
 
 from .utils import notify
+from .utils import utils
 
 DATETIME_FORMAT = "%Y-%m-%d %H:%M:%S"
 args = None
@@ -48,13 +49,13 @@ def main():
         type=float,
         help="The scale to run the detection at, default is 0.25",
     )
-    # argparser.add_argument(
-    # '--view-scale',
-    # # Set it to the env VIEW_SCALE if it isn't blank, otherwise set it to 0.75
-    # default=os.environ['VIEW_SCALE'] if 'VIEW_SCALE' in os.environ and os.environ['VIEW_SCALE'] != '' else 0.75,  # noqa: E501
-    # type=float,
-    # help="The scale to view the detection at, default is 0.75",
-    # )
+    argparser.add_argument(
+    '--view-scale',
+    # Set it to the env VIEW_SCALE if it isn't blank, otherwise set it to 0.75
+    default=os.environ['VIEW_SCALE'] if 'VIEW_SCALE' in os.environ and os.environ['VIEW_SCALE'] != '' else 0.75,  # noqa: E501
+    type=float,
+    help="The scale to view the detection at, default is 0.75",
+    )
 
     argparser.add_argument(
         "--confidence-threshold",
@@ -160,10 +161,12 @@ def main():
         # Only process every other frame of video to save time
         # Resize frame of video to a smaller size for faster recognition processing
         run_frame = cv2.resize(frame, (0, 0), fx=args.run_scale, fy=args.run_scale)
-        # view_frame = cv2.resize(frame, (0, 0), fx=`args.`view_scale, fy=args.view_scale)
+        # view_frame = cv2.resize(frame, (0, 0), fx=args.view_scale, fy=args.view_scale)
 
         results = model(run_frame, verbose=False)
-        for r in results:
+        for i, r in enumerate(results):
+            # list of dicts with each dict containing a label, x1, y1, x2, y2
+            plot_boxes = []
             # Setup dictionary of object names
             if not object_names:
                 for name in r.names.values():
@@ -174,6 +177,7 @@ def main():
                         "last_notification_time": None,
                     }
             for box in r.boxes:
+        
                 # Get the name of the object
                 class_id = r.names[box.cls[0].item()]
                 # Get the coordinates of the object
@@ -192,6 +196,18 @@ def main():
                     # If the confidence is less than 0.5, then SKIP!!!!
                     continue
 
+
+                # Add the object to the list of objects to plot
+                plot_boxes.append(
+                    {
+                        "label": class_id,
+                        "x1": cords[0],
+                        "y1": cords[1],
+                        "x2": cords[2],
+                        "y2": cords[3],
+                    }
+                )
+
                 # End goal: Send a notification when an object has been detected for 2 seconds in the past 15 seconds.
                 # However, don't send a notification if the last notification was less than 15 seconds ago
 
@@ -265,13 +281,17 @@ def main():
                         # Reset the detection duration
                         print("Just sent a notification - resetting detection duration")
                         object_names[class_id]["detection_duration"] = 0
-            im_array = r.plot()
-            # Scale back up the coordinates of the locations of detected objects.
-            # im_array = np.multiply(im_array, 1/args.run_scale)
-            # print(type(im_array))
-            # print(im_array)
-            # exit()
-            cv2.imshow("View", im_array)
+            frame_to_show = utils.plot_label(
+                boxes=plot_boxes,
+                full_frame=frame,
+                # full_frame=r.plot(),
+                run_scale=args.run_scale,
+                view_scale=args.view_scale,
+            )
+            
+            # Display the resulting frame
+            # cv2.imshow("", r)
+            cv2.imshow(f"Video{i}", frame_to_show)
 
         # Hit 'q' on the keyboard to quit!
         if cv2.waitKey(1) & 0xFF == ord("q"):

set-detect-notify/utils/notify.py

@@ -1,32 +1,32 @@
-import datetime
-import httpx
-
-
-def construct_ntfy_headers(
-    title: str = "Object/Person Detected",
-    tag="rotating_light",  # https://docs.ntfy.sh/publish/#tags-emojis
-    priority="default",  #  https://docs.ntfy.sh/publish/#message-priority
-) -> dict:
-    return {"Title": title, "Priority": priority, "Tags": tag}
-
-
-def send_notification(data: str, headers: dict, url: str):
-    if url is None or data is None:
-        raise ValueError("url and data cannot be None")
-    httpx.post(url, data=data.encode("utf-8"), headers=headers)
-
-
-def check_last_seen(last_seen: datetime.datetime, seconds: int = 15):
-    """
-    Check if a time is older than a given number of seconds
-    If it is, return True
-    If last_seen is empty/null, return True
-    """
-    if (
-        datetime.datetime.now() - last_seen > datetime.timedelta(seconds=seconds)
-        or last_seen == ""
-        or last_seen is None
-    ):
-        return True
-    else:
-        return False
+import datetime
+import httpx
+
+
+def construct_ntfy_headers(
+    title: str = "Object/Person Detected",
+    tag="rotating_light",  # https://docs.ntfy.sh/publish/#tags-emojis
+    priority="default",  #  https://docs.ntfy.sh/publish/#message-priority
+) -> dict:
+    return {"Title": title, "Priority": priority, "Tags": tag}
+
+
+def send_notification(data: str, headers: dict, url: str):
+    if url is None or data is None:
+        raise ValueError("url and data cannot be None")
+    httpx.post(url, data=data.encode("utf-8"), headers=headers)
+
+
+def check_last_seen(last_seen: datetime.datetime, seconds: int = 15):
+    """
+    Check if a time is older than a given number of seconds
+    If it is, return True
+    If last_seen is empty/null, return True
+    """
+    if (
+        datetime.datetime.now() - last_seen > datetime.timedelta(seconds=seconds)
+        or last_seen == ""
+        or last_seen is None
+    ):
+        return True
+    else:
+        return False

set-detect-notify/utils/utils.py

@@ -0,0 +1,46 @@
+import cv2
+import numpy as np
+def plot_label(
+        # list of dicts with each dict containing a label, x1, y1, x2, y2
+        boxes: list = None,
+        # opencv image
+        full_frame: np.ndarray = None,
+        # run_scale is the scale of the image that was used to run the model
+        # So the coordinates will be scaled up to the view frame size
+        run_scale: float = None, 
+        # view_scale is the scale of the image, in relation to the full frame
+        # So the coordinates will be scaled appropriately when coming from run_frame
+        view_scale: float = None,
+        font: int = cv2.FONT_HERSHEY_SIMPLEX,
+):
+    view_frame = cv2.resize(full_frame, (0, 0), fx=view_scale, fy=view_scale)
+    for thing in boxes:
+        cv2.rectangle(
+            # Image
+            view_frame,
+            # Start point
+            (int(thing["x1"] * (run_scale/view_scale)), int(thing["y1"] * (run_scale/view_scale))),
+            # End point
+            (int(thing["x2"] * (run_scale/view_scale)), int(thing["y2"] * (run_scale/view_scale))),
+            # Color
+            (0, 255, 0),
+            # Thickness
+            2,
+        )
+        cv2.putText(
+            # Image
+            view_frame,
+            # Text
+            thing["label"],
+            # Origin
+            (int(thing["x1"] * (run_scale/view_scale)), int(thing["y1"] * (run_scale/view_scale))),
+            # Font
+            font,
+            # Font Scale
+            1,
+            # Color
+            (0, 255, 0),
+            # Thickness
+            1
+        )
+    return view_frame