Welcome to the Bahria University DSpace digital repository. DSpace is a digital service that collects, preserves, and distributes digital material. Repositories are important tools for preserving an organization's legacy; they facilitate digital preservation and scholarly communication.
dc.contributor.author | Abdullah Babar, 01-235182-099 | |
dc.contributor.author | Muhammad Afaque Tariq, 01-235182-082 | |
dc.date.accessioned | 2022-11-01T09:58:32Z | |
dc.date.available | 2022-11-01T09:58:32Z | |
dc.date.issued | 2022 | |
dc.identifier.uri | http://hdl.handle.net/123456789/13883 | |
dc.description | Supervised by Ms. Faima Abbasi | en_US |
dc.description.abstract | Generating highlights from any video is a labor intensive work that require some specialization and concentration. Being able to efficiently and effectively process unedited videos has become increasingly important. Cricket is a sport with a complex set of rules and is played for a longer time than most other sports. In this work we work on videos that are created and shared by ICC through different sports channels. Therefore, the videos we work with are domain specific (only cricket match), but are very diverse, featuring a wide range of actions and styles. We aim to improve video understanding by extracting the fundamental and most interesting parts out of videos on the basis of events. The events which were considered to generate the videos are empire actions. We apply a machine learning approach to generate highlights from cricket videos. To evaluate the performance our approach we used evaluation parameters, i.e., accuracy and precision. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Computer Science BU E8-IC | en_US |
dc.relation.ispartofseries | BS (IT);P-01823 | |
dc.subject | Cricket Highlight | en_US |
dc.subject | Highlight Generator | en_US |
dc.title | Cricket Highlight Generator. | en_US |
dc.type | Project Reports | en_US |