2016-05-19 10:00:10 -0600 | received badge | ● Popular Question (source) |
2013-10-12 17:09:03 -0600 | asked a question | Supported embedded linux platforms Hello everybody :) I started developing a computervision application (stitching, object detection, background substractor) using a Raspberry Pi. I profiled my code and it seems that a lot of time is wasted with copying the images. Are there any well supported/documented alternatives to the Raspberry Pi that would provide better performance? (-> higher framerate and/or image size) On a sidenote: How big is the performance impact of NEON support and multiple cores? Is there are roadmap for supporting CUDA on ARM? (https://en.wikipedia.org/wiki/Tegra_2#Upcoming_releases) The Ouya seems to have a good cost-performance ratio. Opinions? https://en.wikipedia.org/wiki/Comparison_of_single-board_computers |
2013-01-11 11:07:28 -0600 | commented question | openCV does not build on my RaspberryPi You are correct. I am using Raspian. |
2013-01-11 08:27:46 -0600 | asked a question | openCV does not build on my RaspberryPi I get the following output when compiling opencv: I've been following this guide. What am I missing? :/ |
2012-12-27 08:33:10 -0600 | received badge | ● Student (source) |
2012-12-26 17:27:05 -0600 | asked a question | Advice on improving performance I am developing for an embedded ARM system and I am looking for advice on improving overall performance. Specifically: What should one avoid when developing for performance? (e.g. what functions are slow) How do you find out where you can improve your code? How to profile a opencv project under Linux? What are fast algorithms for object detection? Are there any code examples of fast implementations? |
2012-12-20 14:22:20 -0600 | asked a question | Performance on Raspberry Pi for detecting humans I would like to detect and track people using a Raspberry Pi, Model B v2 (512MB RAM) and a Logitech C310 webcam on a pan/tilt mount. I experimented with the BackgroundSubtractorMOG2 which worked quite well, but stitching (to build a background for the entire range of vision) is to slow. Now I am considering:
Is it possible to detect people on a Raspberry Pi with LBP or some other algorithm in real time? Can a neural network be fast enough for this too? |
2012-12-20 14:00:48 -0600 | answered a question | Encoding videos for opencv I recompiled with ffmpeg but forgot to -_- |
2012-12-04 17:46:47 -0600 | received badge | ● Supporter (source) |
2012-12-04 17:46:34 -0600 | commented answer | Encoding videos for opencv This is solved, but I am not allowed to close the question yet... It didn't work so I recompiled but forgot to "make install" -_- Everything works fine now... |
2012-12-04 06:01:51 -0600 | commented answer | Encoding videos for opencv For ccp-examle-bgfg_gmg even the original mjpeg videos work... it seems to be a problem with compiling. I do not understand, wh... |
2012-12-03 17:31:56 -0600 | commented answer | Encoding videos for opencv I am running out of ideas... are there any fool-proof video samples I could try? Maybe it's a problem with the code. |
2012-12-03 14:48:10 -0600 | commented answer | Encoding videos for opencv To what codec/format? |
2012-12-03 14:28:52 -0600 | received badge | ● Editor (source) |
2012-12-03 14:28:25 -0600 | asked a question | Encoding videos for opencv I would like to use video datasets to test my program, but unfortunately it does not work. How do I encode them for the current version of opencv? PS: It seems to be a problem with cmake (OpenCV examples work but own project doesn't). I am using the tutorial CMakeList.txt that does not compile including the codecs. Can you give me any pointers on how to correctly do this? |