app.py

import gradio as gr
import cv2
import requests
import os
import torch 
import numpy as np
from ultralytics import YOLO

model = torch.hub.load('ultralytics/yolov5', 'yolov5x', pretrained=True)
path  = [['image_0.jpg'], ['image_1.jpg']]
video_path = [['TresPass_Detection_1.mp4']]
# area =  [(215, 180), (120, 75), (370, 55), (520, 140), (215, 180) ]
area =  [(215, 180), (110, 75), (370, 55), (520, 140), (215, 180) ]

# def show_preds_video(video_path):
def show_preds_video():
    cap = cv2.VideoCapture('TresPass_Detection_1.mp4')
    count=0
    while(cap.isOpened()):
        ret, frame = cap.read()
        if not ret:
            break
        count += 1
        if count % 10 != 0:
            continue
            # frame = cv2.imread(video_path)
        frame=cv2.resize(frame,(1020,600))
        frame_copy = frame.copy()
        frame=cv2.resize(frame,(1020,600))

        results=model(frame)
        for index, row in results.pandas().xyxy[0].iterrows():
            x1 = int(row['xmin'])
            y1 = int(row['ymin'])
            x2 = int(row['xmax'])
            y2 = int(row['ymax'])
            d=(row['name'])

            cx=int(x1+x2)//2
            cy=int(y1+y2)//2

            if ('person') in d:
                results = cv2.pointPolygonTest(np.array(area, np.int32), ((cx,cy)), False)
                if results >0:
                        cv2.rectangle(frame_copy,(x1,y1),(x2,y2),(0,0,255),2)
                        cv2.putText(frame_copy,str(d),(x1,y1),cv2.FONT_HERSHEY_SIMPLEX,1,(0,0,255),1)
                        cv2.putText(frame_copy,str("Alert !!! Trespasser detected !!!"),(50,400),cv2.FONT_HERSHEY_PLAIN,2,(0,0,255),3)

        cv2.polylines(frame_copy, [np.array(area, np.int32)], True, (0,255,0), 2) 

        yield cv2.cvtColor(frame_copy, cv2.COLOR_BGR2RGB)

inputs_video = [  #gr.components.Video(type="filepath", label="Input Video", visible =False), 
               ]

outputs_video = [
    gr.components.Image(type="numpy", label="Output Image"),
]

interface_video = gr.Interface(
    fn=show_preds_video,
    inputs=inputs_video,
    outputs=outputs_video,
    title="Intrusion Detection",
    examples=video_path,
    cache_examples=False,
)

gr.TabbedInterface(
    [interface_video],
    # [interface_image, interface_video],
    tab_names=['Video inference']
).queue().launch(width=200, height = 200)


# def show_preds_image(image_path):
#     frame = cv2.imread(image_path)
#     frame=cv2.resize(frame,(1020,600))
#     results=model(frame)
#     for index, row in results.pandas().xyxy[0].iterrows():
#         x1 = int(row['xmin'])
#         y1 = int(row['ymin'])
#         x2 = int(row['xmax'])
#         y2 = int(row['ymax'])
#         d=(row['name'])

#         cx=int(x1+x2)//2
#         cy=int(y1+y2)//2

#         if ('person') in d:
#            results = cv2.pointPolygonTest(np.array(area, np.int32), ((cx,cy)), False)
#            if results >0:
#                 cv2.rectangle(frame,(x1,y1),(x2,y2),(0,0,255),2)
#                 cv2.putText(frame,str(d),(x1,y1),cv2.FONT_HERSHEY_PLAIN,1,(255,0,0),2)

#     cv2.polylines(frame, [np.array(area, np.int32)], True, (0,255,0), 2) 
#     return cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)

# inputs_image = [
#     gr.components.Image(type="filepath", label="Input Image"),
# ]
# outputs_image = [
#     gr.components.Image(type="numpy", label="Output Image"),
# ]
# interface_image = gr.Interface(
#     fn=show_preds_image,
#     inputs=inputs_image,
#     outputs=outputs_image,
#     title="Parking space counter",
#     examples=path,
#     cache_examples=False,
# )