Modelling, synthesis and characterisation of occlusion in videos
Occlusion is one of the most challenging problems in many video processing applications such as surveillance, gait recognition, activity recognition and so on. Attempts have been made to develop algorithms for handling occlusion and evaluate their performance on various datasets. However, these stud...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2015-12-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2014.0170 |
| _version_ | 1827817708522045440 |
|---|---|
| author | Aditi Roy Pratik Chattopadhyay Shamik Sural Jayanta Mukherjee Gerhard Rigoll |
| author_facet | Aditi Roy Pratik Chattopadhyay Shamik Sural Jayanta Mukherjee Gerhard Rigoll |
| author_sort | Aditi Roy |
| collection | DOAJ |
| description | Occlusion is one of the most challenging problems in many video processing applications such as surveillance, gait recognition, activity recognition and so on. Attempts have been made to develop algorithms for handling occlusion and evaluate their performance on various datasets. However, these studies are subjective in nature and the datasets are hardly characterised in terms of the level of occlusion, thereby precluding any form of quantitative comparison of performance. This shows a compelling need to design an explicit, unambiguous and quantitative model, which should be able to objectively represent occlusion in a video. This study proposes an occlusion model based on the position and pose uncertainties of the moving subjects in a video. The proposed occlusion model is able to characterise the level of occlusion present in a video. It is also employed to synthetically generate occlusion for walking sequences, thus providing a direction for controlled dataset generation against which human identification algorithms can be tested. Given an input video with a subject moving without any occlusion, a particle swarm optimisation‐based parameter estimation methodology is presented that generates the desired level of occlusion. The proposed approaches have been tested on the TUM‐IITKGP and PETS2010 datasets. Finally, as an application, the occlusion model has been used to generate an occluded gait datasets and the performances of different gait recognition algorithms have been compared under varying levels of occlusion. |
| first_indexed | 2024-03-12T00:37:27Z |
| format | Article |
| id | doaj.art-ba23fd0a395f489ca3c8791f61d73d9c |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:37:27Z |
| publishDate | 2015-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-ba23fd0a395f489ca3c8791f61d73d9c2023-09-15T09:29:27ZengWileyIET Computer Vision1751-96321751-96402015-12-019682183010.1049/iet-cvi.2014.0170Modelling, synthesis and characterisation of occlusion in videosAditi Roy0Pratik Chattopadhyay1Shamik Sural2Jayanta Mukherjee3Gerhard Rigoll4Polytechnic School of EngineeringNew York UniversityBrooklynNYUSAIndian Institute of TechnologyKharagpurIndiaIndian Institute of TechnologyKharagpurIndiaIndian Institute of TechnologyKharagpurIndiaTechnical University of MunichGermanyOcclusion is one of the most challenging problems in many video processing applications such as surveillance, gait recognition, activity recognition and so on. Attempts have been made to develop algorithms for handling occlusion and evaluate their performance on various datasets. However, these studies are subjective in nature and the datasets are hardly characterised in terms of the level of occlusion, thereby precluding any form of quantitative comparison of performance. This shows a compelling need to design an explicit, unambiguous and quantitative model, which should be able to objectively represent occlusion in a video. This study proposes an occlusion model based on the position and pose uncertainties of the moving subjects in a video. The proposed occlusion model is able to characterise the level of occlusion present in a video. It is also employed to synthetically generate occlusion for walking sequences, thus providing a direction for controlled dataset generation against which human identification algorithms can be tested. Given an input video with a subject moving without any occlusion, a particle swarm optimisation‐based parameter estimation methodology is presented that generates the desired level of occlusion. The proposed approaches have been tested on the TUM‐IITKGP and PETS2010 datasets. Finally, as an application, the occlusion model has been used to generate an occluded gait datasets and the performances of different gait recognition algorithms have been compared under varying levels of occlusion.https://doi.org/10.1049/iet-cvi.2014.0170occlusion modellingocclusion synthesisocclusion characterisationvideo processing applicationsgait recognitionactivity recognition |
| spellingShingle | Aditi Roy Pratik Chattopadhyay Shamik Sural Jayanta Mukherjee Gerhard Rigoll Modelling, synthesis and characterisation of occlusion in videos IET Computer Vision occlusion modelling occlusion synthesis occlusion characterisation video processing applications gait recognition activity recognition |
| title | Modelling, synthesis and characterisation of occlusion in videos |
| title_full | Modelling, synthesis and characterisation of occlusion in videos |
| title_fullStr | Modelling, synthesis and characterisation of occlusion in videos |
| title_full_unstemmed | Modelling, synthesis and characterisation of occlusion in videos |
| title_short | Modelling, synthesis and characterisation of occlusion in videos |
| title_sort | modelling synthesis and characterisation of occlusion in videos |
| topic | occlusion modelling occlusion synthesis occlusion characterisation video processing applications gait recognition activity recognition |
| url | https://doi.org/10.1049/iet-cvi.2014.0170 |
| work_keys_str_mv | AT aditiroy modellingsynthesisandcharacterisationofocclusioninvideos AT pratikchattopadhyay modellingsynthesisandcharacterisationofocclusioninvideos AT shamiksural modellingsynthesisandcharacterisationofocclusioninvideos AT jayantamukherjee modellingsynthesisandcharacterisationofocclusioninvideos AT gerhardrigoll modellingsynthesisandcharacterisationofocclusioninvideos |