The use of neural networks is becoming morefamiliar in various fields of human activity. Developers from the Massachusetts Institute of Technology are planning to use the capabilities of artificial intelligence for surveillance systems that can detect the actions of a person behind an impenetrable obstacle, such as a wall, by video recording and scanning by radio waves.
The algorithm presented by scientists has two blocks. The initial data comes from a video camera or a radio scanner to a neural network, where an animated skeletal three-dimensional model of a human body is created. Further, in the second module, the program by analysis recognizes the most common human movements: talking on the phone, shaking hands, patting the shoulder or exchanging objects.
When processing data received from a video cameraWe used the open AlphaPose algorithm and a program that transforms flat skeletal models into three-dimensional ones. In the event of poor lighting or the presence of an impenetrable obstacle for video cameras, radio scanners operating in the transmit-receive mode at a frequency of 5.4 to 7.2 GHz were used. Such transmitters are equipped with two antennas located in the vertical and horizontal direction. Using the reception of reflected signals, the algorithm generates three-dimensional skeleton-like models.
When teaching artificial intelligenceWe used several data sets (datasets) that allow us to create certain models using radio signals, and we used the open PKU-MMD action recognition dataset.
When testing a version usingdevelopers of radio wave scanners achieved accuracy in the line of sight of 87.8%, which is comparable to the operation of video surveillance in normal lighting. At the same time, the radio scanner showed higher reliability than video surveillance in low light. Meanwhile, when observing with a scanner through a wall, the accuracy slightly decreased and amounted to 83%.
Such a surveillance system can be effective.used in smart home control systems, where some owners do not want to install video cameras for reasons of preserving personal space.