Skip to main content

Graphics/Visualization/Image

Latest Innovations
Tie Strength Prediction and WeMeddle A computer-implemented method of predicting tie strength between persons within a social media network includes: modeling tie strengths between a user of... Read More A computer-implemented method of predicting tie strength between persons within a social media network includes: modeling tie strengths between a user of the social media network and connected persons in the network as a combination of: a plurality of predictive variables, interactions between dimensions of the predictive variables, and network structure of the social media network; altering or filtering a stream of social media content from the connected persons using the tie strength as associated with the respective connected persons according to the modeling; and delivering the altered or filtered stream of social media content to a communications device of the user.
Fast and Accurate Quantum Chemistry Simulations via Multiobjective Genetic Algorithms Embodiments of the present invention provide, among other things, methods, apparatus, and systems for tuning a semiempirical process for predicting energy... Read More Embodiments of the present invention provide, among other things, methods, apparatus, and systems for tuning a semiempirical process for predicting energy for different molecular configurations. In an example method, an energy value and an energy gradient are determined for each of a plurality of molecular configurations using an accurate method. A functional form of the semiempirical process is optimized using the determined energy values and energy gradients via multiobjective optimization. The functional form relates one or more parameters to energy values and energy gradients.
A Trio of Innovative Imaging Technologies 3-D Insertion into Photographs (TF11149) Professor David Forsyth and his team have developed a program that renders... Read More 3-D Insertion into Photographs (TF11149) Professor David Forsyth and his team have developed a program that renders synthetic objects into legacy photographs. This allows for the insertion of 3-D objects or animations into photos with highly realistic results. Existing methods require measurements of the room or additional photos while this new program does not The film, advertising, and video game industries all use object insertion techniques Current working prototype that functions as an add-in to existing software This technology could also be seamlessly integrated into 3-D rendering platforms A web-based prototype is being developed to enable public testing Relighting Photo Fragments (TF12015) The second program that the University is offering is for relighting image fragments. This software was also developed by Professor David Forsyth and and his team. It extracts fragments of photos and inserts them into other photos with realistic lighting. Estimates 3-D geometry and surface properties of a fragment This program could easily be added to a plug-in for 3-D modeling software Works as a valuable complement to the previously mentioned technology Fully functional prototype has been developed Textureshop (TF04006) The University is also offering Textureshop, a program that allows texture synthesis in photographic editing. This software was developed by Professor John Hart and his team. This program does not require the use of a 3-D mesh to map texture onto a surface in an image Significantly reduces time and effort to map a texture onto 3-D surface Relies on a 2-D imaging technique called graphcut
Barcode and Software for Identifying Insects in Digital Images Researchers working with the lab of Gene Robinson have developed a custom bar code called "bcode" with dimension of 2.1mmX2.1mm which can easily be put on insects and then... Read More Researchers working with the lab of Gene Robinson have developed a custom bar code called "bcode" with dimension of 2.1mmX2.1mm which can easily be put on insects and then tracked through a custom computer vision software. The bcodes can be printed cheaply using office printer at 600dpi.
Forecasting 3D Movement While machines that analyze movement work well, models that anticipate are the future of machine learning. Using static relations to predict future movement results in... Read More While machines that analyze movement work well, models that anticipate are the future of machine learning. Using static relations to predict future movement results in less accurate forecasting because relations between static entities change over time. This technology uses dynamic Neural Relational Inference to predict an outcome for each static relation over time, resulting in more accurate forecasts.
Football Training Tools This suite of tools can be used to improve the performance of a football program. The tools focus on training and preparation and incorporate mobile, virtual reality, and... Read More This suite of tools can be used to improve the performance of a football program. The tools focus on training and preparation and incorporate mobile, virtual reality, and data analytics to get the most out of the football team. Players can see custom formations in a mobile or VR setting and can take the perspective of any position on the field plus several aerial views. This allows for players to easily prepare for opponents and better train by seeing formations from their respective positions on the field. Additionally, this suite includes a team management system. This tool allows coaches to visualize the depth chart and incorporates a play/game-based grading system.
I-RIPRAP: Computer Vision Software for Automated Size and Shape Characterization of Riprap in Stockpile Images Researchers at the University of Illinois have developed a new software for size and shape characterization of riprap materials using image analysis. Riprap is a... Read More Researchers at the University of Illinois have developed a new software for size and shape characterization of riprap materials using image analysis. Riprap is a collection of large broken stones or concrete used along roadways or shoreline as a means of erosion and sediment control. Riprap analysis is currently done manually and is labor intensive and time consuming. This software was developed based on deep learning techniques and provides user-independent image segmentation analysis. This software provides more advances modules for the size and shape characterization than other available methods.
A Model Net Utilizing Temporal Information for Video Object Segmentation Dr. Schwing has developed a model with a temporal backbone that allows video object segmentation. This allows for the model to compare images frame by frame and create a... Read More Dr. Schwing has developed a model with a temporal backbone that allows video object segmentation. This allows for the model to compare images frame by frame and create a propagated image in order to identify occluded objects more accuractely. The previous method of a single image analysis sometimes caused issues in the object getting lost or misidentified by the algorithms. This technology is particularly useful in autonomous driving features for lane changes, and other maneuvers. It also has potential uses in tracking software for security purposes.
D-AnoGAN for Anomaly Detection Researchers have created a Generative Adversarial Network (GAN) for anomaly detection in manufacturing. By deploying a method that clusters data and individually assesses... Read More Researchers have created a Generative Adversarial Network (GAN) for anomaly detection in manufacturing. By deploying a method that clusters data and individually assesses manifolds for anomalies, this method significantly outperforms other GANs in testing. Within particular datasets, D-AnoGAN can be trained to detect industry-specific anomalies with a very low error rate.

Pages