Welcome to the Pycom forum Forum
    • \[\[global:header.categories\]\]
    • \[\[global:header.recent\]\]
    • \[\[global:header.tags\]\]
    • \[\[global:header.popular\]\]
    • Login

    Explore Pybytes | Official Documentation | Report a Firmware Bug/Issue | GitHub

    Camera image over MQTT

    Scheduled Pinned Locked Moved MicroPython
    low power
    27 Posts 9 Posters 17.9k Views 11 Watching
    Loading More Posts
    • Oldest to Newest
    • Newest to Oldest
    • Most Votes
    Reply
    • Reply as topic
    Log in to reply
    This topic has been deleted. Only users with topic management privileges can see it.
    • ahaw021A Offline
      ahaw021 @robmarkcole
      last edited by

      @robmarkcole

      This is a fairly simple computer vision problem

      The work we have done is proprietary to the customer so we aren't able to share it

      What I would suggest you do

      A) Use the storage available locally to save an image
      B) send the counts
      C) run for two weeks and see how accurate it is

      Sample of a related problem

      https://www.youtube.com/watch?v=PHwCK9ItDbc

      Andrei :D

      1 Reply Last reply Reply Quote 0
      • ahaw021A Offline
        ahaw021 @robmarkcole
        last edited by

        @robmarkcole

        did you get anywhere with this

        I have a JeVois camera and can provide you a reference code for a laptop (not an embedded board as I am waiting on my Pycoms) and actually have some eggs that I can send sample code for

        I believe simple blob detection should be good enough for what you need as the eggs should be fairly easy to make out

        Let me know

        Andrei

        R 1 Reply Last reply Reply Quote 0
        • R Offline
          robmarkcole @ahaw021
          last edited by

          @ahaw021 Hi Andrei, didn't make a start yet but its moving up my to-do list.
          Definitely confirming the image recognition algorithm is the first step and the more data the better. Perhaps you can post the image data on GitHub or Kaggle?
          Cheers

          1 Reply Last reply Reply Quote 0
          • B Offline
            BetterAuto Pybytes Beta @bucknall
            last edited by

            @bucknall said in Camera image over MQTT:

            Hi @robmarkcole

            This is definitely possible over WiFi as there are working examples written in C for the ESP32, however I'm yet to see this ported to MicroPython so it might be a while before you're able to do it specifically in MicroPython.

            Here's a link to the example I'm referencing written in C;

            https://github.com/igrr/esp32-cam-demo

            I see that project converts color pictures into ASCII art. Can anyone enumerate some other options for capturing color pictures and sending via network, LoRa or otherwise? I know of the Arducam, what else?

            Anything native to the ESP32 that can just connect one of the Onvif cameras (OV7670, OV2640) and send?

            1 Reply Last reply Reply Quote 0
            • P Offline
              phusy012 @robmarkcole
              last edited by

              @robmarkcole Hi wondering, if you have completed the project. We are also trying to connect camera(with low resolution) to Lopy4 and obtain the still image, convert into ASCII, break down into chunks and send it through LoRa.

              Would appreciate your guidance on how you did.

              Thankyou
              Regards
              Sonam

              S 1 Reply Last reply Reply Quote 0
              • S Offline
                smzk2001 @phusy012
                last edited by

                @phusy012 Hello Phusy012: I am trying to send image file to some back-end server via NBIoT technology. I would really appreciate if you may share some information that you might have collected related to your project.
                I can be contacted at: smzk2001@gmail.com

                J 1 Reply Last reply Reply Quote 0
                • J Offline
                  jcaron @smzk2001
                  last edited by jcaron

                  @smzk2001 NB-IOT is barely better than LoRa. With a peak rate of 26 kbits/s, it’s going to take forever to transmit a picture.

                  Exactly how long will depend a lot on the resolution, number of channels (i.e. grayscale vs colour), depth (number of bits per channel), compression, nature of the image...

                  A very basic 640 x 480 black and white (literally: 1 bit per pixel, not grayscale) uncompressed picture will take over 10 seconds to transmit. A 2 megapixels 24-bit colour picture, uncompressed, will take half an hour. Even if compressed, it will take minutes. Higher resolution pictures will quickly take hours.

                  NB-IOT is definitely not designed for this purpose. Cat-M1 would be barely better.

                  Depending on your exact application (picture parameters as described above, frequency or frame rate...), you’ll have to either switch to a much higher bandwidth technology (“full” LTE, WiFi...) or if relevant switch to local processing of the image to send only the result of the processing (e.g. “a move was detected” or “3 people were present”) rather than the image itself.

                  Of course, in either case, battery life will quickly become an issue.

                  S 1 Reply Last reply Reply Quote 1
                  • S Offline
                    smzk2001 @jcaron
                    last edited by

                    This post is deleted!
                    J 1 Reply Last reply Reply Quote 0
                    • J Offline
                      jcaron @smzk2001
                      last edited by

                      @smzk2001 I’m not sure I understand your issue. If you can send a few bytes then surely you can send thousands?

                      S 1 Reply Last reply Reply Quote 0
                      • S Offline
                        smzk2001 @jcaron
                        last edited by

                        @jcaron Dear Jcaron: Tnx for your reply. Sorry, if I couldn't make it clear. But, I now I have made it to sending a few hundreds of bytes now (upto 1KB). As soon as I am done with the final project, I will share my updates.

                        1 Reply Last reply Reply Quote 0

                        Hello! It looks like you're interested in this conversation, but you don't have an account yet.

                        Getting fed up of having to scroll through the same posts each visit? When you register for an account, you'll always come back to exactly where you were before, and choose to be notified of new replies (either via email, or push notification). You'll also be able to save bookmarks and upvote posts to show your appreciation to other community members.

                        With your input, this post could be even better 💗

                        Register Login
                        • 1
                        • 2
                        • 1 / 2
                        • First post
                          Last post

                        Pycom on Twitter

                        Pycom