opencv 调用 YOLOv3 进行目标检测

训练好的模型参数可以在这个脚本文件中找到，这是针对 coco 数据集训练得到的目标检测网络。 Common Objects in COntext 数据集是微软发布的一个大型图像数据集, 专为对象检测、分割、人体关键点检测、语义分割和字幕生成而设计。数据集中的目标种类有 80 个。
https://github.com/spmallick/learnopencv/blob/master/ObjectDetection-YOLO/getModels.sh

# 这是获取模型参数的 shell 脚本，也可以直接在浏览器下载
wget https://pjreddie.com/media/files/yolov3.weights
wget https://github.com/pjreddie/darknet/blob/master/cfg/yolov3.cfg?raw=true -O ./yolov3.cfg
wget https://github.com/pjreddie/darknet/blob/master/data/coco.names?raw=true -O ./coco.names

'''
YOLO demo
'''
COLORS = [(255,0,0) for i in range(80)]    # 这里所有种类都用蓝色，可以给不同种类用不同颜色
with open('yolo/coco.names','r') as file:     # 这是读取所有种类的名字
	LABELS = file.read().splitlines()

args = {
    "yolo": "yolo",   #.weights 和 .cfg 文件所在的目录
    "image": "animals.jpg",
    "confidence": 0.1,              # minimum bounding box confidence
    "threshold": 0.3,               # NMS threshold
}

# derive the paths to the YOLO weights and model configuration
weightsPath = os.path.sep.join([args["yolo"], "yolov3.weights"])
configPath = os.path.sep.join([args["yolo"], "yolov3.cfg"])
 
# load YOLO object detector trained on COCO dataset (80 classes)
print("[INFO] loading YOLO from disk...")
net = cv2.dnn.readNetFromDarknet(configPath, weightsPath)

# load our input image and grab its spatial dimensions
image = cv2.imread(args["image"])
(H, W) = image.shape[:2]
 
# determine only the *output* layer names that we need from YOLO
ln = net.getLayerNames()
ln = [ln[i[0] - 1] for i in net.getUnconnectedOutLayers()]

# construct a blob from the input image and then perform a forward
# pass of the YOLO object detector, giving us our bounding boxes and
# associated probabilities
blob = cv2.dnn.blobFromImage(image, 1 / 255.0, (416, 416),
	swapRB=True, crop=False)
net.setInput(blob)
start = time.time()
layerOutputs = net.forward(ln)
end = time.time()
 
# show timing information on YOLO
print("[INFO] YOLO took {:.6f} seconds".format(end - start))

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 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 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)

idxs = cv2.dnn.NMSBoxes(boxes, confidences, args["confidence"],
	args["threshold"])

# 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[classIDs[i]]]
		cv2.rectangle(image, (x, y), (x + w, y + h), color, 2)
		text = "{}: {:.4f}".format(LABELS[classIDs[i]], confidences[i])
		cv2.putText(image, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX,
			0.5, color, 2)
 
# show the output image
cv2.imshow("Image", image)
cv2.waitKey(0)

结果如下，图片是从网上随便找来的：

[INFO] loading YOLO from disk...
[INFO] YOLO took 0.996802 seconds