feat: initial HSAP platform

Huaxu Sentinel Active Safety Platform with embedded algorithm code,
Docker Compose setup, and vendored dataset scaffolds for clone-and-run.

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

algorithms/dms_yolo/code/examples/YOLOv8-OpenCV-ONNX-Python/README.md

@@ -0,0 +1,51 @@
+# Ultralytics YOLOv8 Object Detection with OpenCV and ONNX
+
+This example demonstrates how to implement [Ultralytics YOLOv8](https://docs.ultralytics.com/models/yolov8/) object detection using [OpenCV](https://opencv.org/) in [Python](https://www.python.org/), leveraging the [ONNX (Open Neural Network Exchange)](https://onnx.ai/) model format for efficient inference.
+
+## 🚀 Getting Started
+
+Follow these simple steps to get the example running on your local machine.
+
+1.  **Clone the Repository:**
+    If you haven't already, clone the Ultralytics repository to access the example code:
+
+    ```bash
+    git clone https://github.com/ultralytics/ultralytics.git
+    cd ultralytics/examples/YOLOv8-OpenCV-ONNX-Python/
+    ```
+
+2.  **Install Requirements:**
+    Install the necessary Python packages listed in the `requirements.txt` file. We recommend using a virtual environment.
+
+    ```bash
+    pip install -r requirements.txt
+    ```
+
+3.  **Run the Detection Script:**
+    Execute the main Python script, specifying the ONNX model path and the input image.
+    ```bash
+    python main.py --model yolov8n.onnx --img image.jpg
+    ```
+    The script will perform object detection on `image.jpg` using the `yolov8n.onnx` model and display the results.
+
+## 🛠️ Exporting Your Model
+
+If you want to use a different Ultralytics YOLOv8 model or one you've trained yourself, you need to export it to the ONNX format first.
+
+1.  **Install Ultralytics:**
+    If you don't have it installed, get the latest `ultralytics` package:
+
+    ```bash
+    pip install ultralytics
+    ```
+
+2.  **Export the Model:**
+    Use the `yolo export` command to convert your desired model (e.g., `yolov8n.pt`) to ONNX. Ensure you specify `opset=12` or higher for compatibility with OpenCV's DNN module. You can find more details in the Ultralytics [Export documentation](https://docs.ultralytics.com/modes/export/).
+    ```bash
+    yolo export model=yolov8n.pt imgsz=640 format=onnx opset=12
+    ```
+    This command will generate a `yolov8n.onnx` file (or the corresponding name for your model) in your working directory. You can then use this `.onnx` file with the `main.py` script.
+
+## 🤝 Contributing
+
+Contributions are welcome! If you find any issues or have suggestions for improvement, please feel free to open an issue or submit a pull request to the main [Ultralytics repository](https://github.com/ultralytics/ultralytics). Thank you for helping us make Ultralytics YOLO even better!

algorithms/dms_yolo/code/examples/YOLOv8-OpenCV-ONNX-Python/main.py

@@ -0,0 +1,134 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+from __future__ import annotations
+
+import argparse
+from typing import Any
+
+import cv2.dnn
+import numpy as np
+
+from ultralytics.utils import ASSETS, YAML
+from ultralytics.utils.checks import check_yaml
+
+CLASSES = YAML.load(check_yaml("coco8.yaml"))["names"]
+colors = np.random.uniform(0, 255, size=(len(CLASSES), 3))
+
+
+def draw_bounding_box(
+    img: np.ndarray, class_id: int, confidence: float, x: int, y: int, x_plus_w: int, y_plus_h: int
+) -> None:
+    """Draw bounding boxes on the input image based on the provided arguments.
+
+    Args:
+        img (np.ndarray): The input image to draw the bounding box on.
+        class_id (int): Class ID of the detected object.
+        confidence (float): Confidence score of the detected object.
+        x (int): X-coordinate of the top-left corner of the bounding box.
+        y (int): Y-coordinate of the top-left corner of the bounding box.
+        x_plus_w (int): X-coordinate of the bottom-right corner of the bounding box.
+        y_plus_h (int): Y-coordinate of the bottom-right corner of the bounding box.
+    """
+    label = f"{CLASSES[class_id]} ({confidence:.2f})"
+    color = colors[class_id]
+    cv2.rectangle(img, (x, y), (x_plus_w, y_plus_h), color, 2)
+    cv2.putText(img, label, (x - 10, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
+
+
+def main(onnx_model: str, input_image: str) -> list[dict[str, Any]]:
+    """Load ONNX model, perform inference, draw bounding boxes, and display the output image.
+
+    Args:
+        onnx_model (str): Path to the ONNX model.
+        input_image (str): Path to the input image.
+
+    Returns:
+        (list[dict[str, Any]]): List of dictionaries containing detection information such as class_id, class_name,
+            confidence, box coordinates, and scale factor.
+    """
+    # Load the ONNX model
+    model: cv2.dnn.Net = cv2.dnn.readNetFromONNX(onnx_model)
+
+    # Read the input image
+    original_image: np.ndarray = cv2.imread(input_image)
+    [height, width, _] = original_image.shape
+
+    # Prepare a square image for inference
+    length = max((height, width))
+    image = np.zeros((length, length, 3), np.uint8)
+    image[0:height, 0:width] = original_image
+
+    # Calculate scale factor
+    scale = length / 640
+
+    # Preprocess the image and prepare blob for model
+    blob = cv2.dnn.blobFromImage(image, scalefactor=1 / 255, size=(640, 640), swapRB=True)
+    model.setInput(blob)
+
+    # Perform inference
+    outputs = model.forward()
+
+    # Prepare output array
+    outputs = np.array([cv2.transpose(outputs[0])])
+    rows = outputs.shape[1]
+
+    boxes = []
+    scores = []
+    class_ids = []
+
+    # Iterate through output to collect bounding boxes, confidence scores, and class IDs
+    for i in range(rows):
+        classes_scores = outputs[0][i][4:]
+        (_minScore, maxScore, _minClassLoc, (_x, maxClassIndex)) = cv2.minMaxLoc(classes_scores)
+        if maxScore >= 0.25:
+            box = [
+                outputs[0][i][0] - (0.5 * outputs[0][i][2]),  # x center - width/2 = left x
+                outputs[0][i][1] - (0.5 * outputs[0][i][3]),  # y center - height/2 = top y
+                outputs[0][i][2],  # width
+                outputs[0][i][3],  # height
+            ]
+            boxes.append(box)
+            scores.append(maxScore)
+            class_ids.append(maxClassIndex)
+
+    # Apply NMS (Non-maximum suppression)
+    result_boxes = np.array(cv2.dnn.NMSBoxes(boxes, scores, 0.25, 0.45, 0.5)).flatten()
+
+    detections = []
+
+    # Iterate through NMS results to draw bounding boxes and labels
+    for index in result_boxes:
+        index = int(index)
+        box = boxes[index]
+        detection = {
+            "class_id": class_ids[index],
+            "class_name": CLASSES[class_ids[index]],
+            "confidence": scores[index],
+            "box": box,
+            "scale": scale,
+        }
+        detections.append(detection)
+        draw_bounding_box(
+            original_image,
+            class_ids[index],
+            scores[index],
+            round(box[0] * scale),
+            round(box[1] * scale),
+            round((box[0] + box[2]) * scale),
+            round((box[1] + box[3]) * scale),
+        )
+
+    # Display the image with bounding boxes
+    cv2.imshow("image", original_image)
+    cv2.waitKey(0)
+    cv2.destroyAllWindows()
+
+    return detections
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--model", default="yolov8n.onnx", help="Input your ONNX model.")
+    parser.add_argument("--img", default=str(ASSETS / "bus.jpg"), help="Path to input image.")
+    args = parser.parse_args()
+    main(args.model, args.img)

algorithms/dms_yolo/code/examples/YOLOv8-OpenCV-ONNX-Python/requirements.txt

@@ -0,0 +1,3 @@
+numpy
+opencv-python
+ultralytics