- 利用
tensorflow object detection API
來訓練适合工作目标檢測模型,其中使用和訓練方式部落格連結如下:
【Tensorflow object detection API】使用SSD-Mobilenet訓練模型+ubuntu 16.04+python3(步驟十厘清晰!)
- 如下代碼能夠利用opencv實時讀取到rtsp的視訊流,并且采用多線程方式解決了opencv的花屏問題,将視訊流送進目标檢測模型,進行目标檢測:
import threading
# 導入各種包
import numpy as np
import sys
import tensorflow as tf
import time
from distutils.version import StrictVersion
if StrictVersion(tf.__version__) < StrictVersion('1.9.0'):
raise ImportError('Please upgrade your TensorFlow installation to v1.9.* or later!')
# 增加cv包,以及擷取攝像頭裝置号
import cv2
from utils import label_map_util
from utils import visualization_utils as vis_util
# inhere
PATH_TO_CKPT = '/*/research/object_detection/ssd_model_fpn/model/frozen_inference_graph.pb'
# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = '/*/research/object_detection/ssd_model/pascal_label_map.pbtxt'
NUM_CLASSES = 20
class RTSCapture(cv2.VideoCapture):
_cur_frame = None
_reading = False
schemes = ["rtsp://","rtmp://"]
@staticmethod
def create(url, *schemes):
rtscap = RTSCapture(url)
rtscap.frame_receiver = threading.Thread(target=rtscap.recv_frame, daemon=True)
rtscap.schemes.extend(schemes)
if isinstance(url, str) and url.startswith(tuple(rtscap.schemes)):
rtscap._reading = True
elif isinstance(url, int):
pass
return rtscap
def isStarted(self):
ok = self.isOpened()
if ok and self._reading:
ok = self.frame_receiver.is_alive()
return ok
def recv_frame(self):
while self._reading and self.isOpened():
ok, frame = self.read()
if not ok: break
self._cur_frame = frame
self._reading = False
def read2(self):
frame = self._cur_frame
self._cur_frame = None
return frame is not None, frame
def start_read(self):
self.frame_receiver.start()
self.read_latest_frame = self.read2 if self._reading else self.read
def stop_read(self):
self._reading = False
if self.frame_receiver.is_alive(): self.frame_receiver.join()
if __name__ == '__main__':
if len(sys.argv) < 2:
print("usage:")
print("need rtsp://xxx")
sys.exit()
# load graph
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES,
use_display_name=True)
category_index = label_map_util.create_category_index(categories)
# open rtsp
rtscap = RTSCapture.create(sys.argv[1])
rtscap.start_read()
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
while rtscap.isStarted():
ok, image_np = rtscap.read_latest_frame()
if cv2.waitKey(1) & 0xFF == ord('q'):
break
if not ok:
continue
#time_start = time.time()
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image_np, axis=0)
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represent how level of confidence for each of the objects.
# Score is shown on the result image, together with the class label.
scores = detection_graph.get_tensor_by_name('detection_scores:0')
classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Actual detection.
(boxes, scores, classes, num_detections) = sess.run(
[boxes, scores, classes, num_detections],
feed_dict={image_tensor: image_np_expanded})
# Visualization of the results of a detection.
vis_util.visualize_boxes_and_labels_on_image_array(
image_np, np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores), category_index,
use_normalized_coordinates=True,
line_thickness=8)
cv2.imshow('object detection', cv2.resize(image_np, (1500, 800)))
#time_end = time.time()
#print('time cost', (time_end - time_start) * 1000, 'ms')
rtscap.stop_read()
rtscap.release()
cv2.destroyAllWindows()