Spaces:
Sleeping
Sleeping
practisebook
commited on
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
from ultralytics import YOLO
|
3 |
+
import cv2
|
4 |
+
import tempfile
|
5 |
+
import os
|
6 |
+
from gtts import gTTS
|
7 |
+
|
8 |
+
# Load YOLOv8 model
|
9 |
+
@st.cache_resource
|
10 |
+
def load_model():
|
11 |
+
return YOLO('yolov8n.pt') # Automatically downloads YOLOv8 pre-trained model
|
12 |
+
|
13 |
+
model = load_model()
|
14 |
+
|
15 |
+
# Streamlit app title
|
16 |
+
st.title("Object Detection in Video")
|
17 |
+
st.write("Upload a video, and the application will detect and label objects frame by frame, and generate a summary.")
|
18 |
+
|
19 |
+
# File uploader
|
20 |
+
uploaded_video = st.file_uploader("Upload a Video", type=["mp4", "avi", "mov"])
|
21 |
+
|
22 |
+
if uploaded_video:
|
23 |
+
# Save the uploaded video to a temporary file
|
24 |
+
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp4")
|
25 |
+
temp_file.write(uploaded_video.read())
|
26 |
+
video_path = temp_file.name
|
27 |
+
|
28 |
+
# Open the video file
|
29 |
+
video = cv2.VideoCapture(video_path)
|
30 |
+
frame_width = int(video.get(cv2.CAP_PROP_FRAME_WIDTH))
|
31 |
+
frame_height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
32 |
+
fps = int(video.get(cv2.CAP_PROP_FPS))
|
33 |
+
total_frames = int(video.get(cv2.CAP_PROP_FRAME_COUNT))
|
34 |
+
|
35 |
+
# Create an output video file
|
36 |
+
output_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp4")
|
37 |
+
fourcc = cv2.VideoWriter_fourcc(*"mp4v")
|
38 |
+
out = cv2.VideoWriter(output_file.name, fourcc, fps, (frame_width, frame_height))
|
39 |
+
|
40 |
+
# Initialize a set to collect unique detected objects
|
41 |
+
detected_objects = set()
|
42 |
+
|
43 |
+
# Process video frame by frame
|
44 |
+
st.write("Processing video...")
|
45 |
+
progress_bar = st.progress(0)
|
46 |
+
|
47 |
+
for i in range(total_frames):
|
48 |
+
ret, frame = video.read()
|
49 |
+
if not ret:
|
50 |
+
break
|
51 |
+
|
52 |
+
# Object detection on the current frame
|
53 |
+
results = model(frame)
|
54 |
+
|
55 |
+
# Collect unique object names
|
56 |
+
detected_objects.update([model.names[int(box.cls)] for box in results[0].boxes])
|
57 |
+
|
58 |
+
# Annotate frame with bounding boxes
|
59 |
+
annotated_frame = results[0].plot()
|
60 |
+
|
61 |
+
# Write annotated frame to the output video
|
62 |
+
out.write(annotated_frame)
|
63 |
+
|
64 |
+
# Update progress bar
|
65 |
+
progress_bar.progress((i + 1) / total_frames)
|
66 |
+
|
67 |
+
# Release resources
|
68 |
+
video.release()
|
69 |
+
out.release()
|
70 |
+
|
71 |
+
# Generate text summary
|
72 |
+
if detected_objects:
|
73 |
+
detected_objects_list = ", ".join(detected_objects)
|
74 |
+
summary_text = f"In this video, the following objects were detected: {detected_objects_list}."
|
75 |
+
else:
|
76 |
+
summary_text = "No objects were detected in the video."
|
77 |
+
|
78 |
+
st.write("Summary:")
|
79 |
+
st.write(summary_text)
|
80 |
+
|
81 |
+
# Generate audio summary using gTTS
|
82 |
+
tts = gTTS(text=summary_text, lang='en')
|
83 |
+
audio_file = os.path.join(tempfile.gettempdir(), "summary.mp3")
|
84 |
+
tts.save(audio_file)
|
85 |
+
|
86 |
+
# Display the output video
|
87 |
+
st.write("Video processing complete! Download or watch the labeled video below:")
|
88 |
+
st.video(output_file.name)
|
89 |
+
st.download_button(
|
90 |
+
label="Download Labeled Video",
|
91 |
+
data=open(output_file.name, "rb").read(),
|
92 |
+
file_name="labeled_video.mp4",
|
93 |
+
mime="video/mp4"
|
94 |
+
)
|
95 |
+
|
96 |
+
# Provide audio playback
|
97 |
+
st.audio(audio_file, format="audio/mp3")
|
98 |
+
st.download_button(
|
99 |
+
label="Download Audio Summary",
|
100 |
+
data=open(audio_file, "rb").read(),
|
101 |
+
file_name="summary.mp3",
|
102 |
+
mime="audio/mp3"
|
103 |
+
)
|