def getNumberOfPerson(img,place): input_video = img detection_graph, category_index = backbone.set_model('ssd_mobilenet_v2_coco_2018_03_29', 'mscoco_label_map.pbtxt') is_color_recognition_enabled = 0 result = object_counting_api.single_image_object_counting(input_video, detection_graph, category_index, is_color_recognition_enabled) # targeted objects counting cv2.destroyAllWindows() info_dict={} try: idx = result.find('person') info = result[idx:idx+11] #print(info) #print(int(info[-1])) complexity = cal_complexity(int(info[-1])) info_dict = {} info_dict['person'] = int(info[-1]) info_dict['place']= place info_dict['complexity'] = complexity info_dict['time']=datetime.datetime.now().strftime('%Y-%m-%d-%H-%M') except: info_dict['person']= None info_dict['person'] = None info_dict['place']= None info_dict['complexity'] = None info_dict['time']=None return info_dict
def count(image="ParkingLot.jpg"): input_video = image detection_graph, category_index = backbone.set_model( 'ssd_mobilenet_v1_coco_2018_01_28', 'mscoco_label_map.pbtxt') is_color_recognition_enabled = 0 result = object_counting_api.single_image_object_counting( input_video, detection_graph, category_index, is_color_recognition_enabled) # targeted objects counting print(result) return result
def count(image): input_image = image detection_graph = tf.Graph() with detection_graph.as_default(): od_graph_def = tf.GraphDef() with tf.gfile.GFile(PATH_TO_FROZEN_GRAPH, '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) fps = 30 # change it with your input video fps width = 626 # change it with your input video width height = 360 # change it with your input vide height is_color_recognition_enabled = 0 result = object_counting_api.single_image_object_counting(input_image, detection_graph, category_index, is_color_recognition_enabled, fps, width, height) # targeted objects counting return result
#---------------------------------------------- #--- Author : Ahmet Ozlu #--- Mail : [email protected] #--- Date : 27th January 2018 #---------------------------------------------- # Imports import tensorflow as tf # Object detection imports from utils import backbone from api import object_counting_api input_video = "./input_images_and_videos/sample_input_image.jpg" # By default I use an "SSD with Mobilenet" model here. See the detection model zoo (https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-box with varying speeds and accuracies. detection_graph, category_index = backbone.set_model( 'ssd_mobilenet_v1_coco_2018_01_28', 'mscoco_label_map.pbtxt') is_color_recognition_enabled = False # set it to true for enabling the color prediction for the detected objects result = object_counting_api.single_image_object_counting( input_video, detection_graph, category_index, is_color_recognition_enabled) # targeted objects counting print(result)