Abstract: A method for detecting boxes includes receiving a plurality of image frame pairs for an area of interest including at least one target box. Each image frame pair includes a monocular image frame and a respective depth image frame. For each image frame pair, the method includes determining corners for a rectangle associated with the at least one target box within the respective monocular image frame. Based on the determined corners, the method includes the following: performing edge detection and determining faces within the respective monocular image frame; and extracting planes corresponding to the at least one target box from the respective depth image frame. The method includes matching the determined faces to the extracted planes and generating a box estimation based on the determined corners, the performed edge detection, and the matched faces of the at least one target box.

Abstract: A method for detecting boxes includes receiving a plurality of image frame pairs for an area of interest including at least one target box. Each image frame pair includes a monocular image frame and a respective depth image frame. For each image frame pair, the method includes determining corners for a rectangle associated with the at least one target box within the respective monocular image frame. Based on the determined corners, the method includes the following: performing edge detection and determining faces within the respective monocular image frame; and extracting planes corresponding to the at least one target box from the respective depth image frame. The method includes matching the determined faces to the extracted planes and generating a box estimation based on the determined corners, the performed edge detection, and the matched faces of the at least one target box.

Abstract: A method for detecting boxes includes receiving a plurality of image frame pairs for an area of interest including at least one target box. Each image frame pair includes a monocular image frame and a respective depth image frame. For each image frame pair, the method includes determining corners for a rectangle associated with the at least one target box within the respective monocular image frame. Based on the determined corners, the method includes the following: performing edge detection and determining faces within the respective monocular image frame; and extracting planes corresponding to the at least one target box from the respective depth image frame. The method includes matching the determined faces to the extracted planes and generating a box estimation based on the determined corners, the performed edge detection, and the matched faces of the at least one target box.

Abstract: A method for detecting boxes includes receiving a plurality of image frame pairs for an area of interest including at least one target box. Each image frame pair includes a monocular image frame and a respective depth image frame. For each image frame pair, the method includes determining corners for a rectangle associated with the at least one target box within the respective monocular image frame. Based on the determined corners, the method includes the following: performing edge detection and determining faces within the respective monocular image frame; and extracting planes corresponding to the at least one target box from the respective depth image frame. The method includes matching the determined faces to the extracted planes and generating a box estimation based on the determined corners, the performed edge detection, and the matched faces of the at least one target box.

Abstract: A method for detecting boxes includes receiving a plurality of image frame pairs for an area of interest including at least one target box. Each image frame pair includes a monocular image frame and a respective depth image frame. For each image frame pair, the method includes determining corners for a rectangle associated with the at least one target box within the respective monocular image frame. Based on the determined corners, the method includes the following: performing edge detection and determining faces within the respective monocular image frame; and extracting planes corresponding to the at least one target box from the respective depth image frame. The method includes matching the determined faces to the extracted planes and generating a box estimation based on the determined corners, the performed edge detection, and the matched faces of the at least one target box.

Abstract: A method for detecting boxes includes receiving a plurality of image frame pairs for an area of interest including at least one target box. Each image frame pair includes a monocular image frame and a respective depth image frame. For each image frame pair, the method includes determining corners for a rectangle associated with the at least one target box within the respective monocular image frame. Based on the determined corners, the method includes the following: performing edge detection and determining faces within the respective monocular image frame; and extracting planes corresponding to the at least one target box from the respective depth image frame. The method includes matching the determined faces to the extracted planes and generating a box estimation based on the determined corners, the performed edge detection, and the matched faces of the at least one target box.

Abstract: A method for detecting boxes includes receiving a plurality of image frame pairs for an area of interest including at least one target box. Each image frame pair includes a monocular image frame and a respective depth image frame. For each image frame pair, the method includes determining corners for a rectangle associated with the at least one target box within the respective monocular image frame. Based on the determined corners, the method includes the following: performing edge detection and determining faces within the respective monocular image frame; and extracting planes corresponding to the at least one target box from the respective depth image frame. The method includes matching the determined faces to the extracted planes and generating a box estimation based on the determined corners, the performed edge detection, and the matched faces of the at least one target box.

Abstract: A method for detecting boxes includes receiving a plurality of image frame pairs for an area of interest including at least one target box. Each image frame pair includes a monocular image frame and a respective depth image frame. For each image frame pair, the method includes determining corners for a rectangle associated with the at least one target box within the respective monocular image frame. Based on the determined corners, the method includes the following: performing edge detection and determining faces within the respective monocular image frame; and extracting planes corresponding to the at least one target box from the respective depth image frame. The method includes matching the determined faces to the extracted planes and generating a box estimation based on the determined corners, the performed edge detection, and the matched faces of the at least one target box.

Abstract: A method for assessing sharing of items within a social network is provided. The method includes identifying a first sharing of a social item by a first user of a social network, determining one or more second sharings of the social item by one or more second users, the one or more second sharings being based on the first sharing. The method also includes determining a sharing score associated with the first user based on a number of the one or more second sharings, and updating a data structure based on the determined sharing score associated with the first user. The data structure stores respective sharing scores associated with the plurality of users of the social network. Systems and machine-readable media are also provided.

Abstract: A multi-phase process first trains a machine learned rating classifier, and then uses the rating classifier to automatically rate videos in a selected category in a way which mimics human rating. Panels of human viewers rate videos in tuples, and these tuples along with human preference data distilled from the ratings are used to create a training set that is used to train the machine learned rating classifier. The rating classifier becomes capable of predicting human preferences with regards to videos in the selected category. Optionally a second machine learned classifier can be trained to automatically identify videos in the selected category for the panels of human viewers to rate. The output of the multi-phase process can be used to highlight content that is predicted to be higher quality.

Abstract: A ranking system is described for adjusting quality distributions of items responsive to pairwise comparisons. The pairwise comparisons are selected for a user providing a preference between the items in the pairwise comparisons. The selection is determined based on the cost of an error in the rankings of items in combination with the likelihood there is an error in the item rankings. On receiving the comparison result from the user, the quality distributions are updated and can include a confidence modifier to determine the confidence the user's preference is reflective of the actual preference between the items.

Abstract: A mapping method includes using a first mobile unit to map two-dimensional features while the first mobile unit traverses a surface. Three-dimensional positions of the features are sensed during the mapping. A three-dimensional map is created including associations between the three-dimensional positions of the features and the map of the two-dimensional features. The three-dimensional map is provided from the first mobile unit to a second mobile unit. The second mobile unit is used to map the two-dimensional features while the second mobile unit traverses the surface. Three-dimensional positions of the two-dimensional features mapped by the second mobile unit are determined within the second mobile unit and by using the three-dimensional map.

Abstract: A localization system within a vehicle in one embodiment includes a global position system (GPS) receiver, a radar sensor, a data storage device including program instructions stored therein, a symbolic map stored within the data storage device, and a controller operatively coupled to the data storage device, the GPS receiver, and the radar sensor, the controller configured to execute the program instructions to analyze data from the GPS receiver, data from the radar sensor, and data from the stored symbolic map, and determine a probabilistic vehicle location based upon the analysis.

Abstract: A method for assisting in parallel parking includes providing a vehicle with a forward-looking camera and/or a backward-looking camera. The camera is used to capture an image of a parking area including at least one unoccupied parking space and a plurality of parking spaces occupied by other vehicles. A homography of the captured image is created. The homography is used to estimate an image of the parking area from an overhead viewpoint. A portion of the overhead image including the unoccupied parking space is displayed on a display screen within a passenger compartment of the vehicle.

Abstract: A mapping method includes using a first mobile unit to map two-dimensional features while the first mobile unit traverses a surface. Three-dimensional positions of the features are sensed during the mapping. A three-dimensional map is created including associations between the three-dimensional positions of the features and the map of the two-dimensional features. The three-dimensional map is provided from the first mobile unit to a second mobile unit. The second mobile unit is used to map the two-dimensional features while the second mobile unit traverses the surface. Three-dimensional positions of the two-dimensional features mapped by the second mobile unit are determined within the second mobile unit and by using the three-dimensional map.

Abstract: A method for assisting in parallel parking includes providing a vehicle with a forward-looking camera and/or a backward-looking camera. The camera is used to capture an image of a parking area including at least one unoccupied parking space and a plurality of parking spaces occupied by other vehicles. A homography of the captured image is created. The homography is used to estimate an image of the parking area from an overhead viewpoint. A portion of the overhead image including the unoccupied parking space is displayed on a display screen within a passenger compartment of the vehicle.