Microsoft Vision AI Developer Kit Simplifies Building Vision-Based Deep Learning Projects Posted on : Sep 09 - 2019

Computer vision is one of the most popular applications of artificial intelligence. Image classification, object detection and object segmentation are some of the use cases of computer vision-based AI. These techniques are used in a variety of consumer and industrial scenarios. From face recognition-based user authentication to inventory tracking in warehouses to vehicle detection on roads, computer vision is becoming an integral part of next-generation applications.

Computer vision uses advanced neural networks and deep learning algorithms such as Convolutional Neural Networks (CNN), Single Shot Multibox Detector (SSD) and Generative Adversarial Networks (GAN). Applying these algorithms requires a thorough understanding of neural network architecture, advanced mathematics and image processing techniques. For an average ML developer, CNN remains to be a complex branch of AI.

Apart from the knowledge and understanding of algorithms, CNNs demand high end, expensive infrastructure for training the models, which is out of reach for most of the developers.

Even after managing to train and evaluate the model, developers find model deployment as a challenge. Trained CNN models are often deployed in edge devices that don’t have the required resources to perform inferencing - the process of classification and detection of images at runtime.

Edge devices are complemented by purpose-built AI chips that accelerate inferencing which come with their own software drivers and an interfacing layer. Developers are expected to convert the CNN model to the target AI chip and then integrate the application with the interface exposed by the chip. Intel, NVIDIA, Google, Huawei and Qualcomm are some of the key players in the AI accelerator market. Refer to one of my previous articles for a background on AI accelerators.

For the Vision AI Developer Kit, Microsoft and Qualcomm have partnered to simplify training and deploying computer vision-based AI models. Developers can use Microsoft’s cloud-based AI and IoT services on Azure to train models while deploying them on the smart camera edge device powered by a Qualcomm’s AI accelerator.

Let’s take a close look at Vision AI Developer Kit.

The Hardware

The Vision AI Developer Kit not only looks stylish and sophisticated, but also boasts of an impressive configuration.

The kit is powered by a Qualcomm Snapdragon 603 processor, 4GB of LDDR4X memory and 16GB of eMMC storage. Images are captured by an 8-megapixel camera sensor capable of recording in 4K UHD. The device also comes with a four-microphone array and speaker that can be utilized for building voice-based user interfaces. View More