Award Data

Collaboration-Optimized Network for Naturalistic Exploration and Communication about Traffic (CONNECT) 3/19/2018 Collaboration-Optimized Network for Naturalistic Exploration and Communication about Traffic (CONNECT) will be a tool that allows users to easily generate a wide range of data visualizations from the Fatality Analysis Reporting System (FARS). CONNECT will leverage open-source visual ...

Reading Barcode Signs to Support V21 Safety 3/20/2018 For this SBIR we will develop a machine vision system which uses onboard standard-resolution cameras in vehicles to identify and read barcode signs on the roadside. The proposed approach could provide a low-cost solution that make connected and automated vehicle (CAV) technology viable for rural areas with limited access to Information and ...

An Artificial Intelligence (AI) Traffic Data Analysis Tool for Advanced Freeway Traffic Management 3/20/2018 Planned or unplanned traffic events cause various magnitude of traffic congestion and safety impact to road users. It was estimated that 60% of congestions are non-recurrent and 15% of incidents are secondary to the primal accidents. Thus local or regional Traffic Management Centers (T ...

Deep Learning-based Vehicle Tracking with Multiple Sensors 3/19/2018 The DOT is seeking an integrated unit that is capable of identifying and tracking individual vehicles with high accuracy using multiple vehicle detection inputs, including video images, radar-based detection, and wireless signal inputs (including DSRC, cellular, Wi-Fi, and Bluetooth signals), with a deep learning-based engine ...

Digital Twins for Bridge Management through the Integrating of Computer Vision and Finite Element Models 3/19/2018 We propose the development of an innovative integrated solution for health monitoring of bridge structures using a non-contact image-based measurement methodology. High-resolution and regular camera systems will be used to capture the bridge movements and the traffic passing the b ...

Proposal title: Rapid Assessment of Air Void in System in Fresh Concrete Air void parameters such as specific surface (SS) and spacing factor (SF) are essential in evaluating Freeze-Thaw (F-T) durability in fresh concrete. We have demonstrated the feasibility and viability of using an acoustic method to measure in near real time air void distributions in fresh concrete, the proposed solution is b ...

Proposal title: Detection of THC Use in Drivers The overall objective of this program is to develop a portable, cost-effective and non-invasive sensor device for near real-time salivary THC detection to be used at roadside in drivers. This will eliminate the need for expensive and time-consuming analytical techniques which have a turn-around time of several days. During the Phase I program Giner ...

Proposal title: A Robust Railway Track Crack Detection System Using Thermal Signatures In Phase I, we developed a practical sensor platform suitable for mounting on the back of train. A large amount of IR images associated with rail tracks were collected on an MBTA train. Algorithms were developed to identify both right and left tracks from a moving train. To help detect track cracks, we develope ...

Proposal title: Detection of THC Use in Drivers The intoxicating effects of marijuana are of concern to the law enforcement community as well as to the general manufacturing, service and commerce community where employees may need to be screened for intoxication. A reliable method to quantitatively measure the amount of the intoxicating agent delta-9- tetrahydrocannabinol (THC) in suspected marij ...

On this effort Toyon Research Corp. and The Pennsylvania State University are developing deep learning-based algorithms for object recognition and new class discovery in look-down infrared (IR) imagery. Our approach involves the development of a hybrid classifier that exploits both transfer learning and semi-supervised paradigms in order to maintain good generalization accuracy, especially when li ...