Pedestrian dynamics to detect automatic crowd formation
This thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2014.
| Główni autorzy: | , |
|---|---|
| Kolejni autorzy: | |
| Format: | Praca dyplomowa |
| Język: | English |
| Wydane: |
BRAC University
2014
|
| Hasła przedmiotowe: | |
| Dostęp online: | http://hdl.handle.net/10361/3223 |
| id |
10361-3223 |
|---|---|
| record_format |
dspace |
| spelling |
10361-32232022-01-26T10:23:20Z Pedestrian dynamics to detect automatic crowd formation Sarkar, Shovan Ali, Md. Refaat Azhar, Hanif Bin Department of Computer Science and Engineering, BRAC University Computer science and engineering This thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2014. Cataloged from PDF version of thesis report. Includes bibliographical references (page 44). In our work, we are trying to implement such a system that itself can predict whether there is a chance of forming a crowd in a public place or not, which will enrich the entire security system in such a way that the authority will be able to take precautions and avoid unexpected incidents. This system will work by using security cameras to take live streaming, identify each moving elements and analyze their movements. First we will take live streaming from security cameras and then we split the video into frames. Here we can split the video into 25-35 frames per second of playing time. Then we analyzed each frames and identify each moving elements and analyze their movements. First we will take live streaming from security cameras and then we split the video into frames. Here we can split the video into 25-35 frames per second of playing time. Then we analyzed each frames and identify each moving object and assign them with a unique object identification number. We also highlight the object with a rectangle box so in order to make it distinctive. We collect the data of each frame and save them in a data structure. Our algorithm does calculations on those data and predicts the next possible location of structure. Our algorithm does calculations on those data and predicts the next possible location of each object and therefore we can predict the possible location for a crowd. Apart from crowd detection, our research also extracts features from the movement of each objects (in this case pedestrian) and also predicts what will be the position of the object in future, whether a crowd has already formed or not , if someone is suspiciously standing in a busy way etc. Shovan Sarkar Md. Refaat Ali B. Computer Science and Engineering 2014-05-14T04:57:11Z 2014-05-14T04:57:11Z 2014 2014-04 Thesis ID 10101004 ID 11101028 http://hdl.handle.net/10361/3223 en BRAC University thesis are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 45 pages application/pdf BRAC University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
Computer science and engineering |
| spellingShingle |
Computer science and engineering Sarkar, Shovan Ali, Md. Refaat Pedestrian dynamics to detect automatic crowd formation |
| description |
This thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2014. |
| author2 |
Azhar, Hanif Bin |
| author_facet |
Azhar, Hanif Bin Sarkar, Shovan Ali, Md. Refaat |
| format |
Thesis |
| author |
Sarkar, Shovan Ali, Md. Refaat |
| author_sort |
Sarkar, Shovan |
| title |
Pedestrian dynamics to detect automatic crowd formation |
| title_short |
Pedestrian dynamics to detect automatic crowd formation |
| title_full |
Pedestrian dynamics to detect automatic crowd formation |
| title_fullStr |
Pedestrian dynamics to detect automatic crowd formation |
| title_full_unstemmed |
Pedestrian dynamics to detect automatic crowd formation |
| title_sort |
pedestrian dynamics to detect automatic crowd formation |
| publisher |
BRAC University |
| publishDate |
2014 |
| url |
http://hdl.handle.net/10361/3223 |
| work_keys_str_mv |
AT sarkarshovan pedestriandynamicstodetectautomaticcrowdformation AT alimdrefaat pedestriandynamicstodetectautomaticcrowdformation |
| _version_ |
1814309880756961280 |