Insurance Services Office, Inc.

University of Colorado

Venkata Subbarao Veeravarasapu

Maneesh Kumar Singh

Aurobrata Ghosh

Deepak Mittal

Aditya Singh

Terrance Edward Boult

Zheng Zhong

Steve Cruz

Terrance E Boult

Systems and methods for generating simulated scenes from open map data for machine learning are presented. The system includes an automatic scene generative pipeline that uses freely-available map information and random texture maps to create large-scale 3D urban scene layouts for supervised learning methods. The system generates synthetic datasets that have improved generalization capabilities with respect to a given target domain of interest using data from open maps and texture map from the same geographic locations. Data from the generation pipeline of the system improves a model's generalization to real image sets beyond arbitrarily-simulated sets or labeled real data from other geographical regions.

System and method for generating simulated scenes from open map data for machine learning

Computer vision systems and methods for automatic parcel alignment are provided. The system receives a geotagged aerial image, parcel information, and semantic information where each of the parcel and semantic information are overlaid on the geotagged aerial image. The system cleans the parcel information and the semantic information. The system optimizes the parcel information by grouping geo-registered parcels present in the geotagged aerial image into a plurality of islands and generating a plurality of parcel alignment solutions for each island of the plurality of islands. The system refines the plurality of parcel alignment solutions for each island and regularizes each island. The system generates a composite parcel alignment solution based on the refined plurality of parcel alignment solutions for each regularized island to align the geo-registered parcels of each regularized island with the geotagged aerial image.

Computer vision systems and methods for automatic alignment of parcels with geotagged aerial imagery

Systems and methods for detecting and aligning land property boundaries on aerial imagery are provided. The system receives an aerial imagery having land properties. The system applies a feature encoder having a plurality of levels to the aerial imagery. A first level of the plurality of levels includes a convolution block and a discrete wavelet transform layer. The discrete wavelet transform layer decomposes an input feature tensor to the first level into a low-frequency band and a high-frequency band. The high-frequency band is cached and processed with side-convolutional blocks before the high-frequency band are passed to a feature decoder. The system applies the feature decoder to an output of the feature encoder based at least in part on one of inverse discrete wavelet transform layers. The system determines boundaries of the one or more land properties based at least in part on a boundary cross-entropy loss function.

Computer vision systems and methods for detecting and aligning land property boundaries on aerial imagery

A system for improved localization of image forgery. The system generates a variational information bottleneck objective function and works with input image patches to implement an encoder-decoder architecture. The encoder-decoder architecture controls an information flow between the input image patches and a representation layer. The system utilizes information bottleneck to learn useful residual noise patterns and ignore semantic content present in each input image patch. The system trains a neural network to learn a representation indicative of a statistical fingerprint of a source camera model from each input image patch while excluding semantic content thereof. The system can determine a splicing manipulation localization by the trained neural network.

Growing community of inventors

Munich, Germany

Venkata Subbarao Veeravarasapu