diff --git a/deploy/pipeline/pipe_utils.py b/deploy/pipeline/pipe_utils.py
index d4a6307525bb903cc7f09331dbbdbaba5c707fd6..8cc863aa51c4e2df713fee181d9ea5c36257b50b 100644
--- a/deploy/pipeline/pipe_utils.py
+++ b/deploy/pipeline/pipe_utils.py
@@ -68,6 +68,7 @@ class PipeTimer(Times):
             'vehicleplate': Times()
         }
         self.img_num = 0
+        self.track_num = 0
 
     def get_total_time(self):
         total_time = self.total_time.value()
@@ -86,8 +87,11 @@ class PipeTimer(Times):
 
         for k, v in self.module_time.items():
             v_time = round(v.value(), 4)
-            if v_time > 0:
+            if v_time > 0 and k in ['det', 'mot', 'video_action']:
                 print("{} time(ms): {}".format(k, v_time * 1000))
+            elif v_time > 0:
+                print("{} time(ms): {}; per trackid average time(ms): {}".
+                      format(k, v_time * 1000, v_time * 1000 / self.track_num))
 
         print("average latency time(ms): {:.2f}, QPS: {:2f}".format(
             average_latency * 1000, qps))
diff --git a/deploy/pipeline/pipeline.py b/deploy/pipeline/pipeline.py
index 8cfb1dd132d706dbae72ff20f58c0ccea65ad12b..da2489682edd165d392a440e8660987b5fff2877 100644
--- a/deploy/pipeline/pipeline.py
+++ b/deploy/pipeline/pipeline.py
@@ -598,10 +598,11 @@ class PipePredictor(object):
             if not ret:
                 break
             frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+            if frame_id > self.warmup_frame:
+                self.pipe_timer.total_time.start()
 
             if self.modebase["idbased"] or self.modebase["skeletonbased"]:
                 if frame_id > self.warmup_frame:
-                    self.pipe_timer.total_time.start()
                     self.pipe_timer.module_time['mot'].start()
 
                 mot_skip_frame_num = self.mot_predictor.skip_frame_num
@@ -612,11 +613,12 @@ class PipePredictor(object):
                     [copy.deepcopy(frame_rgb)],
                     visual=False,
                     reuse_det_result=reuse_det_result)
-                if frame_id > self.warmup_frame:
-                    self.pipe_timer.module_time['mot'].end()
 
                 # mot output format: id, class, score, xmin, ymin, xmax, ymax
                 mot_res = parse_mot_res(res)
+                if frame_id > self.warmup_frame:
+                    self.pipe_timer.module_time['mot'].end()
+                    self.pipe_timer.track_num += len(mot_res['boxes'])
 
                 # flow_statistic only support single class MOT
                 boxes, scores, ids = res[0]  # batch size = 1 in MOT