{"id":716,"date":"2020-12-19T00:51:34","date_gmt":"2020-12-19T00:51:34","guid":{"rendered":"https:\/\/machine-learning.webcloning.com\/2020\/12\/19\/building-and-deploying-an-object-detection-computer-vision-application-at-the-edge-with-aws-panorama\/"},"modified":"2020-12-19T00:51:34","modified_gmt":"2020-12-19T00:51:34","slug":"building-and-deploying-an-object-detection-computer-vision-application-at-the-edge-with-aws-panorama","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2020\/12\/19\/building-and-deploying-an-object-detection-computer-vision-application-at-the-edge-with-aws-panorama\/","title":{"rendered":"Building and deploying an object detection computer vision application at the edge with AWS Panorama"},"content":{"rendered":"
\n

Computer vision (CV) is sought after technology among companies looking to take advantage of machine learning (ML) to improve their business processes. Enterprises have access to large amounts of video assets from their existing cameras, but the data remains largely untapped without the right tools to gain insights from it. CV provides the tools to unlock opportunities with this data, so you can automate processes that typically require visual inspection, such as evaluating manufacturing quality or identifying bottlenecks in industrial processes. You can take advantage of CV models running in the cloud to automate these inspection tasks, but there are circumstances when relying exclusively on the cloud isn\u2019t optimal due to latency requirements or intermittent connectivity that make a round trip to the cloud infeasible.<\/p>\n

AWS Panorama<\/a> enables you to bring CV to on-premises cameras and make predictions locally with high accuracy and low latency. On the AWS Panorama console, you can easily bring custom trained models to the edge and build applications that integrate with custom business logic. You can then deploy these applications on the AWS Panorama Appliance, which auto-discovers existing IP cameras and runs the applications on video streams to make real-time predictions. You can easily integrate the inference results with other AWS services such as Amazon QuickSight<\/a> to derive ML-powered business intelligence (BI) or route the results to your on-premises systems to trigger an immediate action.<\/p>\n

Sign up for the preview<\/a> to learn more and start building your own CV applications.<\/p>\n

In this post, we look at how you can use AWS Panorama to build and deploy a parking lot car counter application.<\/p>\n

Parking lot car counter application<\/h2>\n

Parking facilities, like the one in the image below, need to know how many cars are parked in a given facility at any point of time, to assess vacancy and intake more customers. You also want to keep track of the number of cars that enter and exit your facility during any given time. You can use this information to improve operations, such as adding more parking payment centers, optimizing price, directing cars to different floors, and more. Parking center owners typically operate more than one facility and are looking for real-time aggregate details of vacancy in order to direct traffic to less-populated facilities and offer real-time discounts.<\/p>\n

\"\"<\/p>\n

To achieve these goals, parking centers sometimes manually count the cars to provide a tally. This inspection can be error prone and isn\u2019t optimal for capturing real-time data. Some parking facilities install sensors that give the number of cars in a particular lot, but these sensors are typically not integrated with analytics systems to derive actionable insights.<\/p>\n

With the AWS Panorama Appliance, you can get a real-time count of number of cars, collect metrics across sites, and correlate them to improve your operations. Let\u2019s see how we can solve this once manual (and expensive) problem using CV at the edge. We go through the details of the trained model, the business logic code, and walk through the steps to create and deploy an application on your AWS Panorama Appliance Developer Kit so you can view the inferences on a connected HDMI screen.<\/p>\n

Computer vision model<\/h2>\n

A CV model helps us extract useful information from images and video frames. We can detect and localize objects in a scene, and identity and classify images and action recognition. You can choose from a variety of frameworks such as TensorFlow, MXNet, and PyTorch to build your CV models, or you can choose from a variety of pre-trained models available from AWS or from third parties such as ISVs.<\/p>\n

For this example, we use a pre-trained GluonCV model downloaded from the GluonCV model zoo<\/a>.<\/p>\n

The model we use is the ssd_512_resnet50_v1_voc<\/a> model. It\u2019s trained on the very popular PASCAL VOC<\/a> dataset. It has 20 classes of objects annotated and labeled for a model to be trained on. The following code shows the classes and their indexes.<\/p>\n

\n
\n
voc_classes = {\r\n\t'aeroplane'\t\t: 0,\r\n\t'bicycle'\t\t: 1,\r\n\t'bird'\t\t\t: 2,\r\n\t'boat'\t\t\t: 3,\r\n\t'bottle'\t\t: 4,\r\n\t'bus'\t\t\t: 5,\r\n\t'car'\t\t\t: 6,\r\n\t'cat'\t\t\t: 7,\r\n\t'chair'\t\t\t: 8,\r\n\t'cow'\t\t\t: 9,\r\n\t'diningtable'\t: 10,\r\n\t'dog'\t\t\t: 11,\r\n\t'horse'\t\t\t: 12,\r\n\t'motorbike'\t\t: 13,\r\n\t'person'\t\t: 14,\r\n\t'pottedplant'\t: 15,\r\n\t'sheep'\t\t\t: 16,\r\n\t'sofa'\t\t\t: 17,\r\n\t'train'\t\t\t: 18,\r\n\t'tvmonitor'\t\t: 19\r\n}<\/code><\/pre>\n<\/div>\n

For our use case, we\u2019re detecting and counting cars. Because we\u2019re talking about cars, we use class 6 as the index in our business logic later in this post.<\/span><\/p>\n<\/div>\n
Our input image shape is [1, 3, 512, 512]. These are the dimensions of the input image the model expects to be given:<\/p>\n