Add hugging files

original_app/README.md

@@ -0,0 +1,11 @@
+This is the based scarecrow application with the back-end and the scarecrow communication setup.
+
+Inside the huggingface face application, as a demo, there is only the back-end part with some visualisation setup.
+
+
+- a.mp3 -> predator sound for human
+- b.mp3 -> predator sound for cell_phone
+- coco.names -> labels for yolo to use
+- scarecrow.py -> the application that collect video and send the stream to the back-end
+- backend.py -> the application which run the model to detect animals
+- yolov3.cfg & yolov3.weights -> can't be included inside huggingface as binary

original_app/backend.py

@@ -0,0 +1,88 @@
+import cv2
+import numpy as np
+import socket
+import pickle
+import struct
+
+# Load YOLO model
+net = cv2.dnn.readNet("yolov3.weights", "yolov3.cfg")
+classes = []
+with open("coco.names", "r") as f:
+    classes = [line.strip() for line in f.readlines()]
+
+resolved_label = ''
+
+# Set up socket
+HOST = ''
+PORT = 8089
+s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+print('Socket created')
+s.bind((HOST, PORT))
+print('Socket bind complete')
+s.listen(10)
+print('Socket now listening')
+
+# Accept connections
+conn, addr = s.accept()
+
+# Receive and process frames
+data = b''
+payload_size = struct.calcsize("L")
+while True:
+    # Retrieve message size
+    while len(data) < payload_size:
+        data += conn.recv(4096)
+    packed_msg_size = data[:payload_size]
+    data = data[payload_size:]
+    msg_size = struct.unpack("L", packed_msg_size)[0]
+
+    # Retrieve all data based on message size
+    while len(data) < msg_size:
+        data += conn.recv(4096)
+    frame_data = data[:msg_size]
+    data = data[msg_size:]
+
+    # Extract frame
+    frame = pickle.loads(frame_data)
+
+    # Run YOLO on frame
+    blob = cv2.dnn.blobFromImage(frame, 1/255.0, (416, 416), swapRB=True, crop=False)
+    net.setInput(blob)
+    outputs = net.forward(net.getUnconnectedOutLayersNames())
+    boxes = []
+    confidences = []
+    class_ids = []
+    for output in outputs:
+        for detection in output:
+            scores = detection[5:]
+            class_id = np.argmax(scores)
+            confidence = scores[class_id]
+            if confidence > 0.5:
+                center_x = int(detection[0] * frame.shape[1])
+                center_y = int(detection[1] * frame.shape[0])
+                w = int(detection[2] * frame.shape[1])
+                h = int(detection[3] * frame.shape[0])
+                x = int(center_x - w/2)
+                y = int(center_y - h/2)
+                boxes.append([x, y, w, h])
+                confidences.append(float(confidence))
+                class_ids.append(class_id)
+    indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
+    if len(indexes) > 0:
+        for i in indexes.flatten():
+            resolved_label = classes[class_ids[i]]
+            print(resolved_label)
+
+    # Display frame
+    cv2.imshow('frame', frame)
+    cv2.waitKey(1)
+
+    # Send response to client
+    try:
+        if len(indexes) > 0:
+            response = "[Scarecrow]: " + resolved_label
+        else:
+            response = "[Scarecrow]: NONE"
+    except IndexError:
+        response = "[Scarecrow]: ERROR"
+    conn.sendall(response.encode())

original_app/coco.names

@@ -0,0 +1,80 @@
+person
+bicycle
+car
+motorbike
+aeroplane
+bus
+train
+truck
+boat
+traffic light
+fire hydrant
+stop sign
+parking meter
+bench
+bird
+cat
+dog
+horse
+sheep
+cow
+elephant
+bear
+zebra
+giraffe
+backpack
+umbrella
+handbag
+tie
+suitcase
+frisbee
+skis
+snowboard
+sports ball
+kite
+baseball bat
+baseball glove
+skateboard
+surfboard
+tennis racket
+bottle
+wine glass
+cup
+fork
+knife
+spoon
+bowl
+banana
+apple
+sandwich
+orange
+broccoli
+carrot
+hot dog
+pizza
+donut
+cake
+chair
+sofa
+pottedplant
+bed
+diningtable
+toilet
+tvmonitor
+laptop
+mouse
+remote
+keyboard
+cell_phone
+microwave
+oven
+toaster
+sink
+refrigerator
+book
+clock
+vase
+scissors
+teddy bear
+hair drier
+toothbrush

original_app/scarecrow.py

@@ -0,0 +1,60 @@
+import cv2
+import numpy as np
+import socket
+import sys
+import pickle
+import struct
+import pygame
+
+# Initialize pygame mixer
+pygame.mixer.init()
+
+# Set up dictionary of label-sound pairs
+label_sound_dict = {
+    "person": "a.mp3",
+    "cell_phone": "b.mp3",
+}
+
+cap = cv2.VideoCapture(0)
+clientsocket = socket.socket(socket.AF_INET,socket.SOCK_STREAM)
+clientsocket.connect(('localhost',8089))
+
+# Initialize variables for label detection
+label_count = 0
+current_label = None
+
+while True:
+    ret, frame = cap.read()
+    # Serialize frame
+    data = pickle.dumps(frame)
+
+    # Send message length first
+    message_size = struct.pack("L", len(data)) ### CHANGED
+
+    # Then data
+    clientsocket.sendall(message_size + data)
+
+    # Receive response from server
+    response = clientsocket.recv(1024)
+    decoded_response = response.decode()
+    print(decoded_response)
+
+    # Check if response is a label we care about
+    if "[Scarecrow]: " in decoded_response:
+        label = decoded_response.split("[Scarecrow]: ")[1]
+        if label in label_sound_dict:
+            if label != current_label:
+                # Reset label count if new label detected
+                current_label = label
+                label_count = 1
+            else:
+                # Increment label count if same label detected
+                label_count += 1
+                if label_count >= 5: # play sound if label detected 5 times in a row
+                    sound_file = label_sound_dict[label]
+                    sound = pygame.mixer.Sound(sound_file)
+                    sound.play()
+                    label_count = 0
+        else:
+            current_label = None
+            label_count = 0