Award Data

In this proposed Phase II effort we will implement a software framework that will reduce the time required to annotate large image/video datasets by a factor of 100x while also reducing the data necessary to train state of the art computer vision models by up to 80%. Our strategy combines several elements and ideas. First, we have developed a sub-tile based a priori theory of how and why CNNs can ...

In Phase I we developed and demonstrated a bi-directional, monolithic, High-Speed, Electro-optic shutter for Range Gated Imaging. While meeting the majority of the key performance parameters for Range-Gated Imaging at high Pulse Repetition Frequency, improvements can be achieved in transmission, contrast and reliability. The Phase Ii activity begins with a upgraded Electro-optic Shutter incorpora ...

Deep Convolutional Neural Networks (DCNNs) have become ubiquitous in the analysis of large datasets with geometric symmetries. These datasets are common in medicine, science, intelligence, autonomous driving and industry. While analysis based on DCNNs have proven powerful, uncertainty estimation for such analyses has required sophisticated empirical studies. This has negatively impacted the effect ...

In Phase II we will explore further what processing of synthetic image generation produces training data that optimizes the model’s performance on real world images. While existing work on CycleGAN optimizes for human visual perception of domain adaptation it may not necessarily be optimal for training a network to generalize to real scenarios. We will look at modifications of the loss functions ...

In its effort to provide necessary intelligence and analysis, the National Geospatial-Intelligence Agency (NGA) utilizes extensive traffic camera systems. However, the large amount of data overwhelms both analysts and existing processing methods. In order to provide a better understanding and reduce the search space for common problems such as target tracking, it is necessary to extract the camera ...

BlueLightAI will build a suite of novel automated object detection and annotation tools for use on massive image data sets.  Based on topological constructions that use our proprietary geometric feature technology, the BlueLightAI suite will incorporate expanded prior knowledge into innate detection, segmentation, identification, and annotation of images. Replacing current Convolutional Neural Ne ...

Toyon Research Corp. proposes development of a software prototype for automated 3D damage assessment in urban environments. We will document the requirements for the algorithms and software, and optimize or extend the algorithms as needed. We will implement the software prototype, leveraging and integrating existing components where possible and implementing new components as needed. We will qua ...

The multidisciplinary area of GEOINT is changing and becoming more complex. A major driver of innovation in GEOINT collection and processing is artificial intelligence (AI). AI is being leveraged to help accomplish spatial analysis, change detection, and image or video triage tasks where filtering objects of interest from large volumes of data is critical. NGA is confronting the changing GEOINT l ...

At a high level, the primary technical objective of the proposed effort is to Identify, obtain, evaluate, and improve datasets; Investigate the use of Meta-Learning to improve the low-shot detection performance of the feed forward network;   Extend research in multi-branch multi-domain embedding networks and semantic layouts for low-shot detection in remote sensing imagery; and Develop and implem ...

Toyon proposes to research and develop algorithms for generalized salient change detection, and to incorporate these algorithms into software tools implemented on the cloud. Our approach leverages the two most promising methods from Phase I, both based on supervised learning. The first method is the entropy-based feature vector and corresponding neural network, which we will apply at a coarse sear ...