Q1. Object Detection System

Mejbah Ahammad -

Question:

Write a Python function using OpenCV and a pre-trained deep learning model to detect objects in an image. The function should take an image path as input, use a MobileNet SSD (Single Shot Detector) model pre-trained on the COCO dataset, and return the image with bounding boxes around detected objects, including labels and confidence scores.

Solution:

import cv2
import numpy as np

def detect_objects(image_path):
    # Load the pre-trained MobileNet SSD model and the corresponding class labels
    net = cv2.dnn.readNetFromCaffe('MobileNetSSD_deploy.prototxt.txt', 'MobileNetSSD_deploy.caffemodel')
    classes = ["background", "aeroplane", "bicycle", "bird", "boat",
               "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
               "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
               "sofa", "train", "tvmonitor"]

    # Load the image and create a blob from it
    image = cv2.imread(image_path)
    (h, w) = image.shape[:2]
    blob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 0.007843, (300, 300), 127.5)

    # Pass the blob through the network and obtain the detections and predictions
    net.setInput(blob)
    detections = net.forward()

    # Loop over the detections
    for i in np.arange(0, detections.shape[2]):
        confidence = detections[0, 0, i, 2]

        # Filter out weak detections by ensuring the confidence is greater than a minimum threshold
        if confidence > 0.2:
            # Extract the index of the class label from the detections
            idx = int(detections[0, 0, i, 1])
            label = classes[idx]

            # Compute the (x, y)-coordinates of the bounding box for the object
            box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
            (startX, startY, endX, endY) = box.astype("int")

            # Display the prediction
            label = "{}: {:.2f}%".format(label, confidence * 100)
            cv2.rectangle(image, (startX, startY), (endX, endY), (0, 255, 0), 2)
            y = startY - 15 if startY - 15 > 15 else startY + 15
            cv2.putText(image, label, (startX, y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)

    # Show the output image
    cv2.imshow("Output", image)
    cv2.waitKey(0)
    cv2.destroyAllWindows()

# Example usage:
detect_objects('path_to_image.jpg')

Explanation of the Solution:

  1. Load Pre-trained Model and Labels:
    • net = cv2.dnn.readNetFromCaffe(...): Loads the SSD model trained with the Caffe framework from disk.
    • classes: A list of class labels the model was trained to detect.
  2. Image Preprocessing:
    • image = cv2.imread(image_path): Loads an image from the specified path.
    • blob = cv2.dnn.blobFromImage(...): Converts the image into a blob by resizing and scaling operations. This blob is then used as the input to the network.
  3. Object Detection:
    • detections = net.forward(): Passes the blob through the network, which returns the detections. Each detection includes the class, score, and bounding box coordinates.
  4. Process Each Detection:
    • Loop through each detection and filter out weak detections based on a confidence threshold.
    • For each valid detection, calculate the bounding box coordinates and draw a rectangle and label on the image to display the result.
  5. Display Result:
    • cv2.imshow(...): Displays the image with bounding boxes and labels.
    • cv2.waitKey(0): Waits for a key press to close the window.

This solution leverages the MobileNet SSD model, which is efficient for real-time object detection due to its balance of speed and accuracy, making it suitable for applications that require running on limited computational resources like mobile devices.