Pose Estimation

Product Specification

Version Q3-2021

Product Description

The Pose Estimation module helps to identify a person in different states: sitting down, standing, walking, falling, getting up, as well as sending a notification in connection with the rule of human behavior.

Pose Estimation Features

  • Recognition of the lying down person
  • Recognition of stand up behavior
  • Recognition of sit down behavior
  • Recognition of a standing person
  • Recognition of a sitting person

–°amera Compatibility

The solution is compatible with all cameras, that return the RTSP stream.

A common choice for effective fallen detection: AXIS P1455-LE.

Camera Installation Requirements

  • Static and reliable camera mount
  • A top view/perspective top view
  • Exclusion of refocusing and image sharpness changes
  • There should be no light sources slowly changing their position in the frame
  • The people to be detected should not merge with the background
  • The camera must be positioned level to the horizon

  • The person's arms and legs should be clearly visible

Requirements for a Video Stream

  • Stable video stream (RTSP format)
  • Absence of fast-moving objects

Supported cameras

All cameras, RTSP

Maximum number of cameras

Unlimited, depending on the PC or Server

Other video sources

Avi Files, Ficheros Jpeg, Bmp

Technical Specifications

Cross-platform solution (Windows, Linux)


Centralized management


Ability to work with various versions of video data sources


Determination of different positions of the human skeleton+
Identification of a person according to the rule+

Minimum Software Requirements

Operating System - Ubuntu 18.04 or Windows 7 / Windows Server 2008 R2

Databases - MySQL 5.5 and newer, PostgreSQL 9.3 and newer, Oracle Express Edition 10g and newer, SQL Server Express Edition 2008 and newer

Minimum Hardware Requirements


 Intel Core i5-8250U @ 1.60GHz and with higher performance




(any from the list below or higher with better performance:

GTX 1660 6GB or

RTX 2060 SUPER 8GB or

RTX 2070 SUPER 8GB or

RTX 2080TI 11GB or

RTX 3070 8GB or

RTX 3080 10GB or

RTX 3090 24GB

Bandwidth5 Mb/s per 1 video analytics or higher*
Response time(local network)200 ms or faster

Security Features

Restricting access to a specific group of customers through access rights


Business logic building system


Encryption of information with dynamic keys, which change with each launch of the module


NVIDIA CUDA technology support


Security of personal data


Support for different interface languages


Interface languages: English, Ukrainian, Russian, Arabic


Alarms and Events

Alarm about the fallen person


Alarm about sitting person+
Alarm about sit down of a person+
Alarm about the stand-up person+
Alarm about walking person+

Software Licenses





Incoresoft VEZHA Pose Estimation


Image Characteristics

  • The minimum size of the recognizable person in the frame  - 70 x 200 pixels
  • Image quality must be at least average
  • There should be no significant compression artifacts
  • Image resolution should be HD or FullHD format or higher with an aspect ratio equals 16:9