Crowd detection from aerial images
The detection of crowd from surveillance imagery is important to monitor public places and to ensure public safety. Hence, this work proposes crowd detection from static image captured from Unmanned Aerial Vehicle. The proposed methodology consists of three steps: FAST feature extraction, Gray Level...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2015
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/48892/25/SitiErneeMdzAiniMFKE2015.pdf |
| _version_ | 1796859407957491712 |
|---|---|
| author | Md. Zaini, Siti Ernee |
| author_facet | Md. Zaini, Siti Ernee |
| author_sort | Md. Zaini, Siti Ernee |
| collection | ePrints |
| description | The detection of crowd from surveillance imagery is important to monitor public places and to ensure public safety. Hence, this work proposes crowd detection from static image captured from Unmanned Aerial Vehicle. The proposed methodology consists of three steps: FAST feature extraction, Gray Level Co-Occurrence Matrix (GLCM) feature computation and the use of Support Vector Machine (SVM) for classification. The use of FAST corner detector is to obtain regions of interest where possible existence of crowd. The application of GLCM is to extract second order statistical texture features for texture analysis. The result of GLCM then, will be classified to crowd and non-crowd using SVM. For evaluation, ten different images were used taken in various crowd formation, event and location. The accuracy of the proposed method is obtained and the classification results are shown visually. |
| first_indexed | 2024-03-05T19:26:43Z |
| format | Thesis |
| id | utm.eprints-48892 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T19:26:43Z |
| publishDate | 2015 |
| record_format | dspace |
| spelling | utm.eprints-488922020-07-05T06:48:38Z http://eprints.utm.my/48892/ Crowd detection from aerial images Md. Zaini, Siti Ernee TK7885-7895 Computer engineer. Computer hardware The detection of crowd from surveillance imagery is important to monitor public places and to ensure public safety. Hence, this work proposes crowd detection from static image captured from Unmanned Aerial Vehicle. The proposed methodology consists of three steps: FAST feature extraction, Gray Level Co-Occurrence Matrix (GLCM) feature computation and the use of Support Vector Machine (SVM) for classification. The use of FAST corner detector is to obtain regions of interest where possible existence of crowd. The application of GLCM is to extract second order statistical texture features for texture analysis. The result of GLCM then, will be classified to crowd and non-crowd using SVM. For evaluation, ten different images were used taken in various crowd formation, event and location. The accuracy of the proposed method is obtained and the classification results are shown visually. 2015-01 Thesis NonPeerReviewed application/pdf en http://eprints.utm.my/48892/25/SitiErneeMdzAiniMFKE2015.pdf Md. Zaini, Siti Ernee (2015) Crowd detection from aerial images. Masters thesis, Universiti Teknologi Malaysia, Faculty of Electrical Engineering. http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:86749 |
| spellingShingle | TK7885-7895 Computer engineer. Computer hardware Md. Zaini, Siti Ernee Crowd detection from aerial images |
| title | Crowd detection from aerial images |
| title_full | Crowd detection from aerial images |
| title_fullStr | Crowd detection from aerial images |
| title_full_unstemmed | Crowd detection from aerial images |
| title_short | Crowd detection from aerial images |
| title_sort | crowd detection from aerial images |
| topic | TK7885-7895 Computer engineer. Computer hardware |
| url | http://eprints.utm.my/48892/25/SitiErneeMdzAiniMFKE2015.pdf |
| work_keys_str_mv | AT mdzainisitiernee crowddetectionfromaerialimages |