Update app.py

app.py

@@ -5,17 +5,12 @@ import streamlit as st
 import PIL
 from ultralytics import YOLO
 
-# Required libraries (ensure these are in your requirements.txt):
-# streamlit
-# opencv-python-headless
-# ultralytics
-# Pillow
+# Required libraries: streamlit, opencv-python-headless, ultralytics, Pillow
 
-# Replace with your model's URL or local path
-model_path = 'https://huggingface.co/spaces/tstone87/ccr-colorado/resolve/main/best.pt'  # Your correct model
+# Replace with your model URL or local file path
+model_path = 'https://huggingface.co/spaces/tstone87/ccr-colorado/resolve/main/best.pt'
 
-
-# Configure the page for Hugging Face Spaces
+# Configure page layout for Hugging Face Spaces
 st.set_page_config(
     page_title="Fire Watch using AI vision models",
     page_icon="🔥",
@@ -23,19 +18,23 @@ st.set_page_config(
     initial_sidebar_state="expanded"
 )
 
-# Sidebar for file upload and settings
+# Sidebar: Upload file, select confidence and video shortening options.
 with st.sidebar:
     st.header("IMAGE/VIDEO UPLOAD")
     source_file = st.file_uploader(
         "Choose an image or video...", type=("jpg", "jpeg", "png", "bmp", "webp", "mp4"))
-    confidence = float(st.slider("Select Model Confidence", 20, 100, 30)) / 100
+    confidence = float(st.slider("Select Model Confidence", 25, 100, 40)) / 100
     video_option = st.selectbox(
         "Select Video Shortening Option", 
         ["Original FPS", "1 fps", "1 frame per 5 seconds", "1 frame per 10 seconds", "1 frame per 15 seconds"]
     )
+    progress_text = st.empty()
+    progress_bar = st.progress(0)
+    # A container for our frame slider (viewer)
+    slider_container = st.empty()
 
-# Main page header and introduction images
-st.title("Fire Watch: Detecting fire or smoke using AI vision models")
+# Main page header and intro images
+st.title("WildfireWatch: Detecting Wildfire using AI")
 col1, col2 = st.columns(2)
 with col1:
     st.image("https://huggingface.co/spaces/tstone87/ccr-colorado/resolve/main/Fire_1.jpeg", use_column_width=True)
@@ -43,11 +42,12 @@ with col2:
     st.image("https://huggingface.co/spaces/tstone87/ccr-colorado/resolve/main/Fire_3.png", use_column_width=True)
 
 st.markdown("""
-Fires in Colorado present a serious challenge, threatening urban communities, highways, and even remote, unpopulated areas. Unexpected ncidents like lightning strike brushes fires can cause significant property damage, environmental degradation, and even loss of life. Early detection is critical to mitigating these risks. The idea for, Fire Watch, leverages a vision model called YOLOv8 for real-time detection of fires and smoke in images and videos, ensuring rapid response across Colorado’s diverse landscapes.
+Fires in Colorado present a serious challenge, threatening urban communities, highways, and even remote areas. Early detection is critical. WildfireWatch leverages YOLOv8 for real‐time fire and smoke detection in images and videos.
 """)
 st.markdown("---")
 st.header("Fire Detection:")
 
+# Create two columns for displaying the upload and results.
 col1, col2 = st.columns(2)
 if source_file:
     if source_file.type.split('/')[0] == 'image':
@@ -60,18 +60,26 @@ if source_file:
 else:
     st.info("Please upload an image or video file to begin.")
 
-# Load the YOLO model
+# Load YOLO model
 try:
     model = YOLO(model_path)
 except Exception as ex:
     st.error(f"Unable to load model. Check the specified path: {model_path}")
     st.error(ex)
 
-if st.sidebar.button("Let's Detect fire"):
+# Initialize session state for frame viewer if not already set
+if 'viewer_frame' not in st.session_state:
+    st.session_state.viewer_frame = 0
+
+# This container will display the currently viewed frame
+viewer_slot = st.empty()
+
+# When the user clicks the detect button...
+if st.sidebar.button("Let's Detect Wildfire"):
     if not source_file:
         st.warning("No file uploaded!")
     elif source_file.type.split('/')[0] == 'image':
-        # Process image input
+        # Process image input.
         res = model.predict(uploaded_image, conf=confidence)
         boxes = res[0].boxes
         res_plotted = res[0].plot()[:, :, ::-1]
@@ -81,18 +89,19 @@ if st.sidebar.button("Let's Detect fire"):
                 for box in boxes:
                     st.write(box.xywh)
     else:
-        # Process video input and shorten video based on sampling option
+        # Process video input.
         processed_frames = []
         frame_count = 0
 
-        # Video properties
+        # Get video properties.
         orig_fps = vidcap.get(cv2.CAP_PROP_FPS)
+        total_frames = int(vidcap.get(cv2.CAP_PROP_FRAME_COUNT))
         width  = int(vidcap.get(cv2.CAP_PROP_FRAME_WIDTH))
         height = int(vidcap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-        
-        # Determine sampling interval and output fps
+
+        # Determine sampling interval and output fps based on option selected.
         if video_option == "Original FPS":
-            sample_interval = 1  # process every frame
+            sample_interval = 1
             output_fps = orig_fps
         elif video_option == "1 fps":
             sample_interval = int(orig_fps) if orig_fps > 0 else 1
@@ -110,20 +119,47 @@ if st.sidebar.button("Let's Detect fire"):
             sample_interval = 1
             output_fps = orig_fps
 
+        # Initial slider for frame viewing.
+        slider_val = st.session_state.viewer_frame
+        slider = slider_container.slider("Frame Viewer", min_value=0, max_value=0, value=slider_val, step=1, key="frame_slider")
+
         success, image = vidcap.read()
         while success:
             if frame_count % sample_interval == 0:
+                # Run detection on current frame.
                 res = model.predict(image, conf=confidence)
                 res_plotted = res[0].plot()[:, :, ::-1]
                 processed_frames.append(res_plotted)
-                with col2:
-                    st.image(res_plotted, caption=f'Detected Frame {frame_count}', use_column_width=True)
-                    with st.expander("Detection Results"):
-                        for box in res[0].boxes:
-                            st.write(box.xywh)
+
+                # Update progress.
+                if total_frames > 0:
+                    progress_pct = int((frame_count / total_frames) * 100)
+                    progress_text.text(f"Processing frame {frame_count} / {total_frames} ({progress_pct}%)")
+                    progress_bar.progress(min(100, progress_pct))
+                else:
+                    progress_text.text(f"Processing frame {frame_count}")
+
+                # Update the slider's max value. Preserve current value.
+                current_index = st.session_state.get("frame_slider", len(processed_frames) - 1)
+                slider = slider_container.slider("Frame Viewer", 
+                                                   min_value=0, 
+                                                   max_value=len(processed_frames)-1, 
+                                                   value=current_index, 
+                                                   step=1, 
+                                                   key="frame_slider")
+
+                # If the user is at the latest frame, update the viewer.
+                if st.session_state.frame_slider == len(processed_frames)-1:
+                    viewer_slot.image(processed_frames[-1], caption=f"Frame {len(processed_frames)-1}", use_column_width=True)
+
             frame_count += 1
             success, image = vidcap.read()
-        
+
+        # Video processing complete.
+        progress_text.text("Video processing complete!")
+        progress_bar.progress(100)
+
+        # After processing, allow downloading the shortened video.
         if processed_frames:
             temp_video_file = tempfile.NamedTemporaryFile(delete=False, suffix='.mp4')
             fourcc = cv2.VideoWriter_fourcc(*'mp4v')