Author: minjik4

Minji’s Status Report for 10/10

This week, Iris and I got together to install the WiFi module in the Jetson Nano. We also noticed that we’re missing the microSD card, which is required to install Linux on the Nano, so we placed a new order. Once the card arrives, we can continue to install necessary modules in the Nano for IoT and face/mask detection.

I did more research on Azure IoT Edge and IoT Hub products. Installing Edge on Nano will be pretty simple, and I’ll be able to configure it to be used as an Edge device. For IoT Hub, I will register the Nano as a connected Edge device. All of this can be easily done once the SD card arrives.

We spent most of this week working on the Design Review. We had to make more detailed design choices for the software stack, and it was helpful to have a detailed implementation before moving forward in the project. We also figured out the logic flow of the Nano once it receives inputs from the RFID scanner, the IR sensor, and the RGB camera. Next week, Iris and I will work to configure the Nano to receive inputs from all three sources and also register as an edge device on IoT Hub to open the Cloud Gateway.

Team Status Update for 10/3 

The most significant risks that could jeopardize the success of the project is if we fail to integrate all of our hardware components. We plan on testing out the individual hardware components prior to connecting everything together. A lot of research has been done to ensure that components are compatible. More research will be done if needed. In addition, we have to ensure that the Nucleo board will be able to turn the Jetson on/off since that is the major target in our low power goal. Jiamin did some research into this topic, but the ideas will have to be tested out once she comes back to Pittsburgh in 2 weeks. If we are unable to use the Nucleo board to wake the Jetson, then we might have to consider using some sort of physical momentary switch to activate the signal. 

After the proposal presentation we realized that the 2 degrees of error for the temperature reading from the FLIR IR camera is not good enough. We looked into cameras that could have better accuracy, but those were way out of our budget. From the TA’s suggestions, we decided that a sensor might be a better option. We decided on a sensor from the MLX90614 series. However, most sensors can only measure from a very short distance (2-5 cm). We did some more research and found that specifically the MLX90614-DCI has an accuracy of 0.5 degree of error for room temperature and 0.2 degree of error for human body temperature. It can also detect from a distance 50 cm, about 20 inches. The FLIR IR was originally around $200 and now we no longer need to buy a separate board to interface the camera with the Jetson. The sensor we chose is only $60, providing a little more breathing room in our $600 budget. 

The schedule has not been changed. Everything is still happening according to the initial Gantt chart created for the proposal presentation. 

Jiamin’s Status Update for 10/3

I submitted the order form for the STM32 Nucleo-64 Board (NUCLEO-L476RG) and the NFC reader (X-NUCLEO-NFC02A1). I read some documentation related to both of these boards and the steps needed for initial setup. I downloaded the STM32CubeIDE and the other software that are needed for the NFC board. I decided that I will most likely code in C instead of C++ for the Nucleo board, since I am more familiar with C. I also bookmarked some good quick start guides and YouTube videos that will come in handy when the boards do arrive. Aside from these 2 boards, I did a little deeper digging into how to turn on/off the Jetson by using the Nucleo board. I originally only did research on Jetson Nano A02 boards, but we purchased a B01 board. The notable thing was that instead of J40 I will be using the J50 headers. The way to disable auto power on and initiate power seems to be utilizing the same concepts. Pins 5 and 6 will need to be connected with a jumper to disable auto power on. Pins 11 and 12 will need to be shorted for a momentary switch to serve as a button to initiate power on when the auto power on is disabled. One thing I’m still a little unsure is how I will short pins 11 and 12. I will have to wait until I am back in Pittsburgh to fully test out some of my ideas.

My progress is on schedule since we planned in the Gantt chart that while we wait for our supplies to come, we will just do research and gather information that will be helpful to us.

If the board can come by next week, I would like to make sure that the Nucleo board and the NFC reader are initialized correctly, so that the NFC is working properly. I would like to write some initial code and tests to make sure the NFC is doing what is expected, and maybe just find some sample code online to test out some of the features of the Nucleo board. I would like to familiarize myself with the hardware and the STM32CubeIDE.

 

Iris’ Status Report for 10/3

We received one of our shipments today! The Jetson Nano came in, so I can start getting familiar with the kit and experimenting with different libraries (Opencv) to try testing out some features. I am trying to attach the wifi antennas to the Jetson Nano and will see if we can get wifi compatibility on it. We are missing some of the items in the order, however so I will need to wait for the Raspberry  Pi Camera Module V2 to come in before I can see how everything works together. I’m also trying to write some rough skeleton code for the mask and facial detection algorithm, I found some good training sets online that I will probably use later on.

I am pretty on track with our proposed schedule, just need to wait for the last few parts to come in. In the next week, I hope to be able to display live video feed onto a monitor and start making significant progress on the mask and facial detection algorithms.

Minji’s Status Report for 10/3

I started to do research on the general structure of an IoT application. Below is a summary of some of the things I learned this week.

Major components of an IoT project:

  • IoT Hardware Device — a physical device that interacts with the environment
  • Connectivity — the link between your device and the cloud
  • Product Cloud — servers that take in and process data

We can reflect this structure onto the scope of our project:

  • IoT Hardware Device — Jetson Nano that is connected to the RFID scanner and IR/RGB cameras
  • Connectivity — WiFi, by attaching the WiFi module to Jetson Nano to enable internet connection
  • Product Cloud — Microsoft Azure IoT Suite

The decision for the product cloud wasn’t very obvious. There are many cloud solutions available, but I found out that most of the community IoT projects that use Jetson Nano utilize the Microsoft Azure platform.

Next week, I am planning on looking more into the language to use for the software platform. I am currently leaning towards using full-stack Java for software development.

Helpful Resources I Found:

https://dev.to/azure/getting-started-with-iot-edge-development-on-nvidia-jetson-devices-2dfl