Automatic document analysis and recognition is a hot topic in a modern computer vision. A common scenario is when the user takes a picture by mobile phone or tablet and the goal is to automatically parse and recognize content from the captured document. Such like pictures, tables, text data, links, etc.
Marker-based augmented reality (AR) is extremely popular nowadays. However, full user immersion is possible only in the case of robust real-time computer vision solutions working on the mobile device. We have developed a custom hybrid tracking system based on local feature tracking and template-based matching.
Object recognition is an important computer vision and machine learning problem. A particular case is automatic target recognition (ATR) on radar images. In the project, our team has developed a custom classification algorithm based on two different tools. We have been working with MSTAR dataset.
Fiducial markers are widely used in various applications like robot navigation, logistics, augmented reality. Fig. 1. Applications of fiducial markers Advantages are obvious High contrast Simple code generation Resistance to extremal angles However, when we deal with a large number of markers, real-time recognition becomes challenging, especially on embedded devices with low power CPUs on-board.
Indoor positioning systems are becoming popular nowadays. Indeed, there is plenty of opportunities for real-time user navigation in GPS-denied environments. An interesting use cases are as follows: Fig. 1. Indoor navigation use cases There are several options for hardware (see It-Jim blog post).
Synthetic aperture radar (SAR) systems are very popular instrument for high-resolution image of ground surface. Unlike to optical systems, SAR can be used in all weather and lighting conditions. A basic idea of SAR technique is coherent processing of received signals on a moving platform (aircraft or satellite).
The goal was to develop the approach for the automatic detection of the number plate area from the vehicle image. A typical ANPR algorithm includes several steps (Fig. 1): The number plate detection is a crucial step since it strongly affects on the overall system performance.
Our task was to develop the algorithm for the automatic road detection in radar images. The challenge was that the radar images are a bit different from the optical ones. In particular, in the case of synthetic aperture radar (SAR), the image formation process is accomplished via coherent processing of the received signals backscattered from the Earth surface.
Systems for detection and tracking of moving objects have a high demand nowadays. Our purpose was to develop the system for the analysis of the humans’ activity in the supermarket. In particular, to cluster the regions of interest (ROI), to detect, track and count the people.