OpenCV (一）yoloV3 / yoloV4 对象检测

环境：

• python 3.6.8
• opencv 4.1.2 (yoloV3) / opencv 4.4.0 (yoloV4)

PS：yoloV3-tiny / yoloV4-tiny 适用

一、参数

# 参考  python yolo_video.py --input videos/airport.mp4 --output output/airport_output.avi --yolo yolo-coco

import numpy as np
import argparse
import imutils
import time
import cv2
import os

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--input", default='./videos/overpass.mp4',
	help="path to input video")
ap.add_argument("-o", "--output", default='./output/overpass.avi',
	help="path to output video")
ap.add_argument("-y", "--yolo", default='./yolo-coco',
	help="base path to YOLO directory")
ap.add_argument("-c", "--confidence", type=float, default=0.5,
	help="minimum probability to filter weak detections")
ap.add_argument("-t", "--threshold", type=float, default=0.3,
	help="threshold when applyong non-maxima suppression")
args = vars(ap.parse_args())

二、加载标签、模型与结构

# load the COCO class labels our YOLO model was trained on
labelsPath = os.path.sep.join([args["yolo"], "car.names"])
LABELS = open(labelsPath).read().strip().split("\n")

# initialize a list of colors to represent each possible class label
np.random.seed(42)
COLORS = np.random.randint(0, 255, size=(len(LABELS), 3),
	dtype="uint8")

# derive the paths to the YOLO weights and model configuration
weightsPath = os.path.sep.join([args["yolo"], "yolov3-tiny-me-416.weights"])
configPath = os.path.sep.join([args["yolo"], "yolov3-tiny-me-416.cfg"])

# load our YOLO object detector trained on COCO dataset (80 classes)
# and determine only the *output* layer names that we need from YOLO
print("[INFO] loading YOLO from disk...")

# 方法 一
# # ['caffe', 'tensorflow', 'torch', 'darknet', 'dldt']
# net = cv2.dnn.readNet(cv2.samples.findFile(weightsPath), #cv2.samples.findFile(configPath),'darknet')

# 方法 二
net = cv2.dnn.readNetFromDarknet(configPath, weightsPath)

# 可选列表
# backends = (cv.dnn.DNN_BACKEND_DEFAULT, cv.dnn.DNN_BACKEND_HALIDE, #cv.dnn.DNN_BACKEND_INFERENCE_ENGINE, cv.dnn.DNN_BACKEND_OPENCV)
# targets = (cv.dnn.DNN_TARGET_CPU, cv.dnn.DNN_TARGET_OPENCL, #cv.dnn.DNN_TARGET_OPENCL_FP16, #cv.dnn.DNN_TARGET_MYRIAD)

# net.setPreferableBackend(cv2.dnn.DNN_BACKEND_OPENCV)
# net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU) 

ln = net.getLayerNames()
ln = [ln[i[0] - 1] for i in net.getUnconnectedOutLayers()]

三、视频-源初始参数（如果要录制解锁 writer ）

# initialize the video stream, pointer to output video file, and
# frame dimensions
vs = cv2.VideoCapture(args["input"])
# writer = None
(W, H) = (None, None)

# try to determine the total number of frames in the video file
try:
	prop = cv2.cv.CV_CAP_PROP_FRAME_COUNT if imutils.is_cv2() \
		else cv2.CAP_PROP_FRAME_COUNT
	total = int(vs.get(prop))
	print("[INFO] {} total frames in video".format(total))

# an error occurred while trying to determine the total
# number of frames in the video file
except:
	print("[INFO] could not determine # of frames in video")
	print("[INFO] no approx. completion time can be provided")
	total = -1

四、读取并预处理+推理

# loop over frames from the video file stream
while True:
	t1 = time.time()
	# read the next frame from the file
	(grabbed, frame) = vs.read()

	# if the frame was not grabbed, then we have reached the end
	# of the stream
	if not grabbed:
		break

	# if the frame dimensions are empty, grab them
	if W is None or H is None:
		(H, W) = frame.shape[:2]

	# construct a blob from the input frame and then perform a forward
	# pass of the YOLO object detector, giving us our bounding boxes
	# and associated probabilities
	blob = cv2.dnn.blobFromImage(frame, 1 / 255.0, (416, 416),
		swapRB=True, crop=False)
	net.setInput(blob)
	start = time.time()
	layerOutputs = net.forward(ln)
	end = time.time()

 

五、结果整合+NMS

	# initialize our lists of detected bounding boxes, confidences,
	# and class IDs, respectively
	boxes = []
	confidences = []
	classIDs = []

	# loop over each of the layer outputs
	for output in layerOutputs:
		# loop over each of the detections
		for detection in output:
			# extract the class ID and confidence (i.e., probability)
			# of the current object detection
			scores = detection[5:]
			classID = np.argmax(scores)
			confidence = scores[classID]

			# filter out weak predictions by ensuring the detected
			# probability is greater than the minimum probability
			if confidence > args["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[0:4] * 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))
				classIDs.append(classID)

	# apply non-maxima suppression to suppress weak, overlapping
	# bounding boxes
	idxs = cv2.dnn.NMSBoxes(boxes, confidences, args["confidence"],
		args["threshold"])

六、画图并可视化（如果要录制解锁 writer ）

	# 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 frame
			color = [int(c) for c in COLORS[classIDs[i]]]
			cv2.rectangle(frame, (x, y), (x + w, y + h), color, 2)
			text = "{}: {:.4f}".format(LABELS[classIDs[i]],
				confidences[i])
			cv2.putText(frame, text, (x, y - 5),
				cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)


	# # check if the video writer is None
	# if writer is None:
	# 	# initialize our video writer
	# 	fourcc = cv2.VideoWriter_fourcc(*"MJPG")
	# 	writer = cv2.VideoWriter(args["output"], fourcc, 30,
	# 		(frame.shape[1], frame.shape[0]), True)
	#
	# 	# some information on processing single frame
	# 	if total > 0:
	# 		elap = (end - start)
	# 		print("[INFO] single frame took {:.4f} seconds".format(elap))
	# 		print("[INFO] estimated total time to finish: {:.4f}".format(
	# 			elap * total))
	#
	# # write the output frame to disk
	# writer.write(frame)

	cv2.imshow("result", frame)
	print('spent time:',time.time()-t1)
	if cv2.waitKey(1) & 0xFF == ord('q'): break

# release the file pointers
print("[INFO] cleaning up...")
# writer.release()
vs.release()

七、测试

$ python yolo_video.py --input videos/car_chase_01.mp4 \
    --output output/car_chase_01.avi --yolo yolo-coco
[INFO] loading YOLO from disk...
[INFO] 583 total frames in video
[INFO] single frame took 0.3500 seconds
[INFO] estimated total time to finish: 204.0238
[INFO] cleaning up...