Joint Infrared Target Recognition and Segmentation Using a Shape Manifold-Aware Level Set
We propose new techniques for joint recognition, segmentation and pose estimation of infrared (IR) targets. The problem is formulated in a probabilistic level set framework where a shape constrained generative model is used to provide a multi-class and multi-view shape prior and where the shape mode...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2015-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/15/5/10118 |
| _version_ | 1811184276017774592 |
|---|---|
| author | Liangjiang Yu Guoliang Fan Jiulu Gong Joseph P. Havlicek |
| author_facet | Liangjiang Yu Guoliang Fan Jiulu Gong Joseph P. Havlicek |
| author_sort | Liangjiang Yu |
| collection | DOAJ |
| description | We propose new techniques for joint recognition, segmentation and pose estimation of infrared (IR) targets. The problem is formulated in a probabilistic level set framework where a shape constrained generative model is used to provide a multi-class and multi-view shape prior and where the shape model involves a couplet of view and identity manifolds (CVIM). A level set energy function is then iteratively optimized under the shape constraints provided by the CVIM. Since both the view and identity variables are expressed explicitly in the objective function, this approach naturally accomplishes recognition, segmentation and pose estimation as joint products of the optimization process. For realistic target chips, we solve the resulting multi-modal optimization problem by adopting a particle swarm optimization (PSO) algorithm and then improve the computational efficiency by implementing a gradient-boosted PSO (GB-PSO). Evaluation was performed using the Military Sensing Information Analysis Center (SENSIAC) ATR database, and experimental results show that both of the PSO algorithms reduce the cost of shape matching during CVIM-based shape inference. Particularly, GB-PSO outperforms other recent ATR algorithms, which require intensive shape matching, either explicitly (with pre-segmentation) or implicitly (without pre-segmentation). |
| first_indexed | 2024-04-11T13:09:37Z |
| format | Article |
| id | doaj.art-b9c54f6c60b34d5798f1aa918824f7c3 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T13:09:37Z |
| publishDate | 2015-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b9c54f6c60b34d5798f1aa918824f7c32022-12-22T04:22:37ZengMDPI AGSensors1424-82202015-04-01155101181014510.3390/s150510118s150510118Joint Infrared Target Recognition and Segmentation Using a Shape Manifold-Aware Level SetLiangjiang Yu0Guoliang Fan1Jiulu Gong2Joseph P. Havlicek3School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, OK 74078, USASchool of Electrical and Computer Engineering, Oklahoma State University, Stillwater, OK 74078, USASchool of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019, USAWe propose new techniques for joint recognition, segmentation and pose estimation of infrared (IR) targets. The problem is formulated in a probabilistic level set framework where a shape constrained generative model is used to provide a multi-class and multi-view shape prior and where the shape model involves a couplet of view and identity manifolds (CVIM). A level set energy function is then iteratively optimized under the shape constraints provided by the CVIM. Since both the view and identity variables are expressed explicitly in the objective function, this approach naturally accomplishes recognition, segmentation and pose estimation as joint products of the optimization process. For realistic target chips, we solve the resulting multi-modal optimization problem by adopting a particle swarm optimization (PSO) algorithm and then improve the computational efficiency by implementing a gradient-boosted PSO (GB-PSO). Evaluation was performed using the Military Sensing Information Analysis Center (SENSIAC) ATR database, and experimental results show that both of the PSO algorithms reduce the cost of shape matching during CVIM-based shape inference. Particularly, GB-PSO outperforms other recent ATR algorithms, which require intensive shape matching, either explicitly (with pre-segmentation) or implicitly (without pre-segmentation).http://www.mdpi.com/1424-8220/15/5/10118infrared ATRlevel setshape modelingparticle swarm optimization |
| spellingShingle | Liangjiang Yu Guoliang Fan Jiulu Gong Joseph P. Havlicek Joint Infrared Target Recognition and Segmentation Using a Shape Manifold-Aware Level Set Sensors infrared ATR level set shape modeling particle swarm optimization |
| title | Joint Infrared Target Recognition and Segmentation Using a Shape Manifold-Aware Level Set |
| title_full | Joint Infrared Target Recognition and Segmentation Using a Shape Manifold-Aware Level Set |
| title_fullStr | Joint Infrared Target Recognition and Segmentation Using a Shape Manifold-Aware Level Set |
| title_full_unstemmed | Joint Infrared Target Recognition and Segmentation Using a Shape Manifold-Aware Level Set |
| title_short | Joint Infrared Target Recognition and Segmentation Using a Shape Manifold-Aware Level Set |
| title_sort | joint infrared target recognition and segmentation using a shape manifold aware level set |
| topic | infrared ATR level set shape modeling particle swarm optimization |
| url | http://www.mdpi.com/1424-8220/15/5/10118 |
| work_keys_str_mv | AT liangjiangyu jointinfraredtargetrecognitionandsegmentationusingashapemanifoldawarelevelset AT guoliangfan jointinfraredtargetrecognitionandsegmentationusingashapemanifoldawarelevelset AT jiulugong jointinfraredtargetrecognitionandsegmentationusingashapemanifoldawarelevelset AT josephphavlicek jointinfraredtargetrecognitionandsegmentationusingashapemanifoldawarelevelset |