Update app.py

app.py

@@ -5,6 +5,18 @@ import onnxruntime as ort
 from PIL import Image
 import tempfile
 
+# Class labels for both vehicles and license plates
+CLASSES = {
+    0: "Vehicle",
+    1: "License_Plate"
+}
+
+# Different colors for each class
+COLORS = {
+    0: (255, 0, 0),  # Red for vehicles
+    1: (0, 255, 0)   # Green for license plates
+}
+
 # Load the ONNX model
 @st.cache_resource
 def load_model():
@@ -13,25 +25,18 @@ def load_model():
 ort_session = load_model()
 
 def preprocess_image(image, target_size=(640, 640)):
-    # Convert PIL Image to numpy array if necessary
     if isinstance(image, Image.Image):
         image = np.array(image)
     
-    # Convert RGB to BGR
     image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
-    
-    # Resize image
+    original_shape = image.shape[:2]
     image = cv2.resize(image, target_size)
-    # Normalize
     image = image.astype(np.float32) / 255.0
-    # Transpose for ONNX input
     image = np.transpose(image, (2, 0, 1))
-    # Add batch dimension
     image = np.expand_dims(image, axis=0)
-    return image
+    return image, original_shape
 
-def postprocess_results(output, image_shape, confidence_threshold=0.25, iou_threshold=0.45):
-    # Handle different possible output formats
+def postprocess_results(output, original_shape, confidence_threshold=0.25, iou_threshold=0.45):
     if isinstance(output, (list, tuple)):
         predictions = output[0]
     elif isinstance(output, np.ndarray):
@@ -39,7 +44,6 @@ def postprocess_results(output, image_shape, confidence_threshold=0.25, iou_thre
     else:
         raise ValueError(f"Unexpected output type: {type(output)}")
 
-    # Reshape if necessary
     if len(predictions.shape) == 4:
         predictions = predictions.squeeze((0, 1))
     elif len(predictions.shape) == 3:
@@ -59,52 +63,93 @@ def postprocess_results(output, image_shape, confidence_threshold=0.25, iou_thre
     # Convert boxes from [x, y, w, h] to [x1, y1, x2, y2]
     boxes[:, 2:] += boxes[:, :2]
 
-    # Scale boxes to image size
-    boxes[:, [0, 2]] *= image_shape[1]
-    boxes[:, [1, 3]] *= image_shape[0]
-
-    # Apply NMS
-    indices = cv2.dnn.NMSBoxes(boxes.tolist(), scores.tolist(), confidence_threshold, iou_threshold)
+    # Scale boxes to original image size
+    h, w = original_shape
+    boxes[:, [0, 2]] *= w
+    boxes[:, [1, 3]] *= h
 
+    # Apply NMS for each class separately
     results = []
-    for i in indices:
-        box = boxes[i]
-        score = scores[i]
-        class_id = class_ids[i]
-        x1, y1, x2, y2 = map(int, box)
-        results.append((x1, y1, x2, y2, float(score), int(class_id)))
+    for class_id in np.unique(class_ids):
+        class_mask = class_ids == class_id
+        class_boxes = boxes[class_mask]
+        class_scores = scores[class_mask]
+        
+        indices = cv2.dnn.NMSBoxes(
+            class_boxes.tolist(), 
+            class_scores.tolist(), 
+            confidence_threshold, 
+            iou_threshold
+        )
+
+        for i in indices:
+            box = class_boxes[i]
+            score = class_scores[i]
+            x1, y1, x2, y2 = map(int, box)
+            results.append((x1, y1, x2, y2, float(score), int(class_id)))
 
     return results
 
 def process_image(image):
     orig_image = image.copy()
-    processed_image = preprocess_image(image)
+    processed_image, original_shape = preprocess_image(image)
     
     # Run inference
     inputs = {ort_session.get_inputs()[0].name: processed_image}
     outputs = ort_session.run(None, inputs)
     
-    results = postprocess_results(outputs, image.shape)
+    results = postprocess_results(outputs, original_shape)
     
     # Draw bounding boxes on the image
     for x1, y1, x2, y2, score, class_id in results:
-        cv2.rectangle(orig_image, (x1, y1), (x2, y2), (0, 255, 0), 2)
-        label = f"License Plate: {score:.2f}"
-        cv2.putText(orig_image, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)
+        color = COLORS[class_id]
+        cv2.rectangle(orig_image, (x1, y1), (x2, y2), color, 2)
+        
+        label = f"{CLASSES[class_id]}: {score:.2f}"
+        # Calculate text size for better positioning
+        (text_width, text_height), _ = cv2.getTextSize(
+            label, cv2.FONT_HERSHEY_SIMPLEX, 0.9, 2
+        )
+        # Draw background rectangle for text
+        cv2.rectangle(
+            orig_image, 
+            (x1, y1 - text_height - 10), 
+            (x1 + text_width, y1), 
+            color, 
+            -1
+        )
+        # Draw text
+        cv2.putText(
+            orig_image,
+            label,
+            (x1, y1 - 5),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.9,
+            (255, 255, 255),
+            2
+        )
     
     return cv2.cvtColor(orig_image, cv2.COLOR_BGR2RGB)
 
 def process_video(video_path):
     cap = cv2.VideoCapture(video_path)
     
-    # Get video properties
     width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
     height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
     fps = int(cap.get(cv2.CAP_PROP_FPS))
     
-    # Create a temporary file to store the processed video
     temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.mp4')
-    out = cv2.VideoWriter(temp_file.name, cv2.VideoWriter_fourcc(*'mp4v'), fps, (width, height))
+    out = cv2.VideoWriter(
+        temp_file.name,
+        cv2.VideoWriter_fourcc(*'mp4v'),
+        fps,
+        (width, height)
+    )
+    
+    # Add progress bar for video processing
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+    progress_bar = st.progress(0)
+    frame_count = 0
     
     while cap.isOpened():
         ret, frame = cap.read()
@@ -113,15 +158,33 @@ def process_video(video_path):
         
         processed_frame = process_image(frame)
         out.write(cv2.cvtColor(processed_frame, cv2.COLOR_RGB2BGR))
+        
+        # Update progress bar
+        frame_count += 1
+        progress_bar.progress(frame_count / total_frames)
     
     cap.release()
     out.release()
+    progress_bar.empty()
     
     return temp_file.name
 
-st.title("License Plate Detection")
+# Streamlit UI
+st.title("Vehicle and License Plate Detection")
 
-uploaded_file = st.file_uploader("Choose an image or video file", type=["jpg", "jpeg", "png", "mp4"])
+# Add confidence threshold slider
+confidence_threshold = st.slider(
+    "Confidence Threshold",
+    min_value=0.0,
+    max_value=1.0,
+    value=0.25,
+    step=0.05
+)
+
+uploaded_file = st.file_uploader(
+    "Choose an image or video file",
+    type=["jpg", "jpeg", "png", "mp4"]
+)
 
 if uploaded_file is not None:
     file_type = uploaded_file.type.split('/')[0]
@@ -130,9 +193,10 @@ if uploaded_file is not None:
         image = Image.open(uploaded_file)
         st.image(image, caption="Uploaded Image", use_column_width=True)
         
-        if st.button("Detect License Plates"):
-            processed_image = process_image(np.array(image))
-            st.image(processed_image, caption="Processed Image", use_column_width=True)
+        if st.button("Detect Objects"):
+            with st.spinner("Processing image..."):
+                processed_image = process_image(np.array(image))
+                st.image(processed_image, caption="Processed Image", use_column_width=True)
     
     elif file_type == "video":
         tfile = tempfile.NamedTemporaryFile(delete=False)
@@ -140,8 +204,20 @@ if uploaded_file is not None:
         
         st.video(tfile.name)
         
-        if st.button("Detect License Plates"):
-            processed_video = process_video(tfile.name)
-            st.video(processed_video)
-
-st.write("Upload an image or video to detect license plates.")
+        if st.button("Detect Objects"):
+            with st.spinner("Processing video..."):
+                processed_video = process_video(tfile.name)
+                st.video(processed_video)
+
+# Add legend
+st.markdown("### Detection Legend")
+for class_id, class_name in CLASSES.items():
+    color = COLORS[class_id]
+    st.markdown(
+        f'<div style="display: flex; align-items: center;">'
+        f'<div style="width: 20px; height: 20px; background-color: rgb{color}; margin-right: 10px;"></div>'
+        f'<span>{class_name}</span></div>',
+        unsafe_allow_html=True
+    )
+
+st.write("Upload an image or video to detect vehicles and license plates.")