 
| Real-time interest point tracking(15th July 2013) | |||||
| As mentioned in an other article about omnidirectional cameras, my Master's Thesis' main topic was real-time interest point extraction and tracking on an omnidirectional image in a challenging forest environment. I found OpenCV's routines mostly rather slow and running in a single thread, so I ended up implementing everything myself to gain more control on the data flow and threads' dependencies. The implemented code would simultaneously use 4 threads on CPU and a few hundred on the GPU, executing interest point extraction and matching at 27 fps (37 ms/frame) for 1800 × 360 pixels (≈0.65 Mpix) panoramic image. 
 |   | ||||
| 
                            Home
                            
                                 | 
| Home | (Home page) | 
| About | (About me) | 
| Platform | (About this blog) | 
| (Niko Nyrhilä) | |
| GitHub | (nikonyrh) | 
| Stackoverflow | (nikonyrh) | 
| Bruteforcing Countdown numbe... | (2023 Apr) | 
| Cheating at Bananagrams with... | (2023 Apr) | 
| Introduction to Stable Diffu... | (2022 Nov) | 
| Matching puzzle pieces together | (2022 Jul) | 
| Single channel speech / musi... | (2022 Feb) | 
| Computer Vision | (13) | 
| GitHub | (12) | 
| Databases | (9) | 
| Elasticsearch | (6) | 
| FFT | (5) | 
| Rendering | (5) | 
| Applied mathematics | (4) | 
| Python | (13) | 
| C++ | (11) | 
| Matlab | (10) | 
| Keras | (6) | 
| Clojure | (6) | 
| Bash | (6) | 
| PHP | (6) | 
| Matl | Pyth | C++ | Cloj | Bash | Kera | |
| Comput | 6 | 6 | 3 | 1 | 0 | 5 | 
| GitHub | 0 | 2 | 1 | 4 | 3 | 0 | 
| Databa | 0 | 3 | 2 | 2 | 1 | 0 | 
| Render | 3 | 0 | 3 | 0 | 0 | 0 | 
| Nginx | 0 | 1 | 0 | 0 | 4 | 0 | 
| Autoen | 0 | 3 | 0 | 1 | 0 | 2 | 
| Elasti | 0 | 2 | 0 | 3 | 0 | 0 | 
| FFT | 3 | 1 | 1 | 0 | 0 | 1 | 
| Data S | 2 | 1 | 2 | 1 | 0 | 1 | 
| JVM | 0 | 1 | 0 | 3 | 1 | 0 | 
| Docker | 0 | 1 | 0 | 0 | 3 | 0 | 
| FastCG | 0 | 0 | 3 | 0 | 0 | 0 | 
| Applie | 2 | 2 | 0 | 0 | 0 | 0 | 
| Field | 2 | 0 | 2 | 0 | 0 | 0 | 
| Omnidi | 2 | 0 | 2 | 0 | 0 | 0 | 
| Affine | 2 | 0 | 2 | 0 | 0 | 0 | 
| Master | 1 | 0 | 2 | 0 | 0 | 0 | 
| Archit | 0 | 1 | 0 | 0 | 2 | 0 | 
| Visual | 1 | 0 | 2 | 0 | 0 | 0 | 
| Spark | 0 | 1 | 0 | 0 | 2 | 0 | 
| Blog | 0 | 0 | 0 | 2 | 0 | 0 | 
| Hyphen | 0 | 0 | 0 | 2 | 0 | 0 | 
| Stack | 0 | 1 | 1 | 0 | 0 | 0 | 
| SQL | 0 | 0 | 1 | 1 | 0 | 0 | 
| Busine | 0 | 1 | 0 | 1 | 0 | 0 | 
| Signal | 0 | 1 | 0 | 0 | 0 | 1 | 
| Encryp | 0 | 0 | 0 | 0 | 1 | 0 | 
| Git | 0 | 0 | 0 | 1 | 0 | 0 | 
| Stable | 0 | 1 | 0 | 0 | 0 | 0 | 
| Redis | 0 | 1 | 0 | 0 | 0 | 0 | 
| Thrust | 0 | 0 | 1 | 0 | 0 | 0 | 
| Kibana | 0 | 0 | 0 | 1 | 0 | 0 | 
| Astron | 1 | 0 | 0 | 0 | 0 | 0 | 
| Mustac | 0 | 0 | 1 | 0 | 0 | 0 | 
| NAT | 0 | 0 | 0 | 0 | 1 | 0 | 
| jQuery | 0 | 0 | 1 | 0 | 0 | 0 | 
| SSH | 0 | 0 | 0 | 0 | 1 | 0 | 
| Happyh | 0 | 0 | 1 | 0 | 0 | 0 | 
| Backup | 0 | 0 | 0 | 0 | 1 | 0 | 
| Pthrea | 0 | 0 | 1 | 0 | 0 | 0 | 
| AWS | 0 | 0 | 0 | 0 | 1 | 0 | 
| SIFT | 0 | 0 | 1 | 0 | 0 | 0 | 
| SURF | 0 | 0 | 1 | 0 | 0 | 0 | 
| Conjug | 0 | 0 | 1 | 0 | 0 | 0 | 
| Kalman | 0 | 0 | 1 | 0 | 0 | 0 | 
| Partic | 0 | 0 | 1 | 0 | 0 | 0 | 
| Gradie | 0 | 0 | 1 | 0 | 0 | 0 | 
| Simult | 0 | 0 | 1 | 0 | 0 | 0 | 
| Roboti | 0 | 0 | 1 | 0 | 0 | 0 | 
| Princi | 1 | 0 | 0 | 0 | 0 | 0 | 
| Receiv | 1 | 0 | 0 | 0 | 0 | 0 | 
| Linear | 1 | 0 | 0 | 0 | 0 | 0 | 
| Suppor | 1 | 0 | 0 | 0 | 0 | 0 | 
| Machin | 1 | 0 | 0 | 0 | 0 | 0 | 
| Discre | 1 | 0 | 0 | 0 | 0 | 0 | 
