import time
import tkinter as tk
import settings
from PIL import Image, ImageTk
import imutils
from pydarknet import Detector, Image
import cv2

def start_video():
    settings.start_video = True
    show_frame()

def stop_video():
    settings.start_video = False
    settings.start_processing = False
    lmain.config(image='')

def start_process():
    settings.start_processing = True

def stop_process():
    settings.start_processing = False

def show_frame():
    if not settings.start_video:
        return None

    _, frame = cap.read()
    frame = imutils.resize(frame, width=400)

    if settings.start_processing:
        frame = process_frame(frame)

    cv2image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
    img = Image.fromarray(cv2image)
    imgtk = ImageTk.PhotoImage(image=cv2image)
    lmain.imgtk = imgtk
    lmain.configure(image=imgtk)
    lmain.after(10, show_frame)

def process_frame(img):
    # grab the frame dimensions and convert it to a blob
    (h, w) = img.shape[:2]
    blob = cv2.dnn.blobFromImage(cv2.resize(img, (300, 300)),
                                 0.007843, (300, 300), 127.5)

    # pass the blob through the network and obtain the detections and
    # predictions
    #net.setInput(blob)
    #detections = net.forward()

    start_time = time.time()

    # Only measure the time taken by YOLO and API Call overhead

    dark_frame = Image(img)
    results = net.detect(dark_frame)
    del dark_frame

    end_time = time.time()
    print("Elapsed Time:",end_time-start_time)

    for cat, score, bounds in results:
        x, y, w, h = bounds
        cv2.rectangle(img, (int(x-w/2),int(y-h/2)),(int(x+w/2),int(y+h/2)),(255,0,0))
        cv2.putText(img, str(cat.decode("utf-8")), (int(x), int(y)), cv2.FONT_HERSHEY_COMPLEX, 1, (255, 255, 0))

    #cv2.imshow("preview", frame)

# load our serialized model from disk
print("Loading model...")
net = Detector(bytes("cfg/yolov3.cfg", encoding="utf-8"), bytes("weights/yolov3.weights", encoding="utf-8"), 0,
                   bytes("cfg/coco.data", encoding="utf-8"))
cap = cv2.VideoCapture(0)

window = tk.Tk()
window.title("DEMO")
window.geometry('700x420')
lbl = tk.Label(window, text="Smart Machine Vision System", font=("Arial Bold", 24))
lbl.grid(column=1, row=0)
imageFrame = tk.Frame(window, width=600, height=500)
imageFrame.grid(row=1, column=1, padx=10, pady=2)
lmain = tk.Label(imageFrame, text="Press Start Video")
lmain.grid(row=1, column=1)
startVideoStreamBtn = tk.Button(window, text="Start Video", command=start_video)
startVideoStreamBtn.grid(column=0, row=2, padx=15)
stopVideoStreamBtn = tk.Button(window, text="Stop Video", command=stop_video)
stopVideoStreamBtn.grid(column=0, row=3, padx=15)
startProcessBtn = tk.Button(window, text="Start Detection", command=start_process)
startProcessBtn.grid(column=1, row=2)
stopProcessBtn = tk.Button(window, text="Stop Detection", command=stop_process)
stopProcessBtn.grid(column=1, row=3)
window.mainloop()