Systems, devices, and methods for imaging a subject's retina and analyzing retinal images
Patent ID: WO2023122294A2
Abstract:
A monocular and/or a binocular system may be used to generate one or more images, or videos, of a subject's retina by scanning in one or two directions in one or two dimensions to, for example, measure and/or report fixation, smooth pursuit, and/or saccadic responses of the subject's eye. The scanning and/or image generation process may be optimized to correct for distortions in the subject's eye and/or improve SNR among one or a plurality of retinal images. In some cases, the retinal images may be used to train a retinal feature detection model and/or algorithm that may be used to make predictions and/or inferences regarding a visual pattern showing features of subsequently received retinal images. These models and/or predicted patterns present within the models may be used by the retinal feature detection model and/or algorithm to monitor features of the retina and, in some instances, track voluntary and/or involuntary eye motion.
Systems and methods for trip planning under uncertainty
Patent ID: US20190107406A1
Abstract:
Systems of an electrical vehicle and the operations thereof are provided. Electric vehicles may be routed from a start location to a destination through a network of charging stations explicitly considering time-varying uncertainty in both charging times, queueing times, and range. The routing objective may be a function of trip duration, electric vehicle state of charge at any time or location along the trip, uncertainty in the vehicle state of charge, the estimated trip duration, etc. Uncertainty in a distribution may be computed using an information-theoretic metric such as entropy. Waiting times may be estimated at an electric vehicle charging station given observed data for that station. An estimated waiting time at a charging station can be communicated directly to the owner of an electric vehicle owner or used to design a robust system for routing through charging stations.
交通摄像头参数获取方法、系统、介质及电子设备
Method, system, medium, and electronic device for obtaining traffic camera parameters
Patent ID: 202210327317.0
Abstract:
本发明提供一种交通摄像头参数获取方法、
系统、介质及电子设备；所述方法包括以下步骤：
获取二维车辆轨迹和三维车辆轨迹；基于所述二
维车辆轨迹和所述三维车辆轨迹计算交通摄像
头参数；本发明涉及基于摄像头检测到的二维车
辆轨迹与高精度的RTK GPS设备测得的三维地理
空间“探头”车辆轨迹，通过优化算法为高精度交
通摄像头求解参数；本发明以优化目标作为需要
求解和优化的参数函数，通过计算相应的数学函
数关系式来构建自动化摄像头参数求解器。
The present invention provides a method, system, medium, and electronic device for obtaining traffic camera parameters. The method includes the following steps: Obtain 2D vehicle trajectories and 3D vehicle trajectories. Based on the 2D vehicle trajectory and the 3D vehicle trajectory, calculate the traffic camera parameters. The invention involves using 2D vehicle trajectories detected by the camera and 3D geospatial 'probe' vehicle trajectories measured by high-precision RTK GPS devices. An optimization algorithm is used to solve for high-precision traffic camera parameters. The invention uses optimization objectives as the parameters to be solved and optimized. By calculating the corresponding mathematical functions, an automated camera parameter solver is constructed.
Modeling of the latent embedding of music using deep neural network
US20180276540A1
Abstract:
Methods and systems are provided for detecting and cataloging qualities in music. While both the data volume and heterogeneity of the digital music content is huge, it has become increasingly important and convenient to build a recommendation or search system to facilitate surfacing these content to the user or consumer community. Embodiments use deep convolutional neural network to imitate how human brain processes hierarchical structures in the auditory signals, such as music, speech, etc., at various timescales. This approach can be used to discover the latent factor models of the music based upon acoustic hyper-images that are extracted from the raw audio waves of music. These latent embeddings can be used either as features to feed to subsequent models, such as collaborative filtering, or to build similarity metrics between songs, or to classify music based on the labels for training such as genre, mood, sentiment, etc.
Personalized news recommendation engine
US10747833B2
Abstract:
A network crawler crawls one or more media sites to extract a plurality of titles for information contained in the one or more media sites. For example, the network crawler may extract the titles on the one or more media sites by identifying different computer formats and converting the titles in the different computer formats into a common computer format for comparison. User profiles which, includes user's interest are stored in a user profile interest database. A novel personalized news recommendation engine recommends news similar to the interest specified in a user profile, where maximum weighted matching is applied to score the similarity of news against user interest in the word2vec space.
Systems, devices, and methods for imaging a subject's retina and analyzing retinal images
Patent ID: WO2023122294A2
Abstract:
A monocular and/or a binocular system may be used to generate one or more images, or videos, of a subject's retina by scanning in one or two directions in one or two dimensions to, for example, measure and/or report fixation, smooth pursuit, and/or saccadic responses of the subject's eye. The scanning and/or image generation process may be optimized to correct for distortions in the subject's eye and/or improve SNR among one or a plurality of retinal images. In some cases, the retinal images may be used to train a retinal feature detection model and/or algorithm that may be used to make predictions and/or inferences regarding a visual pattern showing features of subsequently received retinal images. These models and/or predicted patterns present within the models may be used by the retinal feature detection model and/or algorithm to monitor features of the retina and, in some instances, track voluntary and/or involuntary eye motion.
Systems and methods for trip planning under uncertainty
Patent ID: US20190107406A1
Abstract:
Systems of an electrical vehicle and the operations thereof are provided. Electric vehicles may be routed from a start location to a destination through a network of charging stations explicitly considering time-varying uncertainty in both charging times, queueing times, and range. The routing objective may be a function of trip duration, electric vehicle state of charge at any time or location along the trip, uncertainty in the vehicle state of charge, the estimated trip duration, etc. Uncertainty in a distribution may be computed using an information-theoretic metric such as entropy. Waiting times may be estimated at an electric vehicle charging station given observed data for that station. An estimated waiting time at a charging station can be communicated directly to the owner of an electric vehicle owner or used to design a robust system for routing through charging stations.
交通摄像头参数获取方法、系统、介质及电子设备
Method, system, medium, and electronic device for obtaining traffic camera parameters
Patent ID: 202210327317.0
Abstract:
本发明提供一种交通摄像头参数获取方法、
系统、介质及电子设备；所述方法包括以下步骤：
获取二维车辆轨迹和三维车辆轨迹；基于所述二
维车辆轨迹和所述三维车辆轨迹计算交通摄像
头参数；本发明涉及基于摄像头检测到的二维车
辆轨迹与高精度的RTK GPS设备测得的三维地理
空间“探头”车辆轨迹，通过优化算法为高精度交
通摄像头求解参数；本发明以优化目标作为需要
求解和优化的参数函数，通过计算相应的数学函
数关系式来构建自动化摄像头参数求解器。
The present invention provides a method, system, medium, and electronic device for obtaining traffic camera parameters. The method includes the following steps: Obtain 2D vehicle trajectories and 3D vehicle trajectories. Based on the 2D vehicle trajectory and the 3D vehicle trajectory, calculate the traffic camera parameters. The invention involves using 2D vehicle trajectories detected by the camera and 3D geospatial 'probe' vehicle trajectories measured by high-precision RTK GPS devices. An optimization algorithm is used to solve for high-precision traffic camera parameters. The invention uses optimization objectives as the parameters to be solved and optimized. By calculating the corresponding mathematical functions, an automated camera parameter solver is constructed.
Modeling of the latent embedding of music using deep neural network
US20180276540A1
Abstract:
Methods and systems are provided for detecting and cataloging qualities in music. While both the data volume and heterogeneity of the digital music content is huge, it has become increasingly important and convenient to build a recommendation or search system to facilitate surfacing these content to the user or consumer community. Embodiments use deep convolutional neural network to imitate how human brain processes hierarchical structures in the auditory signals, such as music, speech, etc., at various timescales. This approach can be used to discover the latent factor models of the music based upon acoustic hyper-images that are extracted from the raw audio waves of music. These latent embeddings can be used either as features to feed to subsequent models, such as collaborative filtering, or to build similarity metrics between songs, or to classify music based on the labels for training such as genre, mood, sentiment, etc.
Personalized news recommendation engine
US10747833B2
Abstract:
A network crawler crawls one or more media sites to extract a plurality of titles for information contained in the one or more media sites. For example, the network crawler may extract the titles on the one or more media sites by identifying different computer formats and converting the titles in the different computer formats into a common computer format for comparison. User profiles which, includes user's interest are stored in a user profile interest database. A novel personalized news recommendation engine recommends news similar to the interest specified in a user profile, where maximum weighted matching is applied to score the similarity of news against user interest in the word2vec space.