readme

README.md

@@ -28,8 +28,8 @@ title: mot-metrics
 >>>         sequence_list=["Sentry_2022_11_PROACT_CELADON_7.5M_MOB_2022_11_25_12_12_39"],
 >>>         tracking_mode=True
 >>>    )
->>> module = evaluate.load("SEA-AI/mot-metrics")
->>> res = module._calculate(b, max_iou=0.99)
+>>> module = evaluate.load("SEA-AI/user-friendly-metrics")
+>>> res = module._calculate(b, max_iou=0.99, recognition_thresholds=[0.3, 0.5, 0.8])
 >>> print(res)
 {'Sentry_2022_11_PROACT_CELADON_7.5M_MOB_2022_11_25_12_12_39': {'volcanic-sweep-3_02_2023_N_LN1_ep288_TRACKER': {'idf1': 0.9543031226199543,
    'idp': 0.9804381846635368,
@@ -48,7 +48,10 @@ title: mot-metrics
    'motp': 0.5235835810268012,
    'num_transfer': 0,
    'num_ascend': 1,
-   'num_migrate': 0}}}
+   'num_migrate': 0,
+   'recognition_0.3': 0.9230769230769231, 
+   'recognition_0.5': 0.8461538461538461, 
+   'recognition_0.8': 0.46153846153846156}}}
 ```
 
 ## Metric Settings
@@ -76,6 +79,7 @@ The output is a dictionary containing the following metrics:
 | num_fragmentations   | Total number of switches from tracked to not tracked.                              |
 | mota                 | Multiple object tracker accuracy.                                                  |
 | motp                 | Multiple object tracker precision.                                                 |
+| recognition_0.3      | Recognition rate for a threshold of 0.3                                            |
 
 ## Citations