def process_video(img):
start = time.time()
history = deque(maxlen=30)
skimage.io.imsave('c2.PNG', img)
im2, boxes = test_image('c2.PNG', False)
skimage.io.imsave('c1.PNG', im2)
img_lanes = laneDetection('c1.PNG')
# Iterate through all detected cars
for b in range(1, boxes[1] + 1):
# Find pixels with each car_number label value
nonzero = (boxes[0] == b).nonzero()
# Identify x and y values of those pixels
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])
# Append current boxe to history
history.append([
np.min(nonzerox),
np.min(nonzeroy),
np.max(nonzerox),
np.max(nonzeroy)
])
# Get recent boxes for the last 30 fps
r_boxes = np.array(history).tolist()
# Groups the object candidate rectangles with difference of 10%
boxes = cv2.groupRectangles(r_boxes, 10, .1)
# Draw rectangles if found
if len(boxes[0]) != 0:
for box in boxes[0]:
cv2.rectangle(img_lanes, (box[0], box[1]), (box[2], box[3]),
(0, 0, 255), 6)
# Return image with found cars and lanes
end = time.time()
elapsed = end - start
times.append(elapsed)
return img_lanes
#Training the model, uncomment the following 2 lines to train the model from scratch
#model.fit(X_train, Y_train, batch_size=256, epochs=1, verbose=2, validation_data=(X_test, Y_test))
#model.save_weights('./dataset/model1.h5')
#Loading the pretrained weights , approx 2 MB of data
model.load_weights('./dataset/model.h5')
#Testing the model on randon validation images that were splitted from the dataset(10%)
#Keep the function call commented if there is no dataset folder
#test_random(X_test, Y_test, model)
#Testing the model for a bigger image(1280x720) from the folder test_images
img = './test_images/test4.jpg'
cars_img, B = test_image(img, True)
skimage.io.imsave('cars_detected.PNG', cars_img)
lanes_img = laneDetection(img)
plot_img(lanes_img)
#Combining the results of both pipelines by passing the image with cars to lanes function
combined_image = laneDetection('cars_detected.PNG')
plot_img(combined_image)
#This call creats the Video by processing the test video frame by frame
#Comment this line for avoiding the video creation
create_video()
#print('Showing the results from HOG pipeline -- Classical Vision-- \n')
#model.fit(X_train, Y_train, batch_size=256, epochs=1, verbose=2, validation_data=(X_test, Y_test))
#model.save_weights('./dataset/model1.h5')
#Loading the pretrained weights , approx 2 MB of data
model.load_weights('./dataset/model.h5')
#Testing the model on randon validation images that were splitted from the dataset(10%)
#Keep the function call commented if there is no dataset folder
#test_random(X_test, Y_test, model)
#Testing the model for a bigger image(1280x720) from the folder test_images
img = './test_images/test4.jpg'
cars_img, B = test_image(img, False)
#skimage.io.imsave('cars_detected.PNG', cars_img)
#lanes_img = laneDetection(img)
#plot_img(lanes_img)
#Combining the results of both pipelines by passing the image with cars to lanes function
combined_image = laneDetection('cars_detected.PNG')
plot_img(combined_image)
#This call creats the Video by processing the test video frame by frame
#Comment this line for avoiding the video creation
start = time.time()
create_video()
end = time.time()