Economic activity, such as the number of containers in ports, the utilization of parking spaces in front of stores, or the number of cars in manufacturing plants, can be early indicators of economic trends and developments. Collecting and analyzing this information in real time can enable banks and companies to more accurately predict stock prices and sales, and thus act early in the financial market.
Such activities can be monitored and automatically analyzed in real time through the use of remote sensing, computer vision and machine learning (ML) methods. The goal is a tool that provides valuable information about current economic developments.
Automatic analysis of satellite and drone imagery can be used to monitor economic activities in real time. For this purpose, an ML algorithm is implemented that is able to identify and classify objects in image and radar data by training it with a sufficiently large labeled data set.
However, activity monitoring usually requires the detection of smaller objects, such as cars, ships, containers, freight cars, etc., for which image data with a high resolution is needed. In addition, the data source should have the highest possible update frequency in order to continuously monitor activities and quickly detect trends. Open source satellite data usually does not meet these requirements, so either commercial data sources or individual UAV flights should be used.
The detection and classification of objects in image data is a standard application of machine learning. Special convolutional neural networks (CNN), such as U-Net or Mask R-CNN architectures, are the most common methods. These are also capable of detecting multiple objects in an image. This allows different factors, e.g. number of ships and containers, to be monitored simultaneously, thus providing more detailed insights into economic activities.
Receive news about Machine Learning and news around dida.
Successfully signed up.
Valid email address required.
Email already signed up.
Something went wrong. Please try again.