While wearable technology usually calls to mind devices such as smartwatches and fitness trackers, one exciting new avenue of research is augmented reality glasses. Virtual reality (VR) takes the user to a whole new virtual space, but augmented reality (AR) instead aims to enhance the real world by providing software interactions with physical things, through mediums like phone screens or glasses. This allows for a whole new approach to user interfaces, because programs can now interface with the real world in more meaningful capacities.
In the last two months, Amazon released their new machine learning camera to the public, the AWS DeepLens. The DeepLens is a unique video camera because it carries an onboard Intel Atom processor, meaning that not only can it run a full OS (it runs Ubuntu 16.04 by default), but it can also process video in real time using a machine learning model deployed to it over Amazon Web Services.
The advent of Bluetooth Low Energy (BLE) devices has allowed for the addition of wireless capability to low-powered devices, and expanding the possibilities for the Internet of Things. Because BLE was part of an update to the Bluetooth Standard in 2011, new code had to be written to support devices that utilized the technology. The Generic Attribute Profile (GATT) specification allows for a standardized method of accessing data from BLE devices, and libraries have been written to support this data collection in various languages. By using this technology, we explored the possibility of creating a “smart” kitchen, such that we could wirelessly receive temperature readings from a variety of Bluetooth thermometers.
With the explosion of the Internet of Things in recent years, it is no surprise that Google would want to get developers involved using the Android OS. The resulting product is Android Things (first released in May 2018), a version of the Android OS specifically designed for IoT devices. Based on the same operating system as Android phones, Android Things simplifies the development process and makes creating IoT programs the same procedure as a phone or watch app, but the available libraries are different depending on the IoT hardware.
While Elasticsearch is primarily used as a search engine, the platform has recently become more widely used in a variety of analytics tasks, including the ELK Stack of Elasticsearch, Logstash, and Kibana for real time analysis of large datasets. Elasticsearch also shows great potential in the realm of IoT, in which hundreds of data sources must be monitored in real time. Through optimized searching of time series data, Elasticsearch can be integrated with RESTful web services such as Spring Boot to provide users with real time visualizations of their sensor data.
Speech recognition is a technology we have been interested in for a while. Some of our earlier projects include integrating Alexa with Slack and creating an Alexa skill to aid with inventory management. We have been eager to work with speech recognition again since attending this year’s SpeechTek conference in Washington, DC. Excited to apply some of the lessons we learned and develop something both interesting and practical, we set out to create a smart digital assistant with Jasper.
AR and VR technologies have been a key trend for a while now, and many are saying that augmented reality will be the “new mobile” in terms of the next major platform. The tech is increasingly becoming more accessible to developers, especially in the AR market. This is evidenced by Apple’s announcement of ARKit, Aryzon’s cardboard for mixed reality, and Occipital’s low-cost AR/VR tracking platform.
We recently tested Rekognition’s image detection capabilities with photos from a cell phone camera, so next we decided to automate the process with photos from a Raspberry Pi camera module. We used a motion sensor we had set up in one of our previous projects to begin work on our desired motion-activated identity verification system. With that in mind, we set the Raspberry Pi and camera up on a desk in one of our office rooms, pointed it at the door, and got to work.
In a slight change of pace from our recent explorations of Internet of Things platforms, we started digging into Amazon’s recently announced Rekognition service. Rekognition is a powerful image processing service capable of detecting faces, people, objects, and subtle photo elements such as scene and sentiment.