|
|
Detection of Traffic Signs in Image and Video
Kočica, Filip ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
This thesis deals with the traffic sign detection problematics using modern techniques in image processing. Special architecture of deep convolutional neural network YOLO, i.e. You Only Look Once, which performs both detection and classification in one step, has been used. This architecture allows object detector to work on very high speeds. This thesis also deals with comparison of models trained on real and synthetic datasets. The best model trained on real dataset has reached 63.4% mAP success rate and 82.3% mAP when trained on synthetic dataset. Evaluation of one image takes about ~40.4ms on average graphics processing unit and ~3.9ms on higher than average graphics processing unit. The benefit of this thesis is that under certain conditions neural network model trained on synthetic data can achieve same or even better results than model trained on real data. This may simplify process of object detector development since it is not necessary to annotate large number of images.
|
|
|
Mass streaming in Czech Republic
VOJTA, Tomáš
Streaming is a technology that enables the real-time distribution of audio, video and multimedia content on the Internet. These days, the term ``streaming{\crq}q is becoming more widespread due to internet broadcasting of various radio and television stations. Therefore streaming will be the leading topic of this bachelor thesis. Firstly, the description of the technology itself will be mentioned. Secondly, a research on required hardware and software equipment will be carried( platform Adobe, Windows Media, RealMedia).
|
|
|
Detection of Traffic Signs in Image and Video
Kočica, Filip ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
This thesis deals with the traffic sign detection problematics using modern techniques in image processing. Special architecture of deep convolutional neural network YOLO, i.e. You Only Look Once, which performs both detection and classification in one step, has been used. This architecture allows object detector to work on very high speeds. This thesis also deals with comparison of models trained on real and synthetic datasets. The best model trained on real dataset has reached 63.4% mAP success rate and 82.3% mAP when trained on synthetic dataset. Evaluation of one image takes about ~40.4ms on average graphics processing unit and ~3.9ms on higher than average graphics processing unit. The benefit of this thesis is that under certain conditions neural network model trained on synthetic data can achieve same or even better results than model trained on real data. This may simplify process of object detector development since it is not necessary to annotate large number of images.
|
|
|
The Metaphor in the Poetry of Social Realism of the 1950s
Ondroušková, Světlana ; Bílek, Petr (advisor) ; Holý, Jiří (referee)
Based on Lakoff's theory of conceptual metaphor the thesis provides an insight into how the myth of the cult of leadership and the "new" land is realised in poetry of Social Realism of the 1950s. The analysis is based on understanding the myth as a "true story". The inicial part thus deals with the way of creating narrative of the leader in Social Realism. The other chapters contemplate on the how the effect of "real" is achieved, particularly using the metaphors of a "building", "container" and orientational metaphors. Concerning the hagiographic nature of the poetry, the thesis aims at explaining certain analogies and discrepancies between the myth of Social Realism and the Christian myth. Key words: Social Realism, conceptual metaphor, narrative, myth, real 4
|
|
| |
guest ::
