Hi,
I have been thinking about this question for a while: is the 8M quad that industrial version capable to run frameworks like Tensorflow or/and Caffe and processing the moving object recognition? Of course the image processing includes in that question.
The framework will be driven under operating system, Linux.
I think its capable to that, but there would be some problems on timing the process.
I have planned to use 5 MP camera based on OV5640 chip and some small HD-scale colored TFT-screen. Both maybe connected by the MIPI bus.
The timing between input and output (camera -> image processing -> recognition -> result on the screen with the picture).
I expect like realtime results on output (min 30 fps), so the time to output per picture can be something like 30 milliseconds at least.
Is the i.MX 8M Quad or even QuadLite capable to run process with these limits?
Or is it better to just wait the i.MX 8 launch?
Thanks in advance
Br. Roger
Hi Roger,
The i.MX8M is capable of running Tensorflow or/and Caffe and support deep learning frameworks.
Regards
Tensorflow or Tensorflowlite is better for moving object detection in i.MX8M