Thermal Camera Analysis with Raspberry Pi (AMG8833)

The AMG8833 infrared thermopile array is a 64-pixel (8x8) detector that approximates temperature from radiative bodies. The module is wired to a Raspberry Pi 4 computer and communicates over the I2C bus at 400kHz to send temperature from all 64 pixels at a selectable rate of 1-10 samples per second. The temperature approximation is outputted at a resolution of 0.25°C over a range of 0°C to 80°C. A real-time infrared camera (IR camera) was introduced as a way of monitoring temperature for applications in person counting, heat transfer of electronics, indoor comfort monitoring, industrial non-contact temperature measurement, and other applications where multi-point temperature monitoring may be useful. The approximate error of the sensor over its operable range is 2.5°C, making is particularly useful for applications with larger temperature fluctuations. This tutorial is meant as the first in a series of heat transfer analyses in electronics thermal management using the AMG8833.

High Resolution Thermal Camera with Raspberry Pi and MLX90640

Thermal cameras are similar to standard cameras in that they use light to record images. The most significant distinction is that thermal cameras detect and filter light such that only the infrared region of the electromagnetic spectrum is recorded, not the visible region [read more about infrared cameras here]. Shortly after the discovery of the relationship between radiation and the heat given off by black bodies, infrared detectors were patented as a way to predict temperature via non-contact instrumentation. In recent decades, as integrated circuits shrink in size, infrared detectors have become commonplace in applications of non-destructive testing, medical device technology, and motion detection of heated bodies. The sensor used here is the MLX90640 [datasheet], which is a 768 pixel (24x32) thermal camera. It uses an array of infrared detectors (and likely filters) to detect the radiation given off by objects. Along with a Raspberry Pi computer, the MLX90640 will be used to map and record fairly high-resolution temeperature maps. Using Python, we will be able to push the RPI to its limits by interpolating the MLX90640 to create a 3 frame-per-second (fps) thermal camera at 240x320 pixel resolution.

Satellite Imagery Analysis in Python Part II: GOES-16 Land Surface Temperature (LST) Manipulation

For part II, the focus shifts from the introduction of file formats and libraries to the geospatial analysis of satellite images. Python will again be used, along with many of its libraries. Land Surface Temperature will again be used as the data information, along with shapefiles used for geometric boundary setting, as well as information about buildings and land cover produced by local governments - all of which are used in meteorological and weather research and analyses.

Satellite Imagery Analysis in Python Part I: GOES-16 Data, netCDF Files, and The Basemap Toolkit

In this tutorial series, Python’s Basemap toolkit and several other libraries are utilized to explore the publicly-available Geostationary Operational Environmental Satellite-16 (GOES-16). In this first entry, the following will be introduced: acquisition of satellite data, understanding of satellite data files, mapping of geographic information in Python, and plotting satellite land surface temperature (LST) on a map.

Multiple Object Detection with Python and Raspberry Pi

The picamera and edge detection routines will be used to identify individual objects, predict each object’s color, and approximate each object’s orientation (rotation). By the end of the tutorial, the user will be capable of dividing an image into multiple objects, determining the rotation of the object, and drawing a box around the subsequent object.

Image Processing Object Detection with Raspberry Pi and Python

In this entry, image processing-specific Python toolboxes are explored and applied to object detection to create algorithms that identify multiple objects and approximate their location in the frame using the picamera and Raspberry Pi. The methods used in this tutorial cover edge detection algorithms as well as some simple machine learning algorithms that allow us to identify individual objects in a frame.

Image Processing with Raspberry Pi and Python

The Raspberry Pi has a dedicated camera input port that allows users to record HD video and high-resolution photos. Using Python and specific libraries written for the Pi, users can create tools that take photos and video, and analyze them in real-time or save them for later processing. In this tutorial, I will use the 5MP picamera v1.3 to take photos and analyze them with Python and an Pi Zero W. This creates a self-contained system that could work as an item identification tool, security system, or other image processing application. The goal is to establish the basics of recording video and images onto the Pi, and using Python and statistics to analyze those images.