Create app.py

app.py

@@ -0,0 +1,103 @@
+import streamlit as st
+from ultralytics import YOLO
+import cv2
+import tempfile
+import os
+from gtts import gTTS
+
+# Load YOLOv8 model
+@st.cache_resource
+def load_model():
+    return YOLO('yolov8n.pt')  # Automatically downloads YOLOv8 pre-trained model
+
+model = load_model()
+
+# Streamlit app title
+st.title("Object Detection in Video")
+st.write("Upload a video, and the application will detect and label objects frame by frame, and generate a summary.")
+
+# File uploader
+uploaded_video = st.file_uploader("Upload a Video", type=["mp4", "avi", "mov"])
+
+if uploaded_video:
+    # Save the uploaded video to a temporary file
+    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp4")
+    temp_file.write(uploaded_video.read())
+    video_path = temp_file.name
+
+    # Open the video file
+    video = cv2.VideoCapture(video_path)
+    frame_width = int(video.get(cv2.CAP_PROP_FRAME_WIDTH))
+    frame_height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    fps = int(video.get(cv2.CAP_PROP_FPS))
+    total_frames = int(video.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    # Create an output video file
+    output_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp4")
+    fourcc = cv2.VideoWriter_fourcc(*"mp4v")
+    out = cv2.VideoWriter(output_file.name, fourcc, fps, (frame_width, frame_height))
+
+    # Initialize a set to collect unique detected objects
+    detected_objects = set()
+
+    # Process video frame by frame
+    st.write("Processing video...")
+    progress_bar = st.progress(0)
+
+    for i in range(total_frames):
+        ret, frame = video.read()
+        if not ret:
+            break
+
+        # Object detection on the current frame
+        results = model(frame)
+
+        # Collect unique object names
+        detected_objects.update([model.names[int(box.cls)] for box in results[0].boxes])
+
+        # Annotate frame with bounding boxes
+        annotated_frame = results[0].plot()
+
+        # Write annotated frame to the output video
+        out.write(annotated_frame)
+
+        # Update progress bar
+        progress_bar.progress((i + 1) / total_frames)
+
+    # Release resources
+    video.release()
+    out.release()
+
+    # Generate text summary
+    if detected_objects:
+        detected_objects_list = ", ".join(detected_objects)
+        summary_text = f"In this video, the following objects were detected: {detected_objects_list}."
+    else:
+        summary_text = "No objects were detected in the video."
+
+    st.write("Summary:")
+    st.write(summary_text)
+
+    # Generate audio summary using gTTS
+    tts = gTTS(text=summary_text, lang='en')
+    audio_file = os.path.join(tempfile.gettempdir(), "summary.mp3")
+    tts.save(audio_file)
+
+    # Display the output video
+    st.write("Video processing complete! Download or watch the labeled video below:")
+    st.video(output_file.name)
+    st.download_button(
+        label="Download Labeled Video",
+        data=open(output_file.name, "rb").read(),
+        file_name="labeled_video.mp4",
+        mime="video/mp4"
+    )
+
+    # Provide audio playback
+    st.audio(audio_file, format="audio/mp3")
+    st.download_button(
+        label="Download Audio Summary",
+        data=open(audio_file, "rb").read(),
+        file_name="summary.mp3",
+        mime="audio/mp3"
+    )