If you are interested in Jetson TX1 Camera setup, please have a look on the shots taken with OV5693 CMOS Image Sensor and piped via Tegra X1 ISP (Image Signal Processing). The RAW data from camera goes through the MIPI interface to the Gstreamer pipeline and then is processed via “nvcamerasrc” plugin. I used following pipeline for this shots:
DISPLAY=:0 gst-launch-1.0 nvcamerasrc scene-mode=5 wbmode=5 auto-exposure=off exposure-time=0.066 flicker=1 intent=1 tnr-mode=2 tnr-strength=1 edge-enhancement=1.0 \ ! nvvidconv flip-method=2 \ ! 'video/x-raw(memory:NVMM), width=(int)2592, height=(int)1944, format=(string)I420, framerate=(fraction)30/1' \ ! autovideosink
The image quality might be downgraded by post-processing, which streams data via HDMI to HDMI-to-USB converter (h264 codec) and then screenshots have been converted to the JPEG format with lower quality. Additionally, the light conditions was not the best during the time of shooting (cloudy London day).
I show this shots, because I am impressed by handling auto-balance, auto-exposure, edge-enhancement, noise and many more by quite cheap 5M pixels sensor! Below, some shots under more difficult light condition and reflections…
Hope it helps in your research!
Feel free to contact me if you are interested in meeting the team and contribution to this project in any programming language (puppet, go, php, ruby, js, node.js, objective-c, java… and hardware, PCB, 3D printing, UI/UX, PR… and financial support…)
See my contact page if required.
© COPYRIGHT KRZYSZTOF STASIAK 2016. ALL RIGHTS RESERVED