File size: 4,532 Bytes
f6228f9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 |
# Ultralytics YOLO 🚀, AGPL-3.0 license
import argparse
import cv2.dnn
import numpy as np
from ultralytics.utils import ASSETS, yaml_load
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, class_id, confidence, x, y, x_plus_w, y_plus_h):
"""
Draws bounding boxes on the input image based on the provided arguments.
Args:
img (numpy.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, input_image):
"""
Main function to 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: List of dictionaries containing detection information such as class_id, class_name, confidence, etc.
"""
# 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]),
outputs[0][i][1] - (0.5 * outputs[0][i][3]),
outputs[0][i][2],
outputs[0][i][3],
]
boxes.append(box)
scores.append(maxScore)
class_ids.append(maxClassIndex)
# Apply NMS (Non-maximum suppression)
result_boxes = cv2.dnn.NMSBoxes(boxes, scores, 0.25, 0.45, 0.5)
detections = []
# Iterate through NMS results to draw bounding boxes and labels
for i in range(len(result_boxes)):
index = result_boxes[i]
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)
|