Running Object Detection With Python

import cv2
import numpy as np

# Using OpenCV's DNN module with a pretrained model
# Download: MobileNet SSD pretrained on COCO

def load_coco_detector():
    """Load a MobileNet SSD detector pretrained on COCO."""
    # Class names (COCO 80 classes)
    coco_classes = [
        "background", "person", "bicycle", "car", "motorbike",
        "aeroplane", "bus", "train", "truck", "boat",
        "traffic light", "fire hydrant", "stop sign", "parking meter", "bench",
        "bird", "cat", "dog", "horse", "sheep",
        "cow", "elephant", "bear", "zebra", "giraffe",
        # ... 80 total classes
    ]
    return coco_classes

def detect_objects_dnn(image_path, confidence_threshold=0.5):
    """
    Run object detection using OpenCV DNN.
    This uses a Caffe MobileNet SSD model.
    Download model files:
    - deploy.prototxt
    - mobilenet_iter_73000.caffemodel
    """
    coco_classes = load_coco_detector()

    image = cv2.imread(image_path)
    h, w = image.shape[:2]

    # Load model (requires downloaded model files)
    # net = cv2.dnn.readNetFromCaffe("deploy.prototxt",
    #                               "mobilenet_iter_73000.caffemodel")

    # Prepare image for network
    blob = cv2.dnn.blobFromImage(
        cv2.resize(image, (300, 300)),
        scalefactor=0.007843,
        size=(300, 300),
        mean=127.5
    )

    # net.setInput(blob)
    # detections = net.forward()

    # Process detections
    # for i in range(detections.shape[2]):
    #     confidence = detections[0, 0, i, 2]
    #     if confidence > confidence_threshold:
    #         class_id = int(detections[0, 0, i, 1])
    #         box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
    #         (x1, y1, x2, y2) = box.astype("int")
    #         label = f"{coco_classes[class_id]}: {confidence:.2f}"
    #         cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)
    #         cv2.putText(image, label, (x1, y1-10),
    #                    cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0,255,0), 2)

    print("Detection pipeline ready")
    print("Requires: deploy.prototxt + mobilenet_iter_73000.caffemodel")
    return image

detect_objects_dnn("photo.jpg")