Efficient Reject Options for Particle Filter Object Tracking in Medical Applications
Reliable object tracking that is based on video data constitutes an important challenge in diverse areas, including, among others, assisted surgery. Particle filtering offers a state-of-the-art technology for this challenge. Becaise a particle filter is based on a probabilistic model, it provides ex...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/6/2114 |
| _version_ | 1797540889673859072 |
|---|---|
| author | Johannes Kummert Alexander Schulz Tim Redick Nassim Ayoub Ali Modabber Dirk Abel Barbara Hammer |
| author_facet | Johannes Kummert Alexander Schulz Tim Redick Nassim Ayoub Ali Modabber Dirk Abel Barbara Hammer |
| author_sort | Johannes Kummert |
| collection | DOAJ |
| description | Reliable object tracking that is based on video data constitutes an important challenge in diverse areas, including, among others, assisted surgery. Particle filtering offers a state-of-the-art technology for this challenge. Becaise a particle filter is based on a probabilistic model, it provides explicit likelihood values; in theory, the question of whether an object is reliably tracked can be addressed based on these values, provided that the estimates are correct. In this contribution, we investigate the question of whether these likelihood values are suitable for deciding whether the tracked object has been lost. An immediate strategy uses a simple threshold value to reject settings with a likelihood that is too small. We show in an application from the medical domain—object tracking in assisted surgery in the domain of Robotic Osteotomies—that this simple threshold strategy does not provide a reliable reject option for object tracking, in particular if different settings are considered. However, it is possible to develop reliable and flexible machine learning models that predict a reject based on diverse quantities that are computed by the particle filter. Modeling the task in the form of a regression enables a flexible handling of different demands on the tracking accuracy; modeling the challenge as an ensemble of classification tasks yet surpasses the results, while offering the same flexibility. |
| first_indexed | 2024-03-10T13:08:27Z |
| format | Article |
| id | doaj.art-213bdd2c25744689a3b3cff3124b2637 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T13:08:27Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-213bdd2c25744689a3b3cff3124b26372023-11-21T10:56:05ZengMDPI AGSensors1424-82202021-03-01216211410.3390/s21062114Efficient Reject Options for Particle Filter Object Tracking in Medical ApplicationsJohannes Kummert0Alexander Schulz1Tim Redick2Nassim Ayoub3Ali Modabber4Dirk Abel5Barbara Hammer6Machine Learning Group, Bielefeld University, 33619 Bielefeld, GermanyMachine Learning Group, Bielefeld University, 33619 Bielefeld, GermanyInstitute of Automatic Control, RWTH Aachen University, 52074 Aachen, GermanyDepartment of Oral and Maxillofacial Surgery, University Hospital RWTH Aachen, 52074 Aachen, GermanyDepartment of Oral and Maxillofacial Surgery, University Hospital RWTH Aachen, 52074 Aachen, GermanyInstitute of Automatic Control, RWTH Aachen University, 52074 Aachen, GermanyMachine Learning Group, Bielefeld University, 33619 Bielefeld, GermanyReliable object tracking that is based on video data constitutes an important challenge in diverse areas, including, among others, assisted surgery. Particle filtering offers a state-of-the-art technology for this challenge. Becaise a particle filter is based on a probabilistic model, it provides explicit likelihood values; in theory, the question of whether an object is reliably tracked can be addressed based on these values, provided that the estimates are correct. In this contribution, we investigate the question of whether these likelihood values are suitable for deciding whether the tracked object has been lost. An immediate strategy uses a simple threshold value to reject settings with a likelihood that is too small. We show in an application from the medical domain—object tracking in assisted surgery in the domain of Robotic Osteotomies—that this simple threshold strategy does not provide a reliable reject option for object tracking, in particular if different settings are considered. However, it is possible to develop reliable and flexible machine learning models that predict a reject based on diverse quantities that are computed by the particle filter. Modeling the task in the form of a regression enables a flexible handling of different demands on the tracking accuracy; modeling the challenge as an ensemble of classification tasks yet surpasses the results, while offering the same flexibility.https://www.mdpi.com/1424-8220/21/6/2114secure object trackingreject optionparticle filteringassisted surgery |
| spellingShingle | Johannes Kummert Alexander Schulz Tim Redick Nassim Ayoub Ali Modabber Dirk Abel Barbara Hammer Efficient Reject Options for Particle Filter Object Tracking in Medical Applications Sensors secure object tracking reject option particle filtering assisted surgery |
| title | Efficient Reject Options for Particle Filter Object Tracking in Medical Applications |
| title_full | Efficient Reject Options for Particle Filter Object Tracking in Medical Applications |
| title_fullStr | Efficient Reject Options for Particle Filter Object Tracking in Medical Applications |
| title_full_unstemmed | Efficient Reject Options for Particle Filter Object Tracking in Medical Applications |
| title_short | Efficient Reject Options for Particle Filter Object Tracking in Medical Applications |
| title_sort | efficient reject options for particle filter object tracking in medical applications |
| topic | secure object tracking reject option particle filtering assisted surgery |
| url | https://www.mdpi.com/1424-8220/21/6/2114 |
| work_keys_str_mv | AT johanneskummert efficientrejectoptionsforparticlefilterobjecttrackinginmedicalapplications AT alexanderschulz efficientrejectoptionsforparticlefilterobjecttrackinginmedicalapplications AT timredick efficientrejectoptionsforparticlefilterobjecttrackinginmedicalapplications AT nassimayoub efficientrejectoptionsforparticlefilterobjecttrackinginmedicalapplications AT alimodabber efficientrejectoptionsforparticlefilterobjecttrackinginmedicalapplications AT dirkabel efficientrejectoptionsforparticlefilterobjecttrackinginmedicalapplications AT barbarahammer efficientrejectoptionsforparticlefilterobjecttrackinginmedicalapplications |