diff --git a/Dockerfile b/Dockerfile
index 51ef8f030..1cb9f697e 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -101,6 +101,8 @@ RUN ln -s /coco_labels.txt /label_map.pbtext
 RUN (apt-get autoremove -y; \
      apt-get autoclean -y)
 
+RUN  pip install -U matplotlib
+
 WORKDIR /opt/frigate/
 ADD frigate frigate/
 COPY detect_objects.py .
diff --git a/frigate/object_detection.py b/frigate/object_detection.py
index 9006f4179..55fef80a3 100644
--- a/frigate/object_detection.py
+++ b/frigate/object_detection.py
@@ -47,6 +47,7 @@ class PreppedQueueProcessor(threading.Thread):
                 box = obj.bounding_box.flatten().tolist()
                 parsed_objects.append({
                             'frame_time': frame['frame_time'],
+                            'label_id': obj.label_id,
                             'name': str(self.labels[obj.label_id]),
                             'score': float(obj.score),
                             'xmin': int((box[0] * frame['region_size']) + frame['region_x_offset']),
diff --git a/frigate/objects.py b/frigate/objects.py
index 5109713b6..84a4cde0f 100644
--- a/frigate/objects.py
+++ b/frigate/objects.py
@@ -81,8 +81,10 @@ class BestPersonFrame(threading.Thread):
             if not self.best_person is None and self.best_person['frame_time'] in recent_frames:
                 best_frame = recent_frames[self.best_person['frame_time']]
 
-                label = "{}: {}% {}".format(self.best_person['name'],int(self.best_person['score']*100),int(self.best_person['area']))
-                draw_box_with_label(best_frame, self.best_person['xmin'], self.best_person['ymin'], 
-                    self.best_person['xmax'], self.best_person['ymax'], label)
-                
+                draw_box_with_label(best_frame, self.best_person['xmin'], self.best_person['ymin'],
+                                    self.best_person['xmax'], self.best_person['ymax'],
+                                    self.best_person['name'], self.best_person['score'], self.best_person['area'],
+                                    (255, 0, 0)
+                                    )
+
                 self.best_frame = cv2.cvtColor(best_frame, cv2.COLOR_RGB2BGR)
diff --git a/frigate/util.py b/frigate/util.py
index c73939247..85c009bc9 100644
--- a/frigate/util.py
+++ b/frigate/util.py
@@ -5,11 +5,11 @@ import cv2
 def tonumpyarray(mp_arr):
     return np.frombuffer(mp_arr.get_obj(), dtype=np.uint8)
 
-def draw_box_with_label(frame, x_min, y_min, x_max, y_max, label):
-    color = (255,0,0)
-    cv2.rectangle(frame, (x_min, y_min), 
-        (x_max, y_max), 
-        color, 2)
+def draw_box_with_label(frame, x_min, y_min, x_max, y_max, name, score, area, color):
+    label = "{}: {}% {}".format(name, int(score * 100), int(area))
+    cv2.rectangle(frame, (x_min, y_min),
+        (x_max, y_max),
+        color, 1)
     font_scale = 0.5
     font = cv2.FONT_HERSHEY_SIMPLEX
     # get the width and height of the text box
diff --git a/frigate/video.py b/frigate/video.py
index c4891edcf..f8c4caba9 100644
--- a/frigate/video.py
+++ b/frigate/video.py
@@ -11,6 +11,7 @@ from . util import tonumpyarray, draw_box_with_label
 from . object_detection import FramePrepper
 from . objects import ObjectCleaner, BestPersonFrame
 from . mqtt import MqttObjectPublisher
+import matplotlib.pyplot as plt
 
 # Stores 2 seconds worth of frames when motion is detected so they can be used for other threads
 class FrameTracker(threading.Thread):
@@ -207,6 +208,7 @@ class Camera:
             self.mask = np.zeros((self.frame_shape[0], self.frame_shape[1], 1), np.uint8)
             self.mask[:] = 255
 
+        self.color_map = plt.cm.get_cmap('tab20', 100)
 
     def start_or_restart_capture(self):
         if not self.ffmpeg_process is None:
@@ -316,8 +318,9 @@ class Camera:
 
         # draw the bounding boxes on the screen
         for obj in detected_objects:
-            label = "{}: {}% {}".format(obj['name'],int(obj['score']*100),int(obj['area']))
-            draw_box_with_label(frame, obj['xmin'], obj['ymin'], obj['xmax'], obj['ymax'], label)
+            color = tuple(int(round(255 * c)) for c in self.color_map(obj['label_id'])[:3])
+            draw_box_with_label(frame, obj['xmin'], obj['ymin'], obj['xmax'], obj['ymax'],
+                                obj['name'], obj['score'], obj['area'], color)
 
         for region in self.regions:
             color = (255,255,255)