High-Throughput Computer Vision/Etegent Technologies, LTD
Award last edited on: 8/18/22

Sponsored Program
Awarding Agency
Total Award Amount
Award Phase
Solicitation Topic Code
Principal Investigator
Jeffrey Walrath

Company Information

Etegent Technologies Ltd (AKA: SDL~Sheet Dynamics Ltd)

5050 Section Avenue Suite 110
Cincinnati, OH 45212
   (937) 531-4889
Location: Multiple
Congr. District: 02
County: Hamilton

Phase I

Contract Number: HQ003419P0056
Start Date: 1/31/19    Completed: 7/31/19
Phase I year
Phase I Amount
Etegent is proposing an agile hardware platform to enable object detection at extremely high pixel per watt rates and is also capable of quickly incorporating new algorithmic approaches. The core enabling technology of this system is a multicore system on a chip (SoC) server utilizing several low-power COTS processors configured with a high-speed interconnect switch. Etegent has developed a variety of object detection technologies using state-of-the-art methodologies on satellite imagery and is intimately familiar with the capabilities and challenges of these approaches. Etegent also has a history of developing efficient implementations of algorithms that leverage either common hardware architectures (CPU/GPU) or specialized hardware like DSPs. Etegent is partnering with the Space Computer group of Harris Corporation, which has a long track record of deploying airborne and spaceborne sensor systems. Etegent and Harris combine to form a highly capable multi-disciplinary team that understands the full pipeline required to develop the proposed system.

Phase II

Contract Number: HQ003422C0004
Start Date: 12/16/21    Completed: 12/15/23
Phase II year
Phase II Amount
The Etegent team proposes to design and demonstrate the feasibility of a hardware processor system capable of supporting computer vision (CV) object detection on tens of gigapixels per second in SWaP (Size, Weight and Power) limited environments. Specifically, this proposal will design and implement a modular and composable parallel computing software framework and prototype hardware system enabling the rapid transition of computer vision algorithms types from a development environment to a high performance, low-power, parallel computing platform. The team will research, augment and enhance existing inferencing tools for faster transition from development to deployment of more sophisticated, heterogeneous neural network topologies. As proof of feasibility, this effort will transform and implement several complete object detection neural networks using the developed tools and prototype hardware. Additionally, the team will characterize the implemented approach to measure and verify: 1) system throughput; 2) hardware power consumption; 3) implementation time required to transition networks to the system; and 4) performance of system operating with various sensor data formats. Results of this effort will demonstrate and deliver the software tools and applicable hardware design to achieve high throughput computer vision in SWaP limited environments.