Abstract: The disclosure includes a system and method for performing image rectification using a single image and information identified from the single image. An image recognition application receives an input image, identifies a plurality of objects in the input image, estimates rectification parameters for the plurality of objects, identifies a plurality of candidate rectification parameters using a voting procedure on the rectification parameters for the plurality of objects, estimates final rectification parameters based on the plurality of candidate rectification parameters, computes a global transformation matrix using the final rectification parameters, and performs image rectification on the input image using the global transformation matrix.

Abstract: Systems and methods for performing three-dimensional semantic parsing of indoor spaces in accordance with embodiments of the invention are disclosed. In one embodiment, a method includes receiving input data representing a three-dimensional space, determining disjointed spaces within the received data by generating a density histogram on each of a plurality of axes, determining space dividers based on the generated density histogram, and dividing the point cloud data into segments based on the determined space dividers, and determining elements in the disjointed spaces by aligning the disjointed spaces within the point cloud data along similar axes to create aligned versions of the disjointed spaces normalizing the aligned version of the disjointed spaces into the aligned version of the disjointed spaces, determining features in the disjointed spaces, generating at least one detection score, and filtering the at least one detection score to determine a final set of determined elements.

Abstract: Velocity controllers in accordance with embodiments of the invention enable velocity estimation for tracked objects. One embodiment includes a tracker controller, including: a processor; and a memory containing: a velocity tracker application; a state space describing relationships between measured locations, calculated locations, and changes in locations, where the calculated locations in the state space correspond to unoccluded points on the surface of the tracked object; wherein the processor is configured by the velocity tracker application to: pre-process the state space to identify a tracked object; estimate a velocity of the tracked object using a location history calculated from the measured locations of the tracked object within the state space and a motion model calculated from the state space; and return the velocity of the tracked object.

Abstract: Velocity controllers in accordance with embodiments of the invention enable velocity estimation for tracked objects. One embodiment includes a tracker controller, including: a processor; and a memory containing: a velocity tracker application; a state space describing relationships between measured locations, calculated locations, and changes in locations, where the calculated locations in the state space correspond to unoccluded points on the surface of the tracked object; wherein the processor is configured by the velocity tracker application to: pre-process the state space to identify a tracked object; estimate a velocity of the tracked object using a location history calculated from the measured locations of the tracked object within the state space and a motion model calculated from the state space; and return the velocity of the tracked object.

Abstract: The disclosure includes a system and method for performing image rectification using a single image and information identified from the single image. An image recognition application receives an input image, identifies a plurality of objects in the input image, estimates rectification parameters for the plurality of objects, identifies a plurality of candidate rectification parameters using a voting procedure on the rectification parameters for the plurality of objects, estimates final rectification parameters based on the plurality of candidate rectification parameters, computes a global transformation matrix using the final rectification parameters, and performs image rectification on the input image using the global transformation matrix.

Abstract: A computer-implemented method for detecting objects by using subcategory-aware convolutional neural networks (CNNs) is presented. The method includes generating object region proposals from an image by a region proposal network (RPN) which utilizes subcategory information, and classifying and refining the object region proposals by an object detection network (ODN) that simultaneously performs object category classification, subcategory classification, and bounding box regression. The image is an image pyramid used as input to the RPN and the ODN. The RPN and the ODN each include a feature extrapolating layer to detect object categories with scale variations among the objects.

Abstract: A computer-implemented method for training a convolutional neural network (CNN) is presented. The method includes extracting coordinates of corresponding points in the first and second locations, identifying positive points in the first and second locations, identifying negative points in the first and second locations, training features that correspond to positive points of the first and second locations to move closer to each other, and training features that correspond to negative points in the first and second locations to move away from each other.

Abstract: A system and method for determining an object or product represented in an image is disclosed. The system receives a first image, determines a region of interest in the first image, determines a classification score for the region of interest using a convolutional neural network that assigns the region of interest the classification score corresponding to a class, and identifies a first product in the first image based on the classification score.

Abstract: A method to reconstruct 3D model of an object includes receiving with a processor a set of training data including images of the object from various viewpoints; learning a prior comprised of a mean shape describing a commonality of shapes across a category and a set of weighted anchor points encoding similarities between instances in appearance and spatial consistency; matching anchor points across instances to enable learning a mean shape for the category; and modeling the shape of an object instance as a warped version of a category mean, along with instance-specific details.

Abstract: Velocity controllers in accordance with embodiments of the invention enable velocity estimation for tracked objects. One embodiment includes a tracker controller, including: a processor, and a memory containing: a velocity tracker application; a state space describing relationships between measured locations, calculated locations, and changes in locations, where the calculated locations in the state space correspond to unoccluded points on the surface of the tracked object; wherein the processor is configured by the velocity tracker application to: pre-process the state space to identify a tracked object; estimate a velocity of the tracked object using a location history calculated from the measured locations of the tracked object within the state space and a motion model calculated from the state space; and return the velocity of the tracked object.

Abstract: A method for monitoring construction progress may include storing in memory multiple unordered images obtained from photographs taken at a site; melding the multiple images to reconstruct a dense three-dimensional (3D) as-built point cloud model including merged pixels from the multiple images in 3D space of the site; rectifying and transforming the 3D as-built model to a site coordinate system existing within a 3D as-planned building information model (“as-planned model”); and overlaying the 3D as-built model with the 3D as-planned model for joint visualization thereof to display progress towards completion of a structure shown in the 3D as-planned model. The processor may further link a project schedule to the 3D as-planned model to generate a 4D chronological as-planned model that, when visualized with the 3D as-built point cloud, provides clash detection and schedule quality control during construction.

Abstract: A method to reconstruct 3D model of an object includes receiving with a processor a set of training data including images of the object from various viewpoints; learning a prior comprised of a mean shape describing a commonality of shapes across a category and a set of weighted anchor points encoding similarities between instances in appearance and spatial consistency; matching anchor points across instances to enable learning a mean shape for the category; and modeling the shape of an object instance as a warped version of a category mean, along with instance-specific details.

Abstract: Disclosed are methods and apparatus for obtaining the shape of an object by observing silhouettes of the object. At least one point light source is placed in front of the object, thereby casting a shadow of the object on a translucent panel that is placed behind the object. A camera, or other imaging device, captures an image of the shadow from behind the translucent panel. The object's full silhouette is obtained from the image of the shadow as the region of the shadow is substantially darker than the region outside of the shadow. The full silhouette thus obtained may be processed by any suitable shape from silhouette algorithm, and thus objects are not limited in topological type. A color image of the object can optionally be obtained simultaneously with the shadow image using a camera placed on the same side of the object as the light source.

Abstract: Disclosed are methods and apparatus for obtaining the shape of an object by observing silhouettes of the object. At least one point light source is placed in front of the object, thereby casting a shadow of the object on a translucent panel that is placed behind the object. A camera, or other imaging device, captures an image of the shadow from behind the translucent panel. The object's full silhouette is obtained from the image of the shadow as the region of the shadow is substantially darker than the region outside of the shadow. The full silhouette thus obtained may be processed by any suitable shape from silhouette algorithm, and thus objects are not limited in topological type. A color image of the object can optionally be obtained simultaneously with the shadow image using a camera placed on the same side of the object as the light source.