Detect human only and trigger gpio

[mrbensonchong]

How can I modify the code to make the camera detect human only. And it can trigger gpio when the number of detected human goes to certain number such as 5?

[ISGIND]

Did you find a solution?? I have to detect only cars, so if you find the answer for use only one class... pls support me

[Twikkxx]

Hi did you find a solution for this? I'am working on this kind of project, if the model can detect an object it will trigger the pi gpio

[mrbensonchong]

I can't find the solution for that. finally i use Google Vision Kit to do that. the build-in program is good and you can easily amend the code to trigger the gpio. If you would like to know more about how i do that, i can share with you the video. thx Benson

Ivan Sanchez Gonzalez [email protected] 於 2019年1月24日週四 上午8:38寫道：

Did you find a solution?? I have to detect only cars, so if you find the answer for use only one class... pls support me

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/EdjeElectronics/TensorFlow-Object-Detection-on-the-Raspberry-Pi/issues/15#issuecomment-457021793, or mute the thread https://github.com/notifications/unsubscribe-auth/ApgMGYOWiJ_33PXGniSnLF780vvbUJllks5vGQCIgaJpZM4W1vNp .

[mrbensonchong]

I can't find the solution for that. finally i use Google Vision Kit to do that. the build-in program is good and you can easily amend the code to trigger the gpio. If you would like to know more about how i do that, i can share with you the video. thx Benson

TwixxZone12 [email protected] 於 2019年2月20日週三 下午11:04寫道：

Hi did you find a solution for this? I'am working on this kind of project, if the model can detect an object it will trigger the pi gpio

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/EdjeElectronics/TensorFlow-Object-Detection-on-the-Raspberry-Pi/issues/15#issuecomment-465614931, or mute the thread https://github.com/notifications/unsubscribe-auth/ApgMGXrl9qMjhl7ugxWx9X-NRgrd7uzrks5vPWPzgaJpZM4W1vNp .

[ColbyMay]

Could you share the video for that please @mrbensonchong

[servetcoskun]

@ISGIND @mrbensonchong you can edit the mscoco_label_map.pbtxtfile or make a copy and call it something else, then you can change the path in the code to your label file PATH_TO_LABELS = os.path.join(CWD_PATH, 'data', 'mscoc_label_map_cars.pbtxt') you can also change number of labels depending on how many you have in your .pbtxt file NUM_CLASSES = 10. I got an error after some fiddling around where it will classify the whole image, not sure if its from editing the files and classes variable, but it works nonetheless. Seems to be working fine now.