simple

accident_detection_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccdddd973f939e2b158f4fd0bbba3f57cb993ed50273e86767176419faf808d6
+size 27672816

app.py

@@ -0,0 +1,55 @@
+import streamlit as st
+from PIL import Image
+import numpy as np
+from tensorflow.keras.models import load_model
+import cv2
+
+# Load the saved model
+loaded_model = load_model("accident_detection_model.h5")
+st.title("Accident Detection")
+
+# Checkbox to enable camera input
+camera_checkbox = st.checkbox("Use Camera")
+
+if camera_checkbox:
+    
+
+    image = st.camera_input("Take Photo")
+
+    if(st.button("Capture")):
+
+    # Preprocess the image
+        image = Image.open(image)
+        img_array = np.array(image.resize((150, 150)))
+        img_array = img_array / 255.0
+        img_array = np.expand_dims(img_array, axis=0)
+
+        # Classify the image
+        prediction = loaded_model.predict(img_array)
+        if prediction[0] > 0.5:
+            st.write("Prediction: Accident")
+        else:
+            st.write("Prediction: Non-Accident")
+
+
+else:
+    # Upload image
+    uploaded_file = st.file_uploader("Choose an image...", type="jpg")
+
+    if uploaded_file is not None:
+        image = Image.open(uploaded_file)
+        st.image(image, caption='Uploaded Image.', use_column_width=True)
+        st.write("")
+        st.write("Classifying...")
+
+        # Preprocess the image
+        img_array = np.array(image.resize((150, 150)))
+        img_array = img_array / 255.0
+        img_array = np.expand_dims(img_array, axis=0)
+
+        # Classify the image
+        prediction = loaded_model.predict(img_array)
+        if prediction[0] > 0.5:
+            st.write("Prediction: Accident")
+        else:
+            st.write("Prediction: Non-Accident")