Search

There is a large growth in hardware and software systems capable of producing vast amounts of image and video data. These systems are rich sources of continuous image and video streams. This motivates researchers to build scalable computer vision systems that utilize data-streaming concepts for processing of visual data streams. However, several challenges exist in building large-scale computer vision systems. For example, computer vision algorithms have different accuracy and speed profiles depending on the content, type, and speed of incoming data. Also, it is not clear how to adaptively tune these algorithms in large-scale systems. These challenges exist because we lack formal frameworks for building and optimizing large-scale visual processing. This paper presents formal methods and algorithms that aim to overcome these challenges and improve building and optimizing large-scale computer vision systems. We describe a formal algebra framework for the mathematical description of computer vision pipelines for processing image and video streams. The algebra naturally describes feedback control and provides a formal and abstract method for optimizing computer vision pipelines. We then show that a general optimizer can be used with the feedback-control mechanisms of our stream algebra to provide a common online parameter optimization method for computer vision pipelines. [ABSTRACT FROM AUTHOR]

We propose a new method for remote sensing image matching. The proposed method uses an encoder subnetwork of an autoencoder pretrained on the GTCrossView data to construct image features. A discriminator network trained on the University of California Merced land-use/land-cover data set (LandUse) and the high-resolution satellite scene data set (SatScene) computes a match score between a pair of computed image features. We also propose a new network unit, called residual-dyad, and empirically demonstrate that networks that use residual-dyad units outperform those that do not. We compare our approach with both traditional and more recent learning-based schemes on the LandUse and SatScene data sets, and the proposed method achieves the state-of-the-art result in terms of mean average precision and average normalized modified retrieval rank (ANMRR) metrics. Specifically, our method achieves an overall improvement in performance of 11.26% and 22.41%, respectively, for LandUse and SatScene benchmark data sets. [ABSTRACT FROM AUTHOR]

Recent advancements in wireless networks and sensor technologies have enabled continuous monitoring of remote patients. This has opened doors for exploring new frontiers in the domain of smart healthcare, especially patient monitoring and diagnosis. Scientists and researchers have scouted the novel domain of human bond communications (HBC), which suggests detection and transmission of information using all five human senses (sight, smell, sound, touch, and taste). HBC not only enables these senses to be replicated at a remote location but also helps in diagnosis of several ailments through monitoring. Such a holistic communication medium is facilitated through specialized devices that help healthcare experts in making crucial and timely data-driven decisions for their patients. In this work, we present state-of-the-art research on HBC and possible interactions between HBC and remote healthcare. We present a model HBC framework to assist monitoring and diagnosis of attention deficit hyperactivity disorder patients. We also mention possible applications as well as challenges posed by HBC applications. [ABSTRACT FROM AUTHOR]

We developed a new method for extracting 3D flight trajectories of droplets using high-speed stereo capture. We noticed that traditional multi-camera tracking techniques fare poorly on our problem, in part due to the fact that all droplets have very similar shapes, sizes and appearances. Our method uses local motion models to track individual droplets in each frame. 2D tracks are used to learn a global, non-linear motion model, which in turn can be used to estimate the 3D locations of individual droplets even when these are not visible in any camera. We have evaluated the proposed method on both synthetic and real data and our method is able to reconstruct 3D flight trajectories of hundreds of droplets. The proposed technique solves for both the 3D trajectory of a droplet and its motion model concomitantly, and we have found it to be superior to 3D reconstruction via triangulation. Furthermore, the learned global motion model allows us to relax the simultaneity assumptions of stereo camera systems. Our results suggest that, even when full stereo information is available, our unsynchronized reconstruction using the global motion model can significantly improve the 3D estimation accuracy. [ABSTRACT FROM PUBLISHER]

Integrating personal camera-equipped mobile devices in traditional camera networks could enable a new class of mobile vision applications, but although integration is becoming technically feasible, consumer buy-in could be a thorny problem. [ABSTRACT FROM PUBLISHER]

This paper presents our research towards smart camera networks capable of carrying out advanced surveillance tasks with little or no human supervision. A unique centerpiece of our work is the combination of computer graphics, artificial life, and computer vision simulation technologies to develop such networks and experiment with them. Specifically, we demonstrate a smart camera network comprising static and active simulated video surveillance cameras that provides extensive coverage of a large virtual public space, a train station populated by autonomously self-animating virtual pedestrians. The realistically simulated network of smart cameras performs persistent visual surveillarice of individual pedestrians with minimal intervention. Our innovative camera control strategy naturally addresses camera aggregation and handoff, is robust against camera and communication failures, and requires no camera calibration, detailed world model, or central controller. [ABSTRACT FROM AUTHOR]