Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • Users
  • Groups
Collapse
Brand Logo

ModalAI Forum

  1. ModalAI Support Forum
  2. VOXL SDK and Software
  3. Lepton Thermal Camera for Object detection

Lepton Thermal Camera for Object detection

Scheduled Pinned Locked Moved Unsolved VOXL SDK and Software
voxl-sdk
4 Posts 2 Posters 726 Views
  • 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.
  • Jetson NanoJ Offline
    Jetson NanoJ Offline
    Jetson Nano
    Veteran
    wrote on last edited by
    #1

    Hello @Eric-Katzfey @tom ,

    I had a doubt regarding the thermal camera pipeline(i.e. voxl-lepton-server). Can the output from the thermal camera be used for object detection on the voxl-tflite-server instead of using the RGB Hires camera as usual.

    I am using Lepton thermal camera on VOXL 2 compute.

    Jetson NanoJ 1 Reply Last reply
    0
    • Jetson NanoJ Jetson Nano

      Hello @Eric-Katzfey @tom ,

      I had a doubt regarding the thermal camera pipeline(i.e. voxl-lepton-server). Can the output from the thermal camera be used for object detection on the voxl-tflite-server instead of using the RGB Hires camera as usual.

      I am using Lepton thermal camera on VOXL 2 compute.

      Jetson NanoJ Offline
      Jetson NanoJ Offline
      Jetson Nano
      Veteran
      wrote on last edited by
      #2

      Could you please share some updates on this?

      1 Reply Last reply
      0
      • Zachary Lowell 0Z Offline
        Zachary Lowell 0Z Offline
        Zachary Lowell 0
        ModalAI Team
        wrote on last edited by
        #3

        @Jetson-Nano if you plan on using object detection in tflite server, then you can use yolov5 or yolov8 - I am unsure if you can pipe in that data into tflite with it working as that code base is meant to ingest generic raw and nv frames (RAW8/16 or NV12/21) so streaming in a different frame format might cause issue - if this doesnt fail and it works with the pipe, then it is up to you to train your own model based on the thermal camera feed.

        Jetson NanoJ 1 Reply Last reply
        0
        • Zachary Lowell 0Z Zachary Lowell 0

          @Jetson-Nano if you plan on using object detection in tflite server, then you can use yolov5 or yolov8 - I am unsure if you can pipe in that data into tflite with it working as that code base is meant to ingest generic raw and nv frames (RAW8/16 or NV12/21) so streaming in a different frame format might cause issue - if this doesnt fail and it works with the pipe, then it is up to you to train your own model based on the thermal camera feed.

          Jetson NanoJ Offline
          Jetson NanoJ Offline
          Jetson Nano
          Veteran
          wrote on last edited by
          #4

          @Zachary-Lowell-0 Thank you for your reply. I will test it out and let you of any developments.

          1 Reply Last reply
          0

          Reading along? Create a free ModalAI Forum account to join in.

          With an account you can reply, ask your own question, get an email when a ModalAI engineer answers, and mark the reply that solved it. Your place in each thread is saved between visits.

          Questions about VOXL, Flight Core, ESCs and ModalAI drones are answered here by the engineers who build them.

          Register Login
          Reply
          • Reply as topic
          Log in to reply
          • Oldest to Newest
          • Newest to Oldest
          • Most Votes


          ModalAI
          Categories Recent Tags ModalAI.com Docs
          © 2026 ModalAI® · Accelerating autonomy for smaller, smarter, safer drones · Powered by NodeBB
          • Login

          • Don't have an account? Register

          • Login or register to search.
          • First post
            Last post
          0
          • Categories
          • Recent
          • Tags
          • Popular
          • Users
          • Groups