10分钟学会使用YOLO及Opencv实现目标检测（上）|附源码

$ tree
.
├── images
│   ├── baggage_claim.jpg
│   ├── dining_table.jpg
│   ├── living_room.jpg
│   └── soccer.jpg
├── output
│   ├── airport_output.avi
│   ├── car_chase_01_output.avi
│   ├── car_chase_02_output.avi
│   └── overpass_output.avi
├── videos
│   ├── airport.mp4
│   ├── car_chase_01.mp4
│   ├── car_chase_02.mp4
│   └── overpass.mp4
├── yolo-coco
│   ├── coco.names
│   ├── yolov3.cfg
│   └── yolov3.weights
├── yolo.py
└── yolo_video.py

# import the necessary packagesimport numpy as npimport argparseimport timeimport cv2import os
# construct the argument parse and parse the argumentsap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
   help="path to input image")
ap.add_argument("-y", "--yolo", required=True,
   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 applying non-maxima suppression")
args = vars(ap.parse_args())

# load the COCO class labels our YOLO model was trained onlabelsPath = os.path.sep.join([args["yolo"], "coco.names"])
LABELS = open(labelsPath).read().strip().split("\n")
# initialize a list of colors to represent each possible class labelnp.random.seed(42)
COLORS = np.random.randint(0, 255, size=(len(LABELS), 3),
   dtype="uint8")

# derive the paths to the YOLO weights and model configurationweightsPath = os.path.sep.join([args["yolo"], "yolov3.weights"])
configPath = os.path.sep.join([args["yolo"], "yolov3.cfg"])
# load our 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 dimensionsimage = cv2.imread(args["image"])
(H, W) = image.shape[:2]
# determine only the *output* layer names that we need from YOLOln = 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 probabilitiesblob = 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 YOLOprint("[INFO] YOLO took {:.6f} seconds".format(end - start))

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

# loop over each of the layer outputsfor 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# boxesidxs = cv2.dnn.NMSBoxes(boxes, confidences, args["confidence"],
   args["threshold"])

# ensure at least one detection existsif 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 imagecv2.imshow("Image", image)
cv2.waitKey(0)

$ python yolo.py --image images/baggage_claim.jpg --yolo yolo-coco
[INFO] loading YOLO from disk...
[INFO] YOLO took 0.347815 seconds

$ python yolo.py --image images/living_room.jpg --yolo yolo-coco
[INFO] loading YOLO from disk...
[INFO] YOLO took 0.340221 seconds

$ python yolo.py --image images/dining_table.jpg --yolo yolo-coco
[INFO] loading YOLO from disk...
[INFO] YOLO took 0.362369 seconds

$ python yolo.py --image images/soccer.jpg --yolo yolo-coco
[INFO] loading YOLO from disk...
[INFO] YOLO took 0.345656 seconds