Abstract: Aspects of the present disclosure provide a method for compressing a point cloud. The method includes determining a sub-division technique for the volume based on one or more numbers derived from a distribution of points in the volume, dividing the volume into a number of sub-volumes according to the sub-division technique, and determining whether each sub-volume of the sub-volumes is occupied by at least one point. The method includes generating a bit sequence for the volume comprising a control code that is based on the sub-division technique and an occupancy indicator that indicates whether or not each sub-volume is occupied by at least one point.

Abstract: A method of dynamically updating a feature database that contains features corresponding to a known target object includes providing an image, extracting a first set of features from within the captured image, and comparing the first set of features to the features stored in the feature database. If it is determined that the target object is present in the image then at least one of the extracted features of the first set that are not already included in the feature database are added to the feature database.

Abstract: A method of dynamically updating a feature database that contains features corresponding to a known target object includes providing an image, extracting a first set of features from within the captured image, and comparing the first set of features to the features stored in the feature database. If it is determined that the target object is present in the image then at least one of the extracted features of the first set that are not already included in the feature database are added to the feature database.

Abstract: Disclosed are a system, apparatus, and method for 3D object segmentation within an environment. Image frames are obtained from one or more depth cameras or at different times and planar segments are extracted from data obtained from the image frames. Candidate segments that comprise a non-planar object surface are identified from the extracted planar segments. In one aspect, certain extracted planar segments are identified as comprising a non-planar object surface, and are referred to as candidate segments. Confidence of preexisting candidate segments are adjusted in response to determining correspondence with a candidate segment. In one aspect, one or more preexisting candidate segments are determined to comprise a surface of a preexisting non-planar object hypothesis. Confidence in the non-planar object hypothesis is updated in response to determining correspondence with a candidate segment.

Abstract: A method of recognizing an object of interest in an image includes extracting a first set of features from within the image. Each extracted feature in the first set of features is then categorized as either blob-like or edge-like. A second set of features is then taken from the first set, where a number of the edge-like features to include in the second set of features is based on a relative number of edge-like features to blob-like features included in the first set of extracted features. An object of interest within the image is detected according to the second set of features.

Abstract: Systems, methods, and devices are described for capturing compact representations of three-dimensional objects suitable for offline object detection, and storing the compact representations as object representation in a database. One embodiment may include capturing frames of a scene, identifying points of interest from different key frames of the scene, using the points of interest to create associated three-dimensional key points, and storing key points associated with the object as an object representation in an object detection database.

Abstract: A method of recognizing an object of interest in an image includes extracting a first set of features from within the image. Each extracted feature in the first set of features is then categorized as either blob-like or edge-like. A second set of features is then taken from the first set, where a number of the edge-like features to include in the second set of features is based on a relative number of edge-like features to blob-like features included in the first set of extracted features. An object of interest within the image is detected according to the second set of features.

Abstract: Systems, apparatus and methods for triggering a depth sensor and/or limiting bandwidth and/or maintaining privacy are presented. By limiting use of a depth sensor to times when an optical image alone is insufficient, mobile device power is saved. Furthermore, by reducing a size of an optical image to only the portion of the image needed to detect an object, bandwidth is saved and privacy is maintained by not communicating unneeded or undesired information.

Abstract: Disclosed are a system, apparatus, and method for 3D object segmentation within an environment. Image frames are obtained from one or more depth cameras or at different times and planar segments are extracted from data obtained from the image frames. Candidate segments that comprise a non-planar object surface are identified from the extracted planar segments. In one aspect, certain extracted planar segments are identified as comprising a non-planar object surface, and are referred to as candidate segments. Confidence of preexisting candidate segments are adjusted in response to determining correspondence with a candidate segment. In one aspect, one or more preexisting candidate segments are determined to comprise a surface of a preexisting non-planar object hypothesis. Confidence in the non-planar object hypothesis is updated in response to determining correspondence with a candidate segment.

Abstract: The embodiments utilize OFDM symbols to communicate network IDs. The IDs are encoded into symbols utilizing the network IDs as seeds to scramble respective pilots that are then transmitted by utilizing the symbols. The pilots can be structured into a single OFDM symbol and/or multiple OFDM symbols. The single symbol structure for transmitting the network IDs is independent of the number of network ID bits and minimizes frequency offset and Doppler effects. The multiple symbol structure allows a much coarser timing accuracy to be employed at the expense of transmitting additional symbols. Several embodiments employ a search function to find possible network ID candidates from a transmitted symbol and a selection function to find an optimum candidate from a network ID candidate list.

Abstract: In one example, a method for exiting an object detection pipeline includes determining, while in the object detection pipeline, a number of features within a first tile of an image, wherein the image consists of a plurality of tiles, performing a matching procedure using at least a subset of the features within the first tile if the number of features within the first tile meets a threshold value, exiting the object detection pipeline if a result of the matching procedure indicates an object is recognized in the image, and presenting the result of the matching procedure.

Abstract: A method of dynamically updating a feature database that contains features corresponding to a known target object includes providing an image, extracting a first set of features from within the captured image, and comparing the first set of features to the features stored in the feature database. If it is determined that the target object is present in the image then at least one of the extracted features of the first set that are not already included in the feature database are added to the feature database.

Abstract: Systems, apparatus and methods for triggering a depth sensor and/or limiting bandwidth and/or maintaining privacy are presented. By limiting use of a depth sensor to times when an optical image alone is insufficient, mobile device power is saved. Furthermore, by reducing a size of an optical image to only the portion of the image needed to detect an object, bandwidth is saved and privacy is maintained by not communicating unneeded or undesired information.

Abstract: A difference in intensities of a pair of pixels in an image is repeatedly compared to a threshold, with the pair of pixels being separated by at least one pixel (“skipped pixel”). When the threshold is found to be exceeded, a selected position of a selected pixel in the pair, and at least one additional position adjacent to the selected position are added to a set of positions. The comparing and adding are performed multiple times to generate multiple such sets, each set identifying a region in the image, e.g. an MSER. Sets of positions, identifying regions whose attributes satisfy a test, are merged to obtain a merged set. Intensities of pixels identified in the merged set are used to generate binary values for the region, followed by classification of the region as text/non-text. Regions classified as text are supplied to an optical character recognition (OCR) system.

Abstract: Methods and apparatus for timing synchronization based on transitional pilot symbols. In an aspect, a method is provided for time tracking synchronization in an OFDM system. The method includes receiving at least one TDM pilot symbol comprising a plurality of modulated sub-carriers that are configured to provide a channel estimate having a length that extends up to a duration of an FFT used for data transmission. The method also includes determining one or both of an instantaneous and averaged channel estimates from the plurality of modulated sub-carriers, and calculating a timing offset based on one or both of the channel estimates. An apparatus includes a receiver configured to receive the at least one TDM pilot symbol, a channel estimator configured to determine the instantaneous and averaged channel estimates, and a time synchronizer configured to calculate a timing offset based on the channel estimates.

Abstract: A method of building a database for an object recognition system includes acquiring several multi-view images of a target object and then extracting a first set of features from the images. One of these extracted features is then selected and a second set of features is determined based on which of the first set of features include both, descriptors that match and keypoint locations that are proximate to the selected feature. If a repeatability of the selected feature is greater than a repeatability threshold and if a discriminability is greater than a discriminability threshold, then at least one derived feature is stored to the database, where the derived single feature is representative of the second set of features.

Abstract: Apparatus and methods for use in a wireless communication system are disclosed for recovery of timing tracking in a device, such as a wireless transceiver, after decoding errors occur due to incorrect timing tracking. In particular, the disclosed methods and apparatus recover timing tracking by monitoring a decoded signal in the transceiver for decoding errors occurring during a first frame, determining whether a number of decoding errors is greater than a predetermined amount, reacquiring a first pilot channel at a start of a subsequently received second frame when the number of decoding errors is determined to be greater than the predetermined amount, and resetting timing tracking of the transceiver based on the reacquired first pilot channel.

Abstract: Systems, methods, and devices are described for capturing compact representations of three-dimensional objects suitable for offline object detection, and storing the compact representations as object representation in a database. One embodiment may include capturing frames of a scene, identifying points of interest from different key frames of the scene, using the points of interest to create associated three-dimensional key points, and storing key points associated with the object as an object representation in an object detection database.

Abstract: In one example, a method for exiting an object detection pipeline includes determining, while in the object detection pipeline, a number of features within a first tile of an image, wherein the image consists of a plurality of tiles, performing a matching procedure using at least a subset of the features within the first tile if the number of features within the first tile meets a threshold value, exiting the object detection pipeline if a result of the matching procedure indicates an object is recognized in the image, and presenting the result of the matching procedure.

Abstract: Systems and methods are provided for channel estimation and timing synchronization in a wireless network. In an embodiment, a method is provided for time synchronization at a wireless receiver. The method includes decoding at least one TDM pilot symbol located at a transition between wide and local waveforms and processing the TDM pilot symbol to perform time synchronization for a wireless receiver. Methods for channel estimation at a wireless receiver are also provided. This includes decoding at least one TDM pilot symbol and receiving the TDM pilot symbol from an OFDM broadcast to facilitate channel estimation for a wireless receiver.