At Perm National Research Polytechnic University (PNRPU), scientists have developed an innovative technology to ensure stable video transmission even with a weak internet connection. This development proved to be 28-32% more efficient than existing solutions.
A machine vision complex records and compresses video for transmission over the network. On the server, the data is decompressed back into video. With a poor internet connection (packet loss/delay), the video freezes, skips frames, or becomes blurry. This often happens in remote areas, with an unstable wireless signal, as well as when the object is moving (quadcopters, transport). Failures can lead to serious consequences: for example, video surveillance systems may not recognize criminals or car numbers, and in intensive care units, they may miss a deterioration in the patient's condition.
Our algorithm works in three steps. First, the program uses artificial intelligence to determine which object in the video is the most important (region of interest - ROI) and determines its boundaries. Then it packs this data using a modern compression format - JPEG 2000. It is similar to the usual JPEG, in which we save pictures from the Internet, but surpasses it in quality. During the shooting process, the system evaluates the current internet speed and calculates how much data can be transmitted during the display time of one frame. If the speed is low, the frame data is sent not completely, but only partially. Since the neural network has already determined which area needs to be transmitted, data about the necessary objects are sent first, even with a poor connection.
As noted in PNRPU, the development does not require large computing power, which allows you to stably transmit the image in unstable Internet conditions. This technology can be useful for video surveillance systems in the Ministry of Emergency Situations, geological exploration or agriculture, where there are often problems with communication. The study was conducted as part of the strategic academic leadership program "Priority-2030".
Read more on the topic:
A unique system for protecting industrial facilities from UAVs was developed by NTI engineers
Now on home
The state has accelerated the introduction of unmanned solutions, integrating them into the real sector of the economy
Modernized engines may equip the Lada Azimut crossover
The price is 132 billion 265.8 million rubles
The manufacturer plans to strengthen its lineup of light commercial vehicles
The production of carbon fiber was organized in the shortest possible time
Electric vans will speed up the repair of urban transport infrastructure
Countries are working to synchronize regulations in the field of AI
The service's average daily audience is 55 million people
Stable Isomaterial Based on Metakaolin Has a Density Below 300 kg/m³
Re-identification quality improved twofold with new DynaMix method
Russians will be able to find out about debts online
The company presented the new crossover in Moscow and announced the launch dates for mass production