|
|
Object detection for video surveillance using the SSD approach
Dobranský, Marek ; Lokoč, Jakub (advisor) ; Božovský, Petr (referee)
The surveillance cameras serve various purposes ranging from security to traffic monitoring and marketing. However, with the increasing quantity of utilized cameras, manual video monitoring has become too laborious. In re- cent years, a lot of development in artificial intelligence has been focused on processing the video data automatically and then outputting the desired no- tifications and statistics. This thesis studies the state-of-the-art deep learning models for object detection in a surveillance video and takes an in-depth look at SSD architecture. We aim to enhance the performance of SSD by updating its underlying feature extraction network. We propose to replace the initially used VGG model by a selection of modern ResNet, Xception and NASNet classifica- tion networks. The experiments show that the ResNet50 model offers the best trade-off between speed and precision, while significantly outperforming VGG. With a series of modifications, we improved the Xception model to match the ResNet performance. On top of the architecture-based improvements, we ana- lyze the relationship between SSD and a number of detected classes and their selection. We also designed and implemented a new detector with the use of temporal context provided by the video frames. This detector delivers enhanced precision while...
|
|
|
Object detection for video surveillance using the SSD approach
Dobranský, Marek ; Lokoč, Jakub (advisor) ; Božovský, Petr (referee)
The surveillance cameras serve various purposes ranging from security to traffic monitoring and marketing. However, with the increasing quantity of utilized cameras, manual video monitoring has become too laborious. In re- cent years, a lot of development in artificial intelligence has been focused on processing the video data automatically and then outputting the desired no- tifications and statistics. This thesis studies the state-of-the-art deep learning models for object detection in a surveillance video and takes an in-depth look at SSD architecture. We aim to enhance the performance of SSD by updating its underlying feature extraction network. We propose to replace the initially used VGG model by a selection of modern ResNet, Xception and NASNet classifica- tion networks. The experiments show that the ResNet50 model offers the best trade-off between speed and precision, while significantly outperforming VGG. With a series of modifications, we improved the Xception model to match the ResNet performance. On top of the architecture-based improvements, we ana- lyze the relationship between SSD and a number of detected classes and their selection. We also designed and implemented a new detector with the use of temporal context provided by the video frames. This detector delivers enhanced precision while...
|
|
|
Výkonná simulace destrukce prostředí ve hrách
Dobranský, Marek ; Kratochvíl, Miroslav (advisor) ; Vinárek, Jiří (referee)
Destructible environments have become a popular feature of computer games. Currently used game engines employ different approaches to imple- ment such environment. This thesis studies several such approaches and implements some key ideas from available research in a new, combined ap- proach. We use tessellations and boolean operations on triangular meshes to modify rigid-body objects that represent game environment, and create a simple application to demonstrate the approach in a real-time environment. We conclude that the proposed method is mainly suitable for computer games that feature low-polygon meshes. 1
|
guest ::
