Abstract: An apparatus for classifying a contrast level of an image is provided. One or more processors execute instructions stored in one or more memory devices which configure the one or more processors to obtain an image from an image source, extract intensity values for each pixel of the obtained image, calculate a probability distribution for the obtained image representing a number of pixels at each unique pixel value, determine, from the calculated probability distribution, a spread value representing a series pixel values including at least a predetermined number of pixels at each pixel value in the series of pixel values and classify the obtained image a member of one of three classes based on the calculated probability distribution and the determined spread value.

Abstract: An apparatus for baseline estimation in input signal data is configured to retrieve input signal data (I(xi)) and to subtract baseline estimation data (ƒ(xi)) from the input signal data (I(xi)) to compute output signal data. The apparatus is further configured to compute the baseline estimation data (ƒ(xi)) from a convolution using a discrete Green's function (G(xi)).

Abstract: Provided are a learning data collection apparatus, a learning data collection method, and a program for collecting learning data to be used for efficient retraining.

Abstract: A non-transitory processor-readable medium stores code representing instructions to be executed by the processor. The code comprises code to cause the processor to receive a first image and a second image from a stereo camera pair disposed with a vehicle. The code causes the processor to detect, using a machine learning model, an object based on the first image, the object located within a pre-defined area within a vicinity of the vehicle. The code causes the processor to determine a distance between the object and the vehicle based on disparity between the first image and the second image. The code causes the processor to determine a longitudinal value of the vehicle based on the distance and a height of the vehicle. The code causes the processor to send an instruction to facilitate driving of the vehicle based on a road profile associated with the longitudinal value.

Abstract: A computer-implemented system and method for predicting female sex human offspring to result from a human embryo by processing video image data of the embryo. The method includes receiving image data derived from video of a target embryo taken at substantially real-time frame speed during an embryo observation period of time. The video contains recorded morphokinetic movement of the target embryo occurring during the embryo observation period of time. The movement is represented in the received image data and the received image data is processed using a model generated utilizing machine learning and correlated embryo outcome data.

Abstract: A computer-implemented system and method for predicting male sex bovine offspring to result from a bovine embryo by processing video image data of the embryo. The method includes receiving image data derived from video of a target embryo taken at substantially real-time frame speed during an embryo observation period of time. The video contains recorded morphokinetic movement of the target embryo occurring during the embryo observation period of time. The movement is represented in the received image data and the received image data is processed using a model generated utilizing machine learning and correlated embryo outcome data.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing deep learning to intelligently determine compression settings for compressing a digital image. For instance, the disclosed system utilizes a neural network to generate predicted perceptual quality values for compression settings on a compression quality scale. The disclosed system fits the predicted compression distortions to a perceptual distortion characteristic curve for interpolating predicted perceptual quality values across the compression settings on the compression quality scale. Additionally, the disclosed system then performs a search over the predicted perceptual quality values for the compression settings along the compression quality scale to select a compression setting based on a perceptual quality threshold. The disclosed system generates a compressed digital image according to compression parameters for the selected compression setting.

Abstract: This application relates to a target object detection method and apparatus, a non-transitory computer-readable storage medium, and a computer device. The method includes: obtaining a to-be-detected image; inputting the to-be-detected image into a target object detection model; generating, by the target object detection model, a prediction diagram corresponding to the to-be-detected image, the prediction diagram describing a relation degree to which pixels of the to-be-detected image belong to a target detection object; and performing region segmentation on the prediction diagram to obtain a target detection object region. In addition, a method and an apparatus for training an object detection model into the target object detection model, a non-transitory computer-readable storage medium, and a computer device are also provided.

Abstract: A computer-implemented system and method for predicting female sex bovine offspring to result from a bovine embryo by processing video image data of the embryo. The method includes receiving image data derived from video of a target embryo taken at substantially real-time frame speed during an embryo observation period of time. The video contains recorded morphokinetic movement of the target embryo occurring during the embryo observation period of time. The movement is represented in the received image data and the received image data is processed using a model generated utilizing machine learning and correlated embryo outcome data.

Abstract: An apparatus for recognizing an object in an image includes a preprocessing module configured to receive an image including an object and to output a preprocessed image by performing image enhancement processing on the received image to improve a recognition rate of the object included in the received image; and an object recognition module configured to recognize the object included in the image by inputting the preprocessed image to an input layer of an artificial neural network for object recognition.

Abstract: Techniques are generally described for object detection in image data. First image data comprising a three-dimensional model representing an object may be received. First background image data comprising a first plurality of pixel values may be received. A first feature vector representing the three-dimensional model may be generated. A second feature vector representing the first plurality of pixel values of the first background image data may be generated. A first machine learning model may generate a transformed representation of the three-dimensional model using the first feature vector. First foreground image data comprising a two-dimensional representation of the transformed representation of the three-dimensional model may be generated. A frame of composite image data may be generated by combining the first foreground image data with the first background image data.

Abstract: Among other things, one or more systems and/or techniques for visually augmenting regions within images are provided herein. An image of an object, such as a bag, is segmented to identify an item (e.g., a metal gun barrel). Features of the item are extracted from voxels representing the item within the image (e.g., voxels within a first region), such as a size, shape, density, and orientation of the item. Response to the features of the item matching predefined features of a target item to detect, one or more additional regions are identified, such as a second region proximate to the first region based upon a location of the second region corresponding to where a connected part of the item (e.g., a plastic handle of the gun) is predicted to be located. The one or more regions are visually distinguished within the image from other regions (e.g., colored, highlighted, etc.).

Abstract: Systems and methods are directed to inpainting video. More specifically, initial video data including a sequence of image frames containing missing or corrupted pixel information may be received. Optical flow displacement values and optical flow validity masks may be generated for neighboring image frames of initial video data. Image features from image feature maps of one or more neighboring image frames may be warp-shifted to image feature maps of a current image frame using the optical flow displacement values and warp-shifted image features from the feature maps of the one or more neighboring image frames may be selected based on one or more of the optical flow validity masks. A sequence of complete image frames may be generated based on the selected warp-shifted image features from the feature maps of the one or more neighboring image frames and image features from the image feature maps of the current image frame.

Abstract: Systems and methods described herein relate to training a machine-learning-based monocular depth estimator. One embodiment selects a virtual image in a virtual dataset, the virtual dataset including a plurality of computer-generated virtual images; generates, from the virtual image in accordance with virtual-camera intrinsics, a point cloud in three-dimensional space based on ground-truth depth information associated with the virtual image; reprojects the point cloud back to two-dimensional image space in accordance with real-world camera intrinsics to generate a transformed virtual image; and trains the machine-learning-based monocular depth estimator, at least in part, using the transformed virtual image.

Abstract: Systems and methods for human detection are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The target domain includes humans in one or more different scenes. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.

Abstract: Systems and methods for lane marking and road sign recognition are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The target domain includes one or more road scenes having lane markings and road signs. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing a reservoir computing neural network. In one aspect there is provided a reservoir computing neural network comprising: (i) a brain emulation sub-network, and (ii) a prediction sub-network. The brain emulation sub-network is configured to process the network input in accordance with values of a plurality of brain emulation sub-network parameters to generate an alternative representation of the network input. The prediction sub-network is configured to process the alternative representation of the network input in accordance with values of a plurality of prediction sub-network parameters to generate the network output. The values of the brain emulation sub-network parameters are determined before the reservoir computing neural network is trained and are not adjusting during training of the reservoir computing neural network.

Abstract: Systems and methods for obstacle detection are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The target domain includes one or more road scenes having obstacles. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.

Abstract: Systems, methods, and computer-readable for multi-spatial scale object detection include generating one or more object trackers for tracking at least one object detected from on one or more images. One or more blobs are generated for the at least one object based on tracking motion associated with the at least one object. One or more tracklets are generated for the at least one object based on associating the one or more object trackers and the one or more blobs, the one or more tracklets including one or more scales of object tracking data for the at least one object. One or more uncertainty metrics are generated using the one or more object trackers and an embedding of the one or more tracklets. A training module for detecting and tracking the at least one object using the embedding and the one or more uncertainty metrics is generated using deep learning techniques.

Abstract: Systems and methods for construction zone segmentation are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The target domain includes construction zones scenes having various objects. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.