Spaces:
Running
Running
File size: 4,531 Bytes
9d3162f |
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 |
import cv2
import numpy as np
import time
import sys
CONFIDENCE = 0.5
SCORE_THRESHOLD = 0.5
IOU_THRESHOLD = 0.5
config_path = "cfg/yolov3.cfg"
weights_path = "weights/yolov3.weights"
font_scale = 1
thickness = 1
labels = open("data/coco.names").read().strip().split("\n")
colors = np.random.randint(0, 255, size=(len(labels), 3), dtype="uint8")
net = cv2.dnn.readNetFromDarknet(config_path, weights_path)
ln = net.getLayerNames()
try:
ln = [ln[i[0] - 1] for i in net.getUnconnectedOutLayers()]
except IndexError:
# in case getUnconnectedOutLayers() returns 1D array when CUDA isn't available
ln = [ln[i - 1] for i in net.getUnconnectedOutLayers()]
# read the file from the command line
video_file = sys.argv[1]
cap = cv2.VideoCapture(video_file)
_, image = cap.read()
h, w = image.shape[:2]
fourcc = cv2.VideoWriter_fourcc(*"XVID")
out = cv2.VideoWriter("output.avi", fourcc, 20.0, (w, h))
while True:
_, image = cap.read()
h, w = image.shape[:2]
blob = cv2.dnn.blobFromImage(image, 1/255.0, (416, 416), swapRB=True, crop=False)
net.setInput(blob)
start = time.perf_counter()
layer_outputs = net.forward(ln)
time_took = time.perf_counter() - start
print("Time took:", time_took)
boxes, confidences, class_ids = [], [], []
# loop over each of the layer outputs
for output in layer_outputs:
# loop over each of the object detections
for detection in output:
# extract the class id (label) and confidence (as a probability) of
# the current object detection
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
# discard weak predictions by ensuring the detected
# probability is greater than the minimum probability
if confidence > CONFIDENCE:
# scale the bounding box coordinates back relative to the
# size of the image, keeping in mind that YOLO actually
# returns the center (x, y)-coordinates of the bounding
# box followed by the boxes' width and height
box = detection[:4] * np.array([w, h, w, h])
(centerX, centerY, width, height) = box.astype("int")
# use the center (x, y)-coordinates to derive the top and
# and left corner of the bounding box
x = int(centerX - (width / 2))
y = int(centerY - (height / 2))
# update our list of bounding box coordinates, confidences,
# and class IDs
boxes.append([x, y, int(width), int(height)])
confidences.append(float(confidence))
class_ids.append(class_id)
# perform the non maximum suppression given the scores defined before
idxs = cv2.dnn.NMSBoxes(boxes, confidences, SCORE_THRESHOLD, IOU_THRESHOLD)
font_scale = 1
thickness = 1
# ensure at least one detection exists
if len(idxs) > 0:
# loop over the indexes we are keeping
for i in idxs.flatten():
# extract the bounding box coordinates
x, y = boxes[i][0], boxes[i][1]
w, h = boxes[i][2], boxes[i][3]
# draw a bounding box rectangle and label on the image
color = [int(c) for c in colors[class_ids[i]]]
cv2.rectangle(image, (x, y), (x + w, y + h), color=color, thickness=thickness)
text = f"{labels[class_ids[i]]}: {confidences[i]:.2f}"
# calculate text width & height to draw the transparent boxes as background of the text
(text_width, text_height) = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, fontScale=font_scale, thickness=thickness)[0]
text_offset_x = x
text_offset_y = y - 5
box_coords = ((text_offset_x, text_offset_y), (text_offset_x + text_width + 2, text_offset_y - text_height))
overlay = image.copy()
cv2.rectangle(overlay, box_coords[0], box_coords[1], color=color, thickness=cv2.FILLED)
# add opacity (transparency to the box)
image = cv2.addWeighted(overlay, 0.6, image, 0.4, 0)
# now put the text (label: confidence %)
cv2.putText(image, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX,
fontScale=font_scale, color=(0, 0, 0), thickness=thickness)
out.write(image)
cv2.imshow("image", image)
if ord("q") == cv2.waitKey(1):
break
cap.release()
cv2.destroyAllWindows() |