Development of Shape from Focus Techniques for Robust Mean shift Tracking / (Record no. 616104)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 04153nam a22001697a 4500 |
| 003 - CONTROL NUMBER IDENTIFIER | |
| control field | NUST |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 621.382,MEH |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Mehmood, Rashid |
| 9 (RLIN) | 21363 |
| 245 ## - TITLE STATEMENT | |
| Title | Development of Shape from Focus Techniques for Robust Mean shift Tracking / |
| Statement of responsibility, etc. | Rashid Mehmood |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Place of publication, distribution, etc. | Rawalpindi, |
| Name of publisher, distributor, etc. | MCS (NUST), |
| Date of publication, distribution, etc. | 2017 |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | viii, 140 p |
| 505 ## - FORMATTED CONTENTS NOTE | |
| Formatted contents note | Visual object tracking is an active and challenging computer vision research domain having<br/>wide range of civil and defence applications. Mean shift (MS) is a commonly used<br/>target tracking technique due to its ease of implementation and real time response. However,<br/>it has certain short-comings that limits its tracking performance. In this thesis short<br/>comings of MS tracking like poor localization, complicated background distraction, partial/<br/>full occlusion and distraction due to similar target resemblance are addressed using 2D<br/>and 3D features.<br/>To improve MS target localization problem due to the presence of complex/mingled<br/>background features (in target representation), a novel 2D spatio-spectral technique is<br/>proposed. True background weighted histogram features are identified in target model<br/>representation using spectral and spatial weighting. A transformation is then applied to<br/>minimize their effect in target model representation for localization improvement. Edge<br/>based centroid re-positioning is applied to adjust/re-position the MS estimated target position<br/>for further localization improvement. Occlusion avoidance method is developed for<br/>MS tracking algorithm using adaptive window normalized cross correlation (NCC) based<br/>template matching. The Bhattacharyya coefficient based similarity threshold is used to<br/>detect partial/full occlusion and to initiate the NCC part in MS tracking. A target model<br/>updation for background weighted histogram through online feature consistency data is<br/>also proposed. The proposed 2D MS tracking techniques effectively solved the tracking<br/>problems of clutter, similar target resemblance, complex/fast object movement and partial/<br/>full occlusion.<br/>The failure cases for proposed 2D tracking technique include guidewire tip tracking<br/>for image guided cardiovascular interventions. The guidewire tip being thin, featureless<br/>and deformable structure is easily distracted with its own and similar object like vane structures in neighborhood. Moreover, the tracking of guidewire under low contrast fluoroscopic<br/>images and abrupt shape variations due to cardiac motion make the problem more<br/>challenging. 3D visual tracking techniques are used to incorporate object depth information<br/>to improve robustness. However, the existing 3D tracking techniques lack accuracy<br/>and robustness mainly due to non availability of precise depth features.<br/>In this thesis, depth features are acquired through shape from focus (SFF) technique and<br/>integrated with spectral and spatial features for robust 3D target representation/tracking.<br/>For 3D shape representation through SFF, a novel adaptive focus measure based on linear<br/>combination of multiple morphological gradient operators is proposed. The morphological<br/>edge gradient operators aided by multi-structuring elements are employed for sharpness<br/>measurement. The robust focus measure is then computed by combining the weighted<br/>response of gradient operators. The depth features acquired are integrated in joint histogram<br/>with grey level intensity and texture features to develop a novel technique for real<br/>time 3D representation and tracking of guidewire for image guided cardiovascular interventions.<br/>The grey level intensity is represented through conventional histogram method<br/>whereas the texture and depth features are represented through filtered local binary pattern<br/>histogram and filtered local depth pattern histogram respectively.<br/>The result shows the significant improvement in the accuracy, robustness and computational<br/>efficiency through proposed 2D/3D MS tracking and depth estimation techniques. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | PhD Electrical Engineering Thesis |
| 9 (RLIN) | 133107 |
| 651 ## - SUBJECT ADDED ENTRY--GEOGRAPHIC NAME | |
| Geographic name | PhD EE Thesis |
| 9 (RLIN) | 133108 |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Supervised by Dr. Naveed Iqbal Rao |
| 9 (RLIN) | 132893 |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | |
| Koha item type | Thesis |
| Withdrawn status | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Permanent Location | Current Location | Shelving location | Date acquired | Total Checkouts | Full call number | Barcode | Date last seen | Price effective from | Koha item type | Public note |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Military College of Signals (MCS) | Military College of Signals (MCS) | Thesis | 02/06/2026 | 621.382,MEH | MCSPhD EE-10 | 02/06/2026 | 02/06/2026 | Thesis | Almirah No.68, Shelf No.6 |