Classification and Segmentation in Remotely Sensed Imagery / (Record no. 217733)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 03329 a2200193 4500 |
| 003 - CONTROL NUMBER IDENTIFIER | |
| control field | Nust |
| 005 - DATE AND TIME OF LATEST TRANSACTION | |
| control field | 20260206191029.0 |
| 040 ## - CATALOGING SOURCE | |
| Transcribing agency | Nust |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 621.382,KHU |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Khurashid, Hasnat |
| 9 (RLIN) | 133115 |
| 245 ## - TITLE STATEMENT | |
| Title | Classification and Segmentation in Remotely Sensed Imagery / |
| Statement of responsibility, etc. | Hasnat Khurashid |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Place of publication, distribution, etc. | Rawalpindi, |
| Name of publisher, distributor, etc. | MCS (NUST), |
| Date of publication, distribution, etc. | 2016 |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | xiii, 101 p |
| 505 ## - FORMATTED CONTENTS NOTE | |
| Formatted contents note | Remote sensing technology and it’s applications are rapidly advancing. The algorithms<br/>and techniques for processing of remotely sensed images has thus become increasingly<br/>important and is an area of active research. Recently, a lot of research has been<br/>conducted in the domain of classification techniques of remotely sensed imagery. Classification<br/>techniques extract useful features from the remotely sensed data and then<br/>categorize it into different categories.<br/>This thesis proposes classification techniques for different applications in remotely<br/>sensed imagery. The first technique is a novel method for pixel classification. The<br/>proposed method exploits the spatial information of image pixels using morphological<br/>profiles produced by structuring elements of different sizes and shapes. Morphological<br/>profiles produced by multiple structuring elements are combined into a single feature<br/>by decimal coding. The advantage of proposed feature is that it can effectively utilize<br/>the potential of multiple morphological profiles without increasing the complexity of<br/>feature space. The second technique deals with the classification of image patches.<br/>The work is presented in the context of image retrieval framework of multispectral<br/>image patches. The proposed retrieval method is based on the combination of sparse<br/>coding and global image features. The third technique is for segmentation and change<br/>classification of built-up area in high resolution imagery using logistic regression. The<br/>research was conducted on multi spectral multi temporal images covering the 2010<br/>floods in Pakistan. Segmentation was performed to extract the built up area from the<br/>satellite images and then change detection was performed to find the damaged built up<br/>area. The damaged area was classified into three categories basing on the extent of<br/>damage. The results of change classification were compared and found consistent with<br/>the manual assessment report produced by experts of United Nations using Worldview<br/>1 satellite imagery with sub meter resolution. The fourth and the last technique is<br/>for regularized classification of changes using elastic net and high dimensional change<br/>feature vector comprising spectral, textural and structural changes.<br/>The proposed schemes were tested with simulated as well as real life multispectral<br/>and hyperspectral remotely sensed datasets. The multispectral dataset comprised<br/>of high resolution images with ground resolution of 2.5 meter. The performance was<br/>validated using authentic and publicly available ground truth data using standard performance<br/>measures. Qualitative and quantitative comparisons have been drawn with<br/>state of the art classification schemes and significant improvement is reported. |
| 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. Muhammad Faisal Khan |
| 9 (RLIN) | 133116 |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Koha item type | Thesis |
| Source of classification or shelving scheme | |
| Withdrawn status | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Permanent Location | Current Location | Shelving location | Date acquired | 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 | 12/12/2016 | 621.382,KHU | MCSPhd EE-08 | 12/08/2016 | 12/12/2016 | Thesis | Almirah No.68, Shelf No.6 |