File size: 8,640 Bytes
8f87556 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 |
import os
import cv2
import numpy as np
import matplotlib.pyplot as plt
from shapely.geometry import Polygon, box as shapely_box
import streamlit as st
from PIL import Image
# Utility functions
def extract_class_0_coordinates(filename):
class_0_coordinates = []
with open(filename, 'r') as file:
for line in file:
parts = line.strip().split()
if len(parts) == 0:
continue
if parts[0] == '0':
coordinates = [float(x) for x in parts[1:]]
class_0_coordinates.extend(coordinates)
return class_0_coordinates
def parse_yolo_box(box_string):
values = list(map(float, box_string.split()))
if len(values) < 5:
raise ValueError(f"Expected at least 5 values, got {len(values)}")
return values[0], values[1], values[2], values[3], values[4]
def read_yolo_boxes(file_path):
boxes = []
with open(file_path, 'r') as f:
for line in f:
parts = line.strip().split()
class_name = COCO_CLASSES[int(parts[0])]
x, y, w, h = map(float, parts[1:5])
boxes.append((class_name, x, y, w, h))
return boxes
def yolo_to_pixel_coord(x, y, img_width, img_height):
return int(x * img_width), int(y * img_height)
def yolo_to_pixel_coords(x_center, y_center, width, height, img_width, img_height):
x1 = int((x_center - width / 2) * img_width)
y1 = int((y_center - height / 2) * img_height)
x2 = int((x_center + width / 2) * img_width)
y2 = int((y_center + height / 2) * img_height)
return x1, y1, x2, y2
def box_segment_relationship(yolo_box, segment, img_width, img_height, threshold):
class_id, x_center, y_center, width, height = yolo_box
x1, y1, x2, y2 = yolo_to_pixel_coords(x_center, y_center, width, height, img_width, img_height)
pixel_segment = convert_segment_to_pixel(segment, img_width, img_height)
segment_polygon = Polygon(zip(pixel_segment[::2], pixel_segment[1::2]))
box_polygon = shapely_box(x1, y1, x2, y2)
if box_polygon.intersects(segment_polygon):
return "intersecting"
elif box_polygon.distance(segment_polygon) <= threshold:
return "obstructed"
else:
return "not touching"
def convert_segment_to_pixel(segment, img_width, img_height):
pixel_segment = []
for i in range(0, len(segment), 2):
x, y = yolo_to_pixel_coord(segment[i], segment[i+1], img_width, img_height)
pixel_segment.extend([x, y])
return pixel_segment
def plot_boxes_and_segment(image, yolo_boxes, segment, img_width, img_height, threshold):
fig, ax = plt.subplots(figsize=(12, 8))
ax.imshow(image)
pixel_segment = convert_segment_to_pixel(segment, img_width, img_height)
ax.plot(pixel_segment[::2] + [pixel_segment[0]], pixel_segment[1::2] + [pixel_segment[1]], 'g-', linewidth=2, label='Rail Zone')
colors = {'intersecting': 'r', 'obstructed': 'y', 'not touching': 'b'}
labels = {'intersecting': 'Intersecting Box', 'obstructed': 'Obstructed Box', 'not touching': 'Non-interacting Box'}
for yolo_box in yolo_boxes:
class_id, x_center, y_center, width, height = yolo_box
x1, y1, x2, y2 = yolo_to_pixel_coords(x_center, y_center, width, height, img_width, img_height)
relationship = box_segment_relationship(yolo_box, segment, img_width, img_height, threshold)
color = colors[relationship]
label = labels[relationship]
ax.add_patch(plt.Rectangle((x1, y1), x2-x1, y2-y1, fill=False, edgecolor=color, linewidth=2, label=label))
ax.legend()
ax.axis('off')
plt.tight_layout()
return fig
# COCO classes
COCO_CLASSES = [
'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
'hair drier', 'toothbrush'
]
# Detection functions
def detect_rail(image):
# Open the image using PIL
pil_image = Image.open(image)
# Convert PIL image to numpy array
image = np.array(pil_image)
# Check if the image is RGB (3 channels)
if len(image.shape) == 3 and image.shape[2] == 3:
# Convert RGB to BGR (OpenCV format)
image_bgr = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
else:
# If not RGB, just use the image as is (assuming it's already in a format OpenCV can handle)
image_bgr = image
temp_image_path = "temp_image_rail.jpg"
cv2.imwrite(temp_image_path, image_bgr)
os.system(f"python segment/predict.py --source {temp_image_path} --img 640 --device cpu --weights models/segment/best-2.pt --name yolov9_c_640_detect --exist-ok --save-txt")
label_path = 'runs/predict-seg/yolov9_c_640_detect/labels/temp_image_rail.txt'
segment = extract_class_0_coordinates(label_path)
fig, ax = plt.subplots(figsize=(12, 8))
ax.imshow(image) # Use the original image for display
img_height, img_width = image.shape[:2]
pixel_segment = convert_segment_to_pixel(segment, img_width, img_height)
ax.plot(pixel_segment[::2] + [pixel_segment[0]], pixel_segment[1::2] + [pixel_segment[1]], 'g-', linewidth=2, label='Rail Zone')
ax.legend()
ax.axis('off')
plt.tight_layout()
os.remove(temp_image_path)
os.remove(label_path)
return fig, segment
def detect_objects(image, rail_segment):
# Open the image using PIL
pil_image = Image.open(image)
# Convert PIL image to numpy array
image = np.array(pil_image)
# Check if the image is RGB (3 channels)
if len(image.shape) == 3 and image.shape[2] == 3:
# Convert RGB to BGR (OpenCV format)
image_bgr = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
else:
# If not RGB, just use the image as is (assuming it's already in a format OpenCV can handle)
image_bgr = image
img_height, img_width = image.shape[:2]
temp_image_path = "temp_image_objects.jpg"
cv2.imwrite(temp_image_path, image_bgr)
os.system(f"python detect.py --source {temp_image_path} --img 640 --device cpu --weights models/detect/yolov9-s-converted.pt --name yolov9_c_640_detect --exist-ok --save-txt")
label_path = 'runs/detect/yolov9_c_640_detect/labels/temp_image_objects.txt'
yolo_boxes = read_yolo_boxes(label_path)
threshold = 10 # Set threshold (in pixels)
fig = plot_boxes_and_segment(image, yolo_boxes, rail_segment, img_width, img_height, threshold)
results = []
for class_name, x, y, w, h in yolo_boxes:
result = box_segment_relationship((0, x, y, w, h), rail_segment, img_width, img_height, threshold)
results.append(f"{class_name} at ({x:.2f}, {y:.2f}) is {result} the segment.")
os.remove(temp_image_path)
os.remove(label_path)
return fig, "\n".join(results)
# Streamlit app
def main():
st.title("Two-Step Train Obstruction Detection")
st.write("Step 1: Upload an image to detect the rail. Step 2: Upload an image with objects to detect obstructions.")
# Step 1: Rail Detection
st.header("Step 1: Rail Detection")
rail_image = st.file_uploader("Upload image for rail detection", type=["jpg", "jpeg", "png"])
if rail_image is not None:
rail_fig, rail_segment = detect_rail(rail_image)
st.pyplot(rail_fig)
st.success("Rail detection completed!")
# Step 2: Object Detection
st.header("Step 2: Object Detection")
object_image = st.file_uploader("Upload image for object detection", type=["jpg", "jpeg", "png"])
if object_image is not None:
object_fig, object_results = detect_objects(object_image, rail_segment)
st.pyplot(object_fig)
st.text_area("Analysis Results", object_results, height=200)
st.success("Object detection and analysis completed!")
if __name__ == "__main__":
main() |