Measures for ranking cell trackers without manual validation
作者：
Highlights：
• We develop measures for assessing cell tracking quality without manual validation.
• Information available without manual validation includes distances between cells.
• We use the distances to estimate the precision and recall of the cell tracker.
• We evaluate our measures under a variety of cell tracking conditions.
• In practical scenarios, our performance measures correlate with traditional measures.
摘要
Highlights•We develop measures for assessing cell tracking quality without manual validation.•Information available without manual validation includes distances between cells.•We use the distances to estimate the precision and recall of the cell tracker.•We evaluate our measures under a variety of cell tracking conditions.•In practical scenarios, our performance measures correlate with traditional measures.
论文关键词：Cell tracking,Data association,Tracking quality,Performance measures,Tracker selection,Bayes theorem
论文评审过程：Received 5 July 2012, Revised 11 February 2013, Accepted 10 April 2013, Available online 18 April 2013.
论文官网地址：https://doi.org/10.1016/j.patcog.2013.04.007
