New GOSPA and T-GOSPA quasi-metrics proposed for multi-object tracking evaluation

Researchers have introduced two new quasi-metrics, GOSPA and T-GOSPA, designed to evaluate the performance of multi-object tracking algorithms. These metrics extend existing GOSPA and T-GOSPA measures by allowing for flexible penalties on missed and false objects, and non-symmetric localization costs. The T-GOSPA quasi-metric additionally incorporates a cost for track switching. Simulations were conducted to assess various Bayesian MOT algorithms using the T-GOSPA quasi-metric. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Introduces new evaluation metrics for multi-object tracking, potentially improving algorithm development and comparison.

RANK_REASON This is a research paper introducing new evaluation metrics for multi-object tracking algorithms.

Read on arXiv cs.CV →

• GOSPA
• T-GOSPA
• arXiv
• Ángel F. García-Fernández

• paper
• other