diff --git a/deploy/python/infer.py b/deploy/python/infer.py
index 33f29a7b74bbdbcfb8b3ee0feb5cb59db78ba8f6..99d3b3f44d1eafd8a6560aa5c85c6531d6cdb649 100644
--- a/deploy/python/infer.py
+++ b/deploy/python/infer.py
@@ -71,10 +71,11 @@ class Detector(object):
     def preprocess(self, im):
         preprocess_ops = []
         for op_info in self.config.preprocess_infos:
-            op_type = op_info.pop('type')
+            new_op_info = op_info.copy()
+            op_type = new_op_info.pop('type')
             if op_type == 'Resize':
-                op_info['arch'] = self.config.arch
-            preprocess_ops.append(eval(op_type)(**op_info))
+                new_op_info['arch'] = self.config.arch
+            preprocess_ops.append(eval(op_type)(**new_op_info))
         im, im_info = preprocess(im, preprocess_ops)
         inputs = create_inputs(im, im_info, self.config.arch)
         return inputs, im_info
@@ -481,7 +482,8 @@ def predict_video(detector, camera_id):
             frame,
             results,
             detector.config.labels,
-            mask_resolution=detector.config.mask_resolution)
+            mask_resolution=detector.config.mask_resolution,
+            threshold=FLAGS.threshold)
         im = np.array(im)
         writer.write(im)
         if camera_id != -1:
diff --git a/deploy/python/visualize.py b/deploy/python/visualize.py
index b58a36926657f3246c10f3009952c9481fa3bc72..1c136be4dde9c97c01649b1dab62135eed8062d8 100644
--- a/deploy/python/visualize.py
+++ b/deploy/python/visualize.py
@@ -228,9 +228,22 @@ def draw_segm(im,
         color_mask = np.array(color_mask)
         im[idx[0], idx[1], :] *= 1.0 - alpha
         im[idx[0], idx[1], :] += alpha * color_mask
-        center_y, center_x = ndimage.measurements.center_of_mass(mask)
-        label_text = "{}".format(labels[clsid])
-        vis_pos = (max(int(center_x) - 10, 0), int(center_y))
-        cv2.putText(im, label_text, vis_pos, cv2.FONT_HERSHEY_COMPLEX, 0.3,
-                    (255, 255, 255))
+        sum_x = np.sum(mask, axis=0)
+        x = np.where(sum_x > 0.5)[0]
+        sum_y = np.sum(mask, axis=1)
+        y = np.where(sum_y > 0.5)[0]
+        x0, x1, y0, y1 = x[0], x[-1], y[0], y[-1]
+        cv2.rectangle(im, (x0, y0), (x1, y1),
+                      tuple(color_mask.astype('int32').tolist()), 1)
+        bbox_text = '%s %.2f' % (labels[clsid], score)
+        t_size = cv2.getTextSize(bbox_text, 0, 0.3, thickness=1)[0]
+        cv2.rectangle(im, (x0, y0), (x0 + t_size[0], y0 - t_size[1] - 3),
+                      tuple(color_mask.astype('int32').tolist()), -1)
+        cv2.putText(
+            im,
+            bbox_text, (x0, y0 - 2),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.3, (0, 0, 0),
+            1,
+            lineType=cv2.LINE_AA)
     return Image.fromarray(im.astype('uint8'))