Human detection, classification and visualization using Wi-Fi

Remote detection of human activity using non-intrusive observation methods is an important technological need, particularly for the security industry.  Modern Smart Cities ideas also require new and novel methods of detecting and classifying human movement and general activity. Typically observation/detection is accomplished through digital or analog video cameras. But cameras have a limited field of view which allows avoidance. Deploying many cameras with overlapping coverage may be prohibitively expensive to solve this problem, particularly covering large areas. Special night-vision cameras are also needed for night time detection.  Wi-Fi sensing is an alternative solution to this problem since Wi-Fi signal already exist in an environment to be monitored or may be easily added with a benefit of providing device and human network connectivity.

The following video, provided by our sponsored researches Vahid and Hadi, demonstrates the results of a Proof of Concepts deployment and test. In this video 3 panes are shown. The left most pane shows how the real-time CSI vector changes as captured from a Wi-Fi access point. The middle pane shows an actual person moving in the Wi-Fi field recorded by a regular digital camera. The right most pane shows a reconstructed image of a person as derived from the changes in the CSI vector and overlaid onto the static environment image, for easy visualization.

[ CSI Vector Captures ]         [ Video Capture ]         [ Wi-Fi Detection ]

Previous implementations of Wireless sensing use Wi-Fi received signal strength indicator (RSSI) signals for probing the environment. Modern Wi-Fi standards with OFDM and MIMO technologies, which are adopted in 802.11 n/ac, provide new environment monitoring capabilities at the Wi-Fi receiver side using Channel State Information (CSI). In an empty environment with just a Wi-Fi transmitter and a receiver, the received signal is identical to the transmitted signal. However,  when there are objects in the environment (moving or stationary), the receiver gets multiple copies of the transmitted signal and therefore the received signal will be a perturbed copy of the transmitted signal. This perturbation is not constant over different frequencies and depends on the locations, build-materials, and speeds of the object traversing the environment. Channel State Information (CSI) is a complex-valued vector that quantifies this effect on each of the Wi-Fi frequency bands.


CSI carries new information which allows much more precise detection and classification of objects. CSI is captured by measuring the received signal strength and phase across multiple Wi-Fi subcarriers – up to 114 on a 40 Mhz channel.  CSI vector is then constructed which captures both signal strength and phase information for OFDM sub-carriers and between each pair of transmit-receive antennas receiving multiple signal copies.  As objects move through the monitored Wi-Fi field, CSI vector changes in real-time in a specific way.

Several open source projects allow convenient capture methods for real-time CSI data from Intel Wi-Fi chipsets and from Qualcomm/Atheros chipsets.  Futurebound Corp. provided equipment and logistical support to our affiliated researcher Vahid Pourahmadi and his colleague, Mohammad Hadi Kefayati, to further their efforts in developing a proof of concept system for human detection and visualization of such detection using Wi-Fi and CSI methodology. More details can be found at


Neurosurgical procedures and Augmented Reality – Proof of Concept

Update: March, 2020

We have prepared the following short video demonstrating the concepts of Augmented Reality based training for Neurosurgery students and doctors.

Update:  December 12, 2019

Futurebound Corp. Medical Technology Lead, Dr Urakov, shares results of the Augmented Reality Proof Of Concept development. The following video is presenting a recording of intraoperative demonstration in brain tumor localization and practical utilization of the hologram with switching modes of view from 3D to 2D.

Demonstration of AR to a senior neurosurgeon for the first time showing his sincere excitement level for the technology.

Neurosurgical Assist will allow elimination of the expensive real-time X-Ray and CT scan real-time guidance equipment from operating room. Several examples of our early research work are presented below, provided by Dr Urakov.

1. Brain tumor resection set of images

3D holographic projection generated from MRI images of patient’s brain is superimposed during surgery to visualize relevant anatomy and tumor margins. Views can be changed from three-dimensional to standard axial and sagittal 2D slices while spatial correlation is preserved.

image AimageBMedTech

2. Holographic overlay onto a patient allows for additional visualization while localizing correct thoracic level for operation.


3. Spine surgery with localizing instruments application.  Left windows show the views obtained with mixed-reality glasses during spinal level localization in neck (upper half) and lower back (bottom half) operations. Right windows show correlations with localizing instruments (hemostats for neck and needles for back) as seen with fluoroscopy x-rays. This visualizes our idea of the phase 2 product where mixed reality system is used for guidance of precision medical instruments.



Engineering Cost Estimates (in simple language)

Cost estimation for engineering projects is an important aspect of the systems engineering approach. Accurate estimates usually help keep the project budgets, and often schedules, on track. There are several publications out there explaining various classes for cost estimation and in this post I will attempt presenting such in a more simple terms. For source material reading please refer to

Class ‘D’ (Indicative) Estimate: is an estimate based on list cost per unit X the estimated number of units required for the project. The units themselves, such as number of network switches or servers, are estimated based on high level project requirements. The Class D estimate is the initial estimate that provides further input into the project development at its early stages. One would expect this estimate to be within “order of magnitude” of the actual.

Class ‘C’ Estimate: is an estimate based on full and comprehensive list of project requirements and accounts for the documented assumptions. Often this level of estimation is provided at the design stage. 20-25% accuracy is desired for this class.

Class ‘B’ (Substantive) Estimate: is an estimate based on detailed design of all major systems and subsystems that are part of the project.The estimate does not yet consider cost variances due to change orders and uses list prices of components. Due to this, often Class B is 15-20% accurate compared to the final project cost.

Class ‘A’ (Pre-Tender) Estimate: is an estimate that is based on the final set of designs with all assumptions verified/baselined and accounted for. Project risks are also documented and included in their cost format into this estimate. This Class Estimate is generally expected to be withing 5%-10% accurate of the actual contract cost allowing for minor cost variance due to change orders.

At the end, it is important to remember that project estimation is not a precise science. Existing conditions or something new related to other ongoing projects may affect the original estimates.



Virtual Desktop Infrastructure (Hyper-V)

Virtual Desktop Infrastructure (VDI) is centrally-deployed, centrally-managed desktop delivery solution. Various user workloads are packaged together into several flavors of personal or “kiosk” type desktops and are sent to a user via web interface. The VDI stores and runs the desktop, including a Windows client operating system (e.g. Windows 7 or 8), custom software applications, and  persistent user data, in a server-based virtual machine in a data center. This allows users to interact with the desktop presented on a user device (traditional workstation, thin client, tablet) via Remote Desktop Protocol.

The following table provides list of required components (hardware, software, licenses and effort) and their estimate cost for deploying 200 concurrent user VDI solution, with 75 Virtual Desktop users and 125 Remote Session Host (previously known as Terminal Services) users accessing the system. End-to-end solution is presented.

The design of this VDI solution is based on best practices published by Microsoft and Dell. The image below presents the major building blocks of the solution, with the network assumed to be existing at the client’s site and thus not included in the estimate.

VDI Building Blocks

VDI Building Blocks

The described VDI solution adheres to the following principles:

  • Concurrent users: 75 concurrent Personal Virtual Desktop Sessions (office local or remote) and 125 concurrent Remote Desktop Sessions / Virtualized Applications (e.g. contractors, field technicians, management and maintenance engineers)
  • Easily scalable up with additional building blocks
  • Desktops support both Persistent, Personal, Kiosk or mixed modes
  • Best practices are followed – Systems and Licensing
  • Highly Available – N+1 redundancy in the individual hardware components as well as system overall
  • 5 year hardware components warranty
  • Cost effective solution
VDI Costs

VDI Costs