A Metric for Performance Evaluation of Multi-Target Tracking Algorithms
Performance evaluation of multi-target tracking algorithms is of great practical importance in the design, parameter optimization and comparison of tracking systems. The goal of performance evaluation is to measure the distance between two sets of tracks: the ground truth tracks and the set of estim...
| Main Authors: | , , , |
|---|---|
| Format: | Journal Article |
| Published: |
I E E E
2011
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.11937/30433 |
| _version_ | 1848753087900024832 |
|---|---|
| author | Ristic, B. Vo, Ba-Ngu Clark, D. Vo, Ba Tuong |
| author_facet | Ristic, B. Vo, Ba-Ngu Clark, D. Vo, Ba Tuong |
| author_sort | Ristic, B. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | Performance evaluation of multi-target tracking algorithms is of great practical importance in the design, parameter optimization and comparison of tracking systems. The goal of performance evaluation is to measure the distance between two sets of tracks: the ground truth tracks and the set of estimated tracks. This paper proposes a mathematically rigorous metric for this purpose. The basis of the proposed distance measure is the recently formulated consistent metric for performance evaluation of multi-target filters, referred to as the OSPA metric. Multi-target filters sequentially estimate the number of targets and their position in the state space. The OSPA metric is therefore defined on the space of finite sets of vectors. The distinction between filtering and tracking is that tracking algorithms output tracks and a track represents a labeled temporal sequence of state estimates, associated with the same target. The metric proposed in this paper is therefore defined on the space of finite sets of tracks and incorporates the labeling error. Numerical examples demonstrate that the proposed metric behaves in a manner consistent with our expectations. |
| first_indexed | 2025-11-14T08:18:57Z |
| format | Journal Article |
| id | curtin-20.500.11937-30433 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T08:18:57Z |
| publishDate | 2011 |
| publisher | I E E E |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-304332017-09-13T15:32:24Z A Metric for Performance Evaluation of Multi-Target Tracking Algorithms Ristic, B. Vo, Ba-Ngu Clark, D. Vo, Ba Tuong tracking Estimation performance evaluation Performance evaluation of multi-target tracking algorithms is of great practical importance in the design, parameter optimization and comparison of tracking systems. The goal of performance evaluation is to measure the distance between two sets of tracks: the ground truth tracks and the set of estimated tracks. This paper proposes a mathematically rigorous metric for this purpose. The basis of the proposed distance measure is the recently formulated consistent metric for performance evaluation of multi-target filters, referred to as the OSPA metric. Multi-target filters sequentially estimate the number of targets and their position in the state space. The OSPA metric is therefore defined on the space of finite sets of vectors. The distinction between filtering and tracking is that tracking algorithms output tracks and a track represents a labeled temporal sequence of state estimates, associated with the same target. The metric proposed in this paper is therefore defined on the space of finite sets of tracks and incorporates the labeling error. Numerical examples demonstrate that the proposed metric behaves in a manner consistent with our expectations. 2011 Journal Article http://hdl.handle.net/20.500.11937/30433 10.1109/TSP.2011.2140111 I E E E restricted |
| spellingShingle | tracking Estimation performance evaluation Ristic, B. Vo, Ba-Ngu Clark, D. Vo, Ba Tuong A Metric for Performance Evaluation of Multi-Target Tracking Algorithms |
| title | A Metric for Performance Evaluation of Multi-Target Tracking Algorithms |
| title_full | A Metric for Performance Evaluation of Multi-Target Tracking Algorithms |
| title_fullStr | A Metric for Performance Evaluation of Multi-Target Tracking Algorithms |
| title_full_unstemmed | A Metric for Performance Evaluation of Multi-Target Tracking Algorithms |
| title_short | A Metric for Performance Evaluation of Multi-Target Tracking Algorithms |
| title_sort | metric for performance evaluation of multi-target tracking algorithms |
| topic | tracking Estimation performance evaluation |
| url | http://hdl.handle.net/20.500.11937/30433 |