From bfe2a017d0168efef962225f755807535153fca4 Mon Sep 17 00:00:00 2001 From: Holger Caesar <39502217+holger-nutonomy@users.noreply.github.com> Date: Fri, 13 Nov 2020 07:59:17 +0800 Subject: [PATCH] Replace ratio with number (#497) Co-authored-by: Holger Caesar --- python-sdk/nuscenes/eval/tracking/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/python-sdk/nuscenes/eval/tracking/README.md b/python-sdk/nuscenes/eval/tracking/README.md index b0efd677..1cd9f496 100644 --- a/python-sdk/nuscenes/eval/tracking/README.md +++ b/python-sdk/nuscenes/eval/tracking/README.md @@ -231,8 +231,8 @@ Tracks with a score below the confidence threshold are discarded. * **MOTA** (multi object tracking accuracy) \[3\]: This measure combines three error sources: false positives, missed targets and identity switches. * **MOTP** (multi object tracking precision) \[3\]: The misalignment between the annotated and the predicted bounding boxes. * **FAF**: The average number of false alarms per frame. -* **MT** (ratio of mostly tracked trajectories): The ratio of ground-truth trajectories that are covered by a track hypothesis for at least 80% of their respective life span. -* **ML** (ratio of mostly lost trajectories): The ratio of ground-truth trajectories that are covered by a track hypothesis for at most 20% of their respective life span. +* **MT** (number of mostly tracked trajectories): The number of ground-truth trajectories that are covered by a track hypothesis for at least 80% of their respective life span. +* **ML** (number of mostly lost trajectories): The number of ground-truth trajectories that are covered by a track hypothesis for at most 20% of their respective life span. * **FP** (number of false positives): The total number of false positives. * **FN** (number of false negatives): The total number of false negatives (missed targets). * **IDS** (number of identity switches): The total number of identity switches.