Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

use pi camera for detection on raspberry pi 4 #37

Open
aminatamima opened this issue Sep 19, 2019 · 8 comments
Open

use pi camera for detection on raspberry pi 4 #37

aminatamima opened this issue Sep 19, 2019 · 8 comments

Comments

@aminatamima
Copy link

Hello could someone help on how i can use the project to detect from a pi camera ? Please
Thank you

@aminatamima
Copy link
Author

Could someone help please ?

@josilvacastillo
Copy link

with darknet original repo:
./darknet detector demo cfg/coco.data cfg/yolov3-tiny.cfg yolov3-tiny.weights

in this repo you should build darknet before with opencv=1 in Makefile (install opencv before)
make clean
make
i did this before, the cámera works, but the detector don't works.

@aminatamima
Copy link
Author

I meant with raspberry pi-caméra, this command doesnt work.

But i found and tested this link http://funofdiy.blogspot.com/2018/08/deep-learning-with-raspberry-pi-real.html with a python script for pi-cam live detection.
It works but without opencv =1 :( . got error opencv not found even if i have opencv well installed

@josilvacastillo
Copy link

i tested that branch and its nice, the python script display the predictions.png image in a loop.
when opencv=0 its create a predictions.png but its not display. i think that the problem is in the version of opencv, its need "python-opencv" from apt, but im build from source the 3.4.6 version

@Alexismichel
Copy link

If I take a picture with raspberry camera and execute
./darknet detector test cfg/coco.data cfg/yolov3-tiny.cfg yolov3-tiny.weights data/my_picture.jpg,
the program detect well.
If I try detect on live video, ./darknet detector demo cfg/coco.data cfg/yolov3-tiny.cfg yolov3-tiny.weights, there is no detection...
@josilvacastillo have you found any solution to get the nnpack-darknet working on raspberry pi 4 ?

@smallworld-network-wupeng

If I take a picture with raspberry camera and execute
./darknet detector test cfg/coco.data cfg/yolov3-tiny.cfg yolov3-tiny.weights data/my_picture.jpg,
the program detect well.
If I try detect on live video, ./darknet detector demo cfg/coco.data cfg/yolov3-tiny.cfg yolov3-tiny.weights, there is no detection...
@josilvacastillo have you found any solution to get the nnpack-darknet working on raspberry pi 4 ?

I have same problem ,this looks very weird
WX20200225-220907

@Jaswar
Copy link

Jaswar commented May 17, 2020

Hello,
Has anyone been able to solve the problem of not having any detections when using ./darknet detector demo?

@whgsh
Copy link

whgsh commented Jan 19, 2021

same problem here...using ./darknet detector demo, no detection

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

6 participants