What is the current state-of-the-art for image restoration and enhancement applied to degraded images acquired under less than ideal circumstances? Can the application of such algorithms as a pre-processing step improve image interpretability for manual analysis or automatic visual recognition to classify scene content? While there have been important advances in the area of computational photography to restore or enhance the visual quality of an image, the capabilities of such techniques have not always translated in a useful way to visual recognition tasks. Consequently, there is a pressing need for the development of algorithms that are designed for the joint problem of improving visual appearance and recognition, which will be an enabling factor for the deployment of visual recognition tools in many real-world scenarios. To address this, we introduce the UG$^2$dataset as a large-scale benchmark composed of video imagery captured under challenging conditions, and two enhancement tasks designed to test algorithmic impact on visual quality and automatic object recognition. Furthermore, we propose a set of metrics to evaluate the joint improvement of such tasks as well as individual algorithmic advances, including a novel psychophysics-based evaluation regime for human assessment and a realistic set of quantitative measures for object recognition performance. We introduce six new algorithms for image restoration or enhancement, which were created as part of the IARPA sponsored UG$^2$Challenge workshop held at CVPR 2018. Under the proposed evaluation regime, we present an in-depth analysis of these algorithms and a host of deep learning-based and classic baseline approaches. From the observed results, it is evident that we are in the early days of building a bridge between computational photography and visual recognition, leaving many opportunities for innovation in this area.

We present a light field processing method to quickly produce an image for pattern recognition. Unlike processing for aesthetic purposes, our objective is not to produce the best-looking image, but to produce a recognizable image as fast as possible. By leveraging the recognition algorithm's dynamic range and robustness to optical defocus, we develop carefully-chosen tradeoffs to ensure recognition at a much lower level of computational complexity. Capitalizing on the algorithm's dynamic range yields large speedups by minimizing the number of light field views used in refocusing. Robustness to optical defocus allows us to quantize the refocus parameter and minimize the number of interpolations. The resulting joint optimization is performed via dynamic programming to choose the set of views which, when combined, produce a recognizable refocused image in the least possible computing time. We demonstrate the improved recognition dynamic range of barcode scanning using a Lytro camera, and dramatic reductions in computational complexity on a low-power embedded processor.

Identifying similar narrative sections across longer documents would help identify key events within a corpus, enrich understanding of those events, provide a mechanism for organizing corpora according to their event content, and allow for bottom-up testing of theories of narrative. This paper proposes an automated method for narrative alignment across large textual corpora using techniques from natural language processing and similarity-based image segmentation. This method proceeds by segmenting each document into a series of events, constructs sequences of abstracted representations of those events, compares pairs of sequences to generate image matrices, segments the images, identifies similar segments to discover commonly occurring narrative units, and, finally, returns the source sentences to make the clusters of narrative similarity readable. Preliminary tests of elements of this method were conducted on a small heterogeneous corpus (<; 100 documents) and a moderate heterogeneous corpus (10k documents). Further implementation as described in this position paper is necessary to scale to the full 251k document corpus from which the moderate corpus was drawn.

Archives of human rights violations reports, by virtue of their poor metadata, basis in natural language, and scale, obscure fine grain analyses of violation event patterns. Cross-document coreference of victim or perpetrator occurrences from across a corpus is challenging, particularly when those mentions relate to different events. These challenges are emblematic of the transition from small scale to big data analysis in the humanities. This paper discusses these issues and proposes a framework to address these challenges so as to explore narrative construction and the formation of collective memory. Though our framework is based on processing human rights violation reports, it can be readily extended to support other big data problems in the humanities.

Free/Libre and Open source software are generally maintained by a group of developers contributing to the software voluntarily without the presence of any governing institution. Online collaboration platforms and sub-version systems allow developers from all over the world with the necessary skills to contribute to the software. Recently, there has been much interest in analyzing the developers' geographic location since it also serves as a socio-economic marker. In this paper we present our spatio-temporal visualization technique called Storygraph that shows the developers, developer locations and the frequency of commits based on the commit log in one integrated view. We also apply our techniques to the VCS of Rails, Homebrew and D3.js obtained from GitHub.

Applying advanced video technology to understand (human) activity and intent, including the interaction of multiple people and objects, is becoming increasingly important, especially for intelligent video surveillance. Recently, technical interest in video surveillance has moved from lowlevel processing modules, such as motion detection and motion tracking, to activity awareness and more complex scene understanding. This paper presents an integrated video surveillance system at Honeywell labs, which detects predefined activities with improved robustness. Also, we present the ‘new activity’ detection (pattern discovery), which can automatically capture new activities, and present the newly detected activities to the operator who checks for their validity and adds them into the activity models. Moreover, we present a torso angle feature, which represents people posture, to detect activities, such as people falling. We used real world data sets to show the effectiveness of our proposed method.

The Research Oriented Sensing Inexpensive (ROSI) robot is a new, highly capable mobile sensor node designed to enable collaborative applications. Not only capable of two-way communication, ROSI robots also possess a full suite of traditional small scale sensors which can be augmented with visual information from a digital camera via a semi-dedicated onboard processor. This is accomplished in the same form factor of the original Scouts using commodity components for a low cost. This work details an approach to localizing robots with respect to each other using a collaborative sensing mechanism. Determination of relative angles, overlapping field of view and direction are explored.