Hello Object Detection

This tutorial is also available as a Jupyter notebook that can be cloned directly from GitHub. See the installation guide for instructions to run this tutorial locally on Windows, Linux or macOS. To run without installing anything, click the launch binder button.

A very basic introduction to using object detection models with OpenVINO.

We use the horizontal-text-detection-0001 model from the Open Model Zoo. It detects horizontal text in images and returns a blob of data in the shape of [100, 5]. Each detected text box is stored in the format [x_min, y_min, x_max, y_max, conf], where (x_min, y_min) are the coordinates of the top left bounding box corner, (x_max, y_max) are the coordinates of the bottom right bounding box corner and conf is the confidence for the predicted class.

Imports

import cv2
import matplotlib.pyplot as plt
import numpy as np
from openvino.inference_engine import IECore

Load the Model

ie = IECore()

net = ie.read_network(
    model="model/horizontal-text-detection-0001.xml",
    weights="model/horizontal-text-detection-0001.bin",
)
exec_net = ie.load_network(net, "CPU")

output_layer_ir = next(iter(exec_net.outputs))
input_layer_ir = next(iter(exec_net.input_info))

Load an Image

# Text detection models expects image in BGR format
image = cv2.imread("data/intel_rnb.jpg")

# N,C,H,W = batch size, number of channels, height, width
N, C, H, W = net.input_info[input_layer_ir].tensor_desc.dims

# Resize image to meet network expected input sizes
resized_image = cv2.resize(image, (W, H))

# Reshape to network input shape
input_image = np.expand_dims(resized_image.transpose(2, 0, 1), 0)

plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB));

Do Inference

result = exec_net.infer(inputs={input_layer_ir: input_image})

# Extract list of boxes from results
boxes = result["boxes"]

# Remove zero only boxes
boxes = boxes[~np.all(boxes == 0, axis=1)]

Visualize Results

# For each detection, the description has the format: [x_min, y_min, x_max, y_max, conf]
# Image passed here is in BGR format with changed width and height. To display it in colors expected by matplotlib we use cvtColor funtion
def convert_result_to_image(bgr_image, resized_image, boxes, threshold=0.3, conf_labels=True):
    # Define colors for boxes and descriptions
    colors = {"red": (255, 0, 0), "green": (0, 255, 0)}

    # Fetch image shapes to calculate ratio
    (real_y, real_x), (resized_y, resized_x) = bgr_image.shape[:2], resized_image.shape[:2]
    ratio_x, ratio_y = real_x / resized_x, real_y / resized_y

    # Convert base image from bgr to rgb format
    rgb_image = cv2.cvtColor(bgr_image, cv2.COLOR_BGR2RGB)

    # Iterate through non-zero boxes
    for box in boxes:
        # Pick confidence factor from last place in array
        conf = box[-1]
        if conf > threshold:
            # Convert float to int and multiply corner position of each box by x and y ratio
            # In case that bounding box is found at the top of the image,
            # we position upper box bar little bit lower to make it visible on image
            (x_min, y_min, x_max, y_max) = [
                int(max(corner_position * ratio_y, 10)) if idx % 2
                else int(corner_position * ratio_x)
                for idx, corner_position in enumerate(box[:-1])
            ]

            # Draw box based on position, parameters in rectangle function are: image, start_point, end_point, color, thickness
            rgb_image = cv2.rectangle(rgb_image, (x_min, y_min), (x_max, y_max), colors["green"], 3)

            # Add text to image based on position and confidence
            # Parameters in text function are: image, text, bottomleft_corner_textfield, font, font_scale, color, thickness, line_type
            if conf_labels:
                rgb_image = cv2.putText(
                    rgb_image,
                    f"{conf:.2f}",
                    (x_min, y_min - 10),
                    cv2.FONT_HERSHEY_SIMPLEX,
                    0.8,
                    colors["red"],
                    1,
                    cv2.LINE_AA,
                )

    return rgb_image

plt.figure(figsize=(10, 6))
plt.axis("off")
plt.imshow(convert_result_to_image(image, resized_image, boxes, conf_labels=False));

Prev Next