我正在尝试从 pyimagesearch web 实现以下代码，以使用 dlib 进行多对象跟踪。我尝试自定义它以使用detectron2 而不是Mobilenet + SSD Caffe 模型运行它。这是代码
#!/usr/bin/python
# -*- coding: utf-8 -*-
import cv2
import numpy as np
import multiprocessing
import torch
import imutils
import dlib
import detectron2
import argparse
from detectron2.utils.logger import setup_logger
setup_logger()
from imutils.video import FPS
from detectron2.config import get_cfg
from detectron2 import model_zoo
from detectron2.engine import DefaultPredictor
from detectron2.utils.visualizer import Visualizer, ColorMode
from detectron2.data import MetadataCatalog
from detectron2.structures import Boxes, BoxMode, pairwise_iou
# dlib tracker
def start_tracker(
boxes,
label,
rgb,
inputQueue,
outputQueue,
):
# construct a dlib rectangle object from the bounding box
# coordinates and then start the correlation tracker
t = dlib.correlation_tracker()
left = boxes[0]
top = boxes[1]
right = boxes[2]
bottom = boxes[3]
rect = dlib.rectangle(int(left), int(top), int(right), int(bottom))
t.start_track(rgb, rect)
# loop indefinitely -- this function will be called as a daemon
# process so we don't need to worry about joining it
while True:
# attempt to grab the next frame from the input queue
rgb = inputQueue.get()
# if there was an entry in our queue, process it
if rgb is not None:
# update the tracker and grab the position of the tracked
# object
t.update(rgb)
pos = t.get_position()
# unpack the position object
startX = int(pos.left())
startY = int(pos.top())
endX = int(pos.right())
endY = int(pos.bottom())
# add the label + bounding box coordinates to the output
# queue
outputQueue.put((label, (startX, startY, endX, endY)))
ap = argparse.ArgumentParser()
ap.add_argument('-v', '--video', required=True,
help='path to input video file')
ap.add_argument('-o', '--output', type=str,
help='path to optional output video file')
ap.add_argument('-c', '--confidence', type=float, default=0.990,
help='minimum probability to filter weak detections')
args = vars(ap.parse_args())
# initialize our list of queues -- both input queue and output queue
# for *every* object that we will be tracking
inputQueues = []
outputQueues = []
# initialize the video stream and output video writer
print '[INFO] starting video stream...'
vs = cv2.VideoCapture(args['video'])
writer = None
label = ''
# start the frames per second throughput estimator
fps = FPS().start()
# Detectron
cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file('COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml'
))
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.7 # set threshold for this model
cfg.MODEL.WEIGHTS = \
model_zoo.get_checkpoint_url('COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml'
)
predictor = DefaultPredictor(cfg)
# loop over frames from the video file stream
while True:
# grab the next frame from the video file
(grabbed, frame) = vs.read()
# check to see if we have reached the end of the video file
if frame is None:
break
# resize the frame for faster processing and then convert the
# frame from BGR to RGB ordering (dlib needs RGB ordering)
frame = imutils.resize(frame, width=600)
rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
# if we are supposed to be writing a video to disk, initialize
# the writer
if args['output'] is not None and writer is None:
fourcc = cv2.VideoWriter_fourcc(*'MJPG')
writer = cv2.VideoWriter(args['output'], fourcc, 30,
(frame.shape[1], frame.shape[0]), True)
# if our list of queues is empty then we know we have yet to
# create our first object tracker
if len(inputQueues) == 0:
outputs = predictor(rgb)
instances = outputs['instances']
scores = instances.scores.cpu().numpy()
# loop over the detections
for i in np.arange(start=0, stop=len(instances), step=1):
# extract the confidence (i.e., probability) associated
# with the prediction
confidence = scores[i]
# filter out weak detections by requiring a minimum
# confidence
if confidence > args['confidence']:
# compute the (x, y)-coordinates of the bounding box
# for the object
boxes = instances.pred_boxes.tensor.cpu().numpy()
boxes = BoxMode.convert(boxes, BoxMode.XYXY_ABS,
BoxMode.XYWH_ABS)
boxes = boxes.tolist()
boxes = boxes[i]
(startX, startY, endX, endY) = boxes
bb = (startX, startY, endX, endY)
label = 'Id:' + str(i)
# create two brand new input and output queues,
# respectively
iq = multiprocessing.Queue()
oq = multiprocessing.Queue()
inputQueues.append(iq)
outputQueues.append(oq)
# spawn a daemon process for a new object tracker
p = multiprocessing.Process(target=start_tracker,
args=(bb, label, rgb, iq, oq))
p.daemon = True
p.start()
# grab the corresponding class label for the detection
# and draw the bounding box
cv2.rectangle(frame, (int(startX), int(startY)),
(int(endX), int(endY)), (int(0),
int(0xFF), int(0)), int(2))
cv2.putText(
frame,
label,
(int(startX), int(startY - 15)),
cv2.FONT_HERSHEY_SIMPLEX,
int(0.45),
(int(0), int(0xFF), int(0)),
int(2),
)
else:
# otherwise, we've already performed detection so let's track
# multiple objects
# loop over each of our input ques and add the input RGB
# frame to it, enabling us to update each of the respective
# object trackers running in separate processes
for iq in inputQueues:
iq.put(rgb)
# loop over each of the output queues
for oq in outputQueues:
# grab the updated bounding box coordinates for the
# object -- the .get method is a blocking operation so
# this will pause our execution until the respective
# process finishes the tracking update
(label, startX, startY, endX, endY) = oq.get()
# draw the bounding box from the correlation object
# tracker
cv2.rectangle(frame, (int(startX), int(startY)),
(int(endX), int(endY)), (int(0), int(0xFF),
int(0)), int(2))
cv2.putText(
frame,
label,
(int(startX), int(startY - 15)),
cv2.FONT_HERSHEY_SIMPLEX,
int(0.45),
(int(0), int(0xFF), int(0)),
int(2),
)
# check to see if we should write the frame to disk
if writer is not None:
writer.write(frame)
# show the output frame
# cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
# if the `q` key was pressed, break from the loop
if key == ord('q'):
break
# update the FPS counter
fps.update()
# stop the timer and display FPS information
fps.stop()
print '[INFO] elapsed time: {:.2f}'.format(fps.elapsed())
print '[INFO] approx. FPS: {:.2f}'.format(fps.fps())
# check to see if we need to release the video writer pointer
if writer is not None:
writer.release()
# do a bit of cleanup
# cv2.destroyAllWindows()
vs.release()
无论如何，我一遍又一遍地遇到这个错误，此时我不知道我做错了什么
Process Process-1:
Traceback (most recent call last):
File "/usr/lib/python3.6/multiprocessing/process.py", line 258, in _bootstrap
self.run()
File "/usr/lib/python3.6/multiprocessing/process.py", line 93, in run
self._target(*self._args, **self._kwargs)
File "Detection-Tracking.py", line 42, in start_tracker
t.start_track(rgb, rect)
RuntimeError:
Error detected at line 61.
Error detected in file /tmp/pip-wheel-66glv9rf/dlib/dlib/../dlib/image_processing/correlation_tracker.h.
Error detected in function void dlib::correlation_tracker::start_track(const image_type&, const dlib::drectangle&) [with image_type = dlib::numpy_image<dlib::rgb_pixel>].
Failing expression was p.is_empty() == false.
You can't give an empty rectangle.
void correlation_tracker::start_track()
我已经检查了 dlib.rectangle 的输入顺序是否正确，所以我愿意接受你能给我的任何想法。