Detekce chodců pomocí dronů
| dc.contributor.advisor | Fusek, Radovan | |
| dc.contributor.author | Bystričan, Jakub | |
| dc.contributor.referee | Holuša, Michael | |
| dc.date.accepted | 2021-05-31 | |
| dc.date.accessioned | 2021-07-15T09:31:20Z | |
| dc.date.available | 2021-07-15T09:31:20Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | V tejto práci boli porovnávané metódy detekcie chodcov na snímkoch z dronov pomocou konvolučných neurónových sietí. Boli použité dve detekčné siete - YOLOv5 a Retinanet. U týchto sietí bola porovnávaná ich presnosť, rýchlosť a náročnosť trénovania. Taktiež bol sledovaný vplyv niektorých parametrov trénovania na výsledky detekcie. Pre trénovanie a testovanie bol použitý Stanford Drone Dataset ktorý obsahuje videozáznamy zachytené s dronom z kampusu Univerzity v Stanforde. | cs |
| dc.description.abstract | The main focus of this study was pedestrian detection using drones and convolutional neural networks. 2 detection networks were used - YOLOv5 and Retinanet. The performance was compared based on precision and speed of detection and the demands on training process. Impact of certian training parameters on results was also observed. For training and testing Stanford Drone Dataset was used, containing video recordings captured by drones at Stanford University campus. | en |
| dc.description.department | 460 - Katedra informatiky | cs |
| dc.description.result | výborně | cs |
| dc.format.extent | 16207996 bytes | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.other | OSD002 | |
| dc.identifier.sender | S2724 | |
| dc.identifier.thesis | BYS0043_FEI_B2647_2612R025_2021 | |
| dc.identifier.uri | http://hdl.handle.net/10084/144034 | |
| dc.language.iso | cs | |
| dc.publisher | Vysoká škola báňská – Technická univerzita Ostrava | cs |
| dc.rights.access | openAccess | |
| dc.subject | konvolučné neurónové siete | cs |
| dc.subject | detekcia chodcov | cs |
| dc.subject | hlboké učenie | cs |
| dc.subject | YOLOv5 | cs |
| dc.subject | Retinanet | cs |
| dc.subject | convolutional neural networks | en |
| dc.subject | pedestrian detectio | en |
| dc.subject | deep learning | en |
| dc.subject | YOLOv5 | en |
| dc.subject | Retinanet | en |
| dc.thesis.degree-branch | Informatika a výpočetní technika | cs |
| dc.thesis.degree-grantor | Vysoká škola báňská – Technická univerzita Ostrava. Fakulta elektrotechniky a informatiky | cs |
| dc.thesis.degree-level | Bakalářský studijní program | cs |
| dc.thesis.degree-name | Bc. | |
| dc.thesis.degree-program | Informační a komunikační technologie | cs |
| dc.title | Detekce chodců pomocí dronů | cs |
| dc.title.alternative | Pedestrian Detection Using Unmanned Aerial Vehicles | en |
| dc.type | Bakalářská práce | cs |
Files
Original bundle
1 - 5 out of 5 results
Loading...
- Name:
- BYS0043_FEI_B2647_2612R025_2021.pdf
- Size:
- 15.46 MB
- Format:
- Adobe Portable Document Format
- Description:
- Text práce
Loading...
- Name:
- BYS0043_FEI_B2647_2612R025_2021_zadani.pdf
- Size:
- 45.95 KB
- Format:
- Adobe Portable Document Format
- Description:
- Zadání
Loading...
- Name:
- BYS0043_FEI_B2647_2612R025_2021_priloha.zip
- Size:
- 60.94 MB
- Format:
- Unknown data format
- Description:
- Příloha
Loading...
- Name:
- BYS0043_FEI_B2647_2612R025_2021_posudek_vedouci_Fusek_Radovan.pdf
- Size:
- 55.06 KB
- Format:
- Adobe Portable Document Format
- Description:
- Posudek vedoucího – Fusek, Radovan
Loading...
- Name:
- BYS0043_FEI_B2647_2612R025_2021_posudek_oponent_Holusa_Michael.pdf
- Size:
- 55.92 KB
- Format:
- Adobe Portable Document Format
- Description:
- Posudek oponenta – Holuša, Michael