Diplomovka
vedúci: RNDr. Miroslav Opiela, PhD.
konzultant: RNDr. Šimon Horvát, PhD.
✑ https://s.ics.upjs.sk/~martina_kuchtova/
Ciele
References
(Recommended reading)
- MENDOZA-SILVA, Germán Martín; TORRES-SOSPEDRA, Joaquín; HUERTA, Joaquín. A meta-review of indoor positioning systems. Sensors, 2019, 19.20: 4507.
- SZELISKI, Richard. Computer vision: algorithms and applications. Springer Nature, 2022.
- WOZNIAK, Piotr, et al. Scene recognition for indoor localization of mobile robots using deep CNN. In: Computer Vision and Graphics: International Conference, ICCVG 2018, Warsaw, Poland, September 17-19, 2018, Proceedings. Springer International Publishing, 2018. p. 137-147.
Documents
Indoor Navigation using AR (2023) at Dhanalakshmi College of Engineering's
Resources
Playlist
"The optimist sees opportunity in every difficulty.”
WORK DONE
State of the Art
Cloud
WEEKLY TASKS
Notes
DEADLINES
Data anonymisation
Methods
To do | method "name" | preview | status | affected | notes | method type | Enviroment/dependencies | Result |
---|---|---|---|---|---|---|---|---|
face swap (Real Time) | scripted | face | RealTime ntb camera | model | VS Codedlib | Example | ||
face swap | scripted | face | works on img, video | model | VS Codedlib | Example | ||
LAMA | model | Docker | haven' tested yet | |||||
pixel (face) | scripted | face | OpenCVcenzorhaar_cascades | ENV23 | Example | |||
censored (face) | scripted | face | black rect - profile&front face / eyes based | OpenCVcenzorhaar_cascades | ENV23 | Example | ||
blur (person) | in process | body | OpenCVblurhaar_cascades | ENV23 | haven' tested yet | |||
blur (face) | scripted | face | profile&front face / eyes based | OpenCVblurhaar_cascades | ENV23 | Example | ||
Untitled | haven' tested yet | |||||||
Untitled | haven' tested yet | |||||||
censor (face) domcol | dominant colour rectangle | haven' tested yet | ||||||
remove heads/faces | haven' tested yet | |||||||
remove people | haven' tested yet | |||||||
replace face (overlay) | haven' tested yet | |||||||
blur (whole image) | haven' tested yet |
Anonymisation candidates:
- face
- head (face & hair)
- upper body
- body
- image region
- whole image
Potential solutions:
➳ hair, moustage, glasses
➳ hood
➳ face filters, face-swap
➳ removal (AI supported)
Articles
Data
Data collecting
Name | Segments | Video count | Frames (circa) |
---|---|---|---|
Empty hall | ABCDE | ||
Person (standing) | ABC | ||
People (standing) | |||
Person (walking in front) | ABC | ||
Person (walking against cam) | ABCD | ||
Selfie vid | BC |
NN v. 0.1
empty hall trained; 3 segments (2 of them are following parts of the hallway)