Merge branch 'master' of http://gitlab.sliit.lk/2021-115/2021-115 into it18110708_kodikara

 Conflicts:
	.idea/workspace.xml

Hazardous_object_detection/Hot_objects/hotObject-detection.py

 # IT18006308
+
+# Import Libraries
+from imageai.Detection import ObjectDetection, VideoObjectDetection
+import os
+import pickle
+import time
+import cv2
+import sys
+
+THRESHOLD_ITEM = 0.5
+THRESHOLD_PERSON = 0.5
+
+print("Test 1 : Hot Object Detection Start")
+
+detector = VideoObjectDetection()
+detector.setModelTypeAsYOLOv3()
+detector.setModelPath("../model/yolo.h5")
+detector.loadModel()
+
+
+def forFrame(frame_number, output_array, outpun_count, returned_frame):
+    kettle_count = 0
+    kettles = []
+    person_count = 0
+    persons = []
+
+    for detection in output_array:
+        print(str(detection['name']) + " - " + str(detection['percentage_probability']) + " - " + str(
+            detection['box_point']))
+
+        if detection['name'] == 'kettle' and detection['percentage_probability'] >= THRESHOLD_ITEM:
+            kettle_count = kettle_count + 1
+            kettles.append(detection['box_point'])
+            print(detection["name"], " : ", detection["percentage_probability"], " : ", detection['box_point'])
+
+        if detection['name'] == 'person' and detection['percentage_probability'] >= THRESHOLD_PERSON:
+            person_count = person_count + 1
+            persons.append(detection['box_point'])
+            print(detection["name"], " : ", detection["percentage_probability"], " : ", detection['box_point'])
+
+        # Check the person is in room
+        if len(persons) == 0:
+            print("Person is not in room")
+
+        if len(persons) > 1:
+            print("Person in room")

Hazardous_object_detection/Sharp_objects/sharpObject-detection.py

 # IT18006308
 
 # Import Libraries
-from imageai.Detection import ObjectDetection
+from imageai.Detection import ObjectDetection, VideoObjectDetection
+from imageai.Detection.Custom import CustomObjectDetection
+
 import os
 import pickle
 import time
@@ -9,35 +11,68 @@ import cv2
 import sys
 
 THRESHOLD_ITEM = 0.5
+THRESHOLD_PERSON = 0.5
 
 print("Test 1 : Sharp Object Detection Start")
 
-detector = ObjectDetection()
-detector2 = ObjectDetection()
+# detector = ObjectDetection()
+detector = VideoObjectDetection()
+detector2 = VideoObjectDetection()
 
 detector.setModelTypeAsYOLOv3()
-detector.setModelPath("model/yolo.h5")
+detector.setModelPath("../model/yolo.h5")
 detector.loadModel()
-detection1 = detector.detectObjectsFromImage(input_image="input/sharp2.jpg", output_image_path="output/sharp2.jpg")
+# detection1 = detector.detectObjectsFromImage(input_image="input/sharp2.jpg", output_image_path="output/sharp2.jpg")
 
 detector2.setModelTypeAsRetinaNet()
 detector2.setModelPath("model/resnet50_coco_best_v2.1.0.h5")
 detector2.loadModel()
 
-detection2 = detector2.detectObjectsFromImage(input_image="input/sharp2.jpg", output_image_path="output/sharp2.jpg")
 
-scissors_count = 0
-scissors = []
+# detection2 = detector2.detectObjectsFromImage(input_image="input/sharp2.jpg", output_image_path="output/sharp2.jpg")
+
+def forFrame(frame_number, output_array, outpun_count, returned_frame):
+    scissors_count = 0
+    scissors = []
+    knife_count = 0
+    knife = []
+    fork_count = 0
+    fork = []
+    person_count = 0
+    person = []
+
+    print(frame_number)
+
+    # YOLOv3 Model (person and scissors)
+    for detection in output_array:
+        print(str(detection['name']) + " - " + str(detection['percentage_probability']) + " - " + str(
+            detection['box_point']))
+
+        # identify Scissors
+        if detection['name'] == 'scissors' and detection['percentage_probability'] >= THRESHOLD_ITEM:
+            scissors_count = scissors_count + 1
+            scissors.append(detection['box_point'])
+            print(detection["name"], " : ", detection["percentage_probability"], " : ", detection['box_point'])
+
+        if detection['name'] == 'person' and detection['percentage_probability'] >= THRESHOLD_PERSON:
+            person_count = person_count + 1
+            person.append(detection['box_point'])
+            print(detection["name"], " : ", detection["percentage_probability"], " : ", detection['box_point'])
+
+        # RetinaNet Model
+        if detection['name'] == 'knife' and detection['percentage probability'] >= THRESHOLD_ITEM:
+            knife_count = knife_count + 1
+            knife.append(detection['box_point'])
+            print(detection["name"], " : ", detection["percentage_probability"], " : ", detection["box_point"])
 
-print(detection1)
+        if detection['name'] == 'fork' and detection['percentage_probability'] >= THRESHOLD_ITEM:
+            fork_count = fork_count + 1
+            fork.append(detection['box_point'])
+            print(detection["name"], " : ", detection["percentage_probability"], " : ", detection["box_point"])
 
-# YOLOv3 Model
-for detection in detection1:
-    print(str(detection['name']) + " - " + str(detection['precentage_probability']) + " - " + str(
-        detection['box_point']))
+    # Check the person is in room
+    if len(person) == 0:
+        print("Person is not in room")
 
-    # identify Scissors
-    if(detection['name'] == 'scissors' and detection['precentage_probability'] >= THRESHOLD_ITEM):
-        scissors_count = scissors_count + 1
-        scissors.append(detection['box_point'])
-        print(detection["name"], " : ", detection["precentage_probability"], " : ", detection['box_point'])
+    if len(person) > 1:
+        print("Person in room")