AI-Driven Video Understanding Technology

Request a demo

VIISIGHTS BEHAVIORAL RECOGNITION
VIDEO UNDERSTANDING TECHNOLOGY
DETECTION. RECOGNITION. INNOVATION.

viisights’ innovative behavioral recognition video understanding technology is based on a unique implementation of deep neural networks. These AI-driven networks are capable of analyzing and deducting high-level concepts derived from video content.

viisights technology recognizes the behavior of diverse objects, as well as its relevant contexts. For example, the system is capable of recognizing an individual moving back and forth in a predefined area. Such a behavior may be “loitering”. However, the way people behave at a bus stop is different from their behavior near an ATM machine. viisights intelligent video analytics system automatically identifies the location type – bus stop or ATM – without any manual setup or calibration. The combination of human behavior (e.g. moving back and forth) and location type results in a unique insight that classifies the movement either as loitering or as something entirely different.

The integration of multiple deep neural networks and the holistic analysis of multiple dimensions of video understanding, creates a significant challenge in terms of throughput and scalability processing.

viisights overcomes these challenges in a two-folded approach:

Using NVIDIA GPU processors which provide the demanding processing power required by the system.

Incorporating a unique system architecture that significantly shortens the processing time of each analysis aspect, thus allowing the system to complete the holistic analysis in near real time.

THE FOLLOWING IS A HIGH-LEVEL VIEW OF THE SYSTEM ARCHITECTURE:

blank

Our intelligent behavioral recognition video understanding technology utilizes a unique orchestrated architecture that enables the effective implementation of advanced deep neural networks. This architecture supports multiple holistic views by using:

  • Multi-scale image analysis
  • Time-aware analysis
  • Smart integration between object detection and the tracking mechanism
  • Innovative object detection structure that accelerates performance and increases accuracy

PRODUCT MODEL

viisights behavioral recognition video understanding technology leverages the classical deep learning model, as depicted in the following diagram, while implementing unique training tools and methodologies to reduce the amount of data required for training

blank

viisights uses NVIDIA GPU in both the training process and in the production system. In the training system it uses the Tesla P100 GPU and in the production, it uses several types of GPU depends on feature set configuration and the required workload. By such choice of hardware, viisights combines the power of the advanced GPU with affordable cost in the production environment.