from imageai.Detection import ObjectDetection, VideoObjectDetection
import os
import cv2
import rospy
from std_msgs.msg import Bool, String
video_detector = VideoObjectDetection()
video_detector_resnet = VideoObjectDetection()
camera = cv2.VideoCapture(0)
model_path = "./models/yolo-tiny.h5"
model_path_resnet = "./models/resnet50_coco_best_v2.0.1.h5"
video_detector.setModelTypeAsTinyYOLOv3()
video_detector_resnet.setModelTypeAsRetinaNet()
video_detector.setModelPath(model_path)
video_detector_resnet.setModelPath(model_path_resnet)
#video_detector.loadModel()
video_detector_resnet.loadModel()
#publishers
pub_bool = rospy.Publisher('detecting_object', Bool, queue_size=100)
pub_str = rospy.Publisher('objects_detected', String, queue_size=100)
custom = video_detector_resnet.CustomObjects(person=True,
handbag=True,
tie=True,
suitcase=True,
bottle=True,
from imageai.Detection import VideoObjectDetection
import os
execution_path = os.getcwd()
detector = VideoObjectDetection()
detector.setModelTypeAsYOLOv3()
detector.setModelPath(
os.path.join(execution_path, "C:\\Users\\Admin_Robo\\Desktop\\yolo.h5"))
detector.loadModel(detection_speed='faster')
video_path = detector.detectObjectsFromVideo(
input_file_path=os.path.join(
execution_path,
"C:\\Users\\Admin_Robo\\Desktop\\WIN_20190912_17_36_23_Pro.mp4"),
output_file_path=os.path.join(execution_path,
"C:\\Users\\Admin_Robo\\Desktop\\esp_test"),
frames_per_second=1,
log_progress=True)
print(video_path)
def predict():
data = request.get_json(force=True)
body = data.get('data')
filew = body.get('file')
print(filew)
decoded_string = base64.b64decode(filew)
with open('1.mp4', 'wb') as wfile:
wfile.write(decoded_string)
video = cv2.VideoCapture("1.mp4")
# Find OpenCV version
(major_ver, minor_ver, subminor_ver) = (cv2.__version__).split('.')
fps = 0
if int(major_ver) < 3:
fps = round(video.get(cv2.cv.CV_CAP_PROP_FPS))
print("Frames per second using video.get(cv2.cv.CV_CAP_PROP_FPS): {0}".
format(fps))
else:
fps = round(video.get(cv2.CAP_PROP_FPS))
print(
"Frames per second using video.get(cv2.CAP_PROP_FPS) : {0}".format(
fps))
video.release()
# def incr():
# global varib
# varib = 'bbbbbbbb'
# incr()
# print("varib", varib)
def forSeconds(second_number, output_arrays, count_arrays,
average_output_count):
print("SECOND : ", second_number)
# print("Array for the outputs of each frame ", output_arrays)
# print("Array for output count for unique objects in each frame : ", count_arrays)
# print("Output average count for unique objects in the last second: ", average_output_count)
# print("------------END OF A SECOND --------------")
def forFull(output_arrays, count_arrays, average_output_count):
#Perform action on the 3 parameters returned into the function
# print("Array for the outputs of each frame ", output_arrays)
# print("Array for output count for unique objects in each frame : ", count_arrays)
# print("Output average count for unique objects in the last second: ", average_output_count)
global objects
objects = output_arrays
video_detector = VideoObjectDetection()
video_detector.setModelTypeAsYOLOv3()
video_detector.setModelPath(os.path.join(execution_path, "yolo.h5"))
video_detector.loadModel()
video_detector.detectObjectsFromVideo(
input_file_path=os.path.join(execution_path, "1.mp4"),
output_file_path=os.path.join(execution_path, "traffic_detected"),
frames_per_second=fps,
per_second_function=forSeconds,
video_complete_function=forFull,
minimum_percentage_probability=30)
def convert_avi_to_mp4(avi_file_path, output_name):
os.popen(
"ffmpeg -i '{input}' -ac 2 -b:v 2000k -c:a aac -c:v libx264 -b:a 160k -vprofile high -bf 0 -strict experimental -f mp4 './static/{output}.mp4'"
.format(input=avi_file_path, output=output_name))
return True
convert_avi_to_mp4("traffic_detected.avi", "converted")
json_dump = pd.Series(objects).to_json(orient='values')
print("==============", json_dump)
return json_dump
def __init__(self):
execution_path = os.getcwd()
self.myDetector = VideoObjectDetection()
def configureVideoDetector(self):
self.detector = VideoObjectDetection()
self.detector.setModelTypeAsYOLOv3()
self.detector.setModelPath( os.path.join(self.execution_path , yolo_network_path))
self.detector.loadModel()
average_output_count)
print("------------END OF A MINUTE --------------")
#full
def forFull(output_arrays, count_arrays, average_output_count):
print("Array for the outputs of each frame ", output_arrays)
print("Array for output count for unique objects in each frame : ",
count_arrays)
print("Output average count for unique objects in the entire video: ",
average_output_count)
print("------------END OF THE VIDEO --------------")
camera = cv2.VideoCapture(0)
detectormodel = VideoObjectDetection()
detectormodel.setModelTypeAsYOLOv3()
detectormodel.setModelPath(os.path.join(os.getcwd(), "yolo.h5"))
detectormodel.loadModel()
# plt.show()
video_path = detectormodel.detectObjectsFromVideo(
camera_input=camera,
output_file_path=os.path.join(os.getcwd(), "camera_detected_video"),
frames_per_second=20,
log_progress=True,
minimum_percentage_probability=40,
detection_timeout=20,
per_minute_function=forMinute)
# output(plots)
resized = False
start_cv = time.time()
bbox, label, conf = cv.detect_common_objects(frame)
elapsed_time_cv += (time.time() - start_cv)
#print(bbox, label, conf)
# draw bounding box over detected objects
out = draw_bbox(frame, bbox, label, conf)
output_movie_cv.write(frame)
frame_number += 1
print("time spent in conversion: {}".format(elapsed_time_cv))
input_movie.release()
detector5 = VideoObjectDetection()
detector5.setModelTypeAsYOLOv3()
detector5.setModelPath(os.path.join(execution_path, "model_data/yolo.h5"))
detector5.loadModel()
custom_objects = detector5.CustomObjects(person=True)
start = time.time()
video_path = detector5.detectCustomObjectsFromVideo(
custom_objects=custom_objects,
input_file_path=os.path.join(execution_path,
"data/test_videos/hamilton_clip.mp4"),
output_file_path=os.path.join(execution_path,
"data/test_videos/obj_det_normal"),
frames_per_second=29)
eplased_time = time.time() - start
