Attention-Based Vision for Autonomous Vehicles
Navy SBIR FY2014.1

Sol No.: Navy SBIR FY2014.1
Topic No.: N141-076
Topic Title: Attention-Based Vision for Autonomous Vehicles
Proposal No.: N141-076-0982
Firm: SiliconScapes
330 Innovation Blvd.
Suite 302
State College, Pennsylvania 16803
Contact: Kevin Irick
Phone: (678) 612-4431
Web Site:
Abstract: This small business innovation Phase I project aims to develop a robust architecture for an attention based visual system for autonomous vehicle applications. Such a system is a critical front-end component for highly cognitive systems that can recognize objects and extract scene semantics from high resolution, multimodal image streams. The proposed solution is based on a bottom-up and top-down visual attention mechanism coupled with a hierarchical object recognition framework. This Phase I project aims to develop a complete specification, at an algorithmic level, of the proposed visual attention framework to determine the feasibility and project the performance that could be realized in a Phase II prototype. In addition to the size, weight, and power constraints imposed by a general vehicle platform, autonomous vehicles impose that visual information be captured and processed with short latency to afford real-time decision making. As such our solution will employ an appropriate combination of software and custom hardware accelerators to realize the latency and throughput requirements of an autonomous vehicle.
Benefits: Intelligent Video Analytics, IVA, was a $180 million market in 2012 and is expected to reach $850 million by 2017 with a CAGR of 30% over the span. The video analytics market covers a diverse range of domains including security, surveillance, robotics, retail, and automotive. Due to the complexity in traditional computer vision approaches, many of the IVA solutions still require significant human monitoring and interaction. SiliconScapes' proposed Attention Based Vision concept, with efficiency and performance realized through custom hardware implementation, will be a key element to the company's ability to offer superior vision based solutions across many of the Intelligent Video Analytics submarkets. The commercial impact is that SiliconScapes would be in a position to identify and partner with existing IP camera - and related technology - providers in the retail, security, and transportation markets to augment the capabilities of their existing products or to offer new solutions to commercially viable problems.