A system for physiological motion measurement is provided. The system may acquire a reference image corresponding to a reference motion phase of an ROI and a target image of the ROI corresponding to a target motion phase, wherein the reference motion phase may be different from the target motion phase. The system may identify one or more feature points relating to the ROI from the reference image, and determine a motion field of the feature points from the reference motion phase to the target motion phase using a motion prediction model. An input of the motion prediction model may include at least the reference image and the target image. The system may further determine a physiological condition of the ROI based on the motion field.

Lane line attribute detection methods and apparatuses, electronic devices, and intelligent devices are provided. The method includes: obtaining a pavement image collected by an image acquisition device mounted on an intelligent device; determining probability maps according to the pavement image, wherein the probability maps include at least two sets of: color, line type, and edge attribute probability maps, each color attribute probability map represents probabilities of points in the pavement image belonging to a color corresponding to the color attribute probability map, each line type attribute probability map represents probabilities of points in the pavement image belonging to a line type corresponding to the line type attribute probability map, and each edge attribute probability map represents probabilities of points in the pavement image belonging to an edge corresponding to the edge attribute probability map; and determining a lane line attribute in the pavement image according to the probability maps.

Methods and apparatus to improve driver-assistance vision systems using object detection based on motion vectors are disclosed. An example apparatus includes a motion vector object detection analyzer to generate a motion vector boundary box around an object represented in a first image, the motion vector boundary box generated based on a comparison of the first image relative to a second image. The example apparatus also includes a boundary box analyzer to: determine whether the motion vector boundary box corresponds to any artificial intelligence (AI)-based boundary box generated based on an analysis of the first image using an object detection machine learning model; and, in response to the motion vector boundary box not corresponding to any AI-based boundary box associated with the first image, associate a label with the motion vector boundary, the label to indicate the object detection machine learning model did not recognize the object in the first image.

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.

A system for selecting a treatment schema based on user willingness includes at least a first computing device configured to receive at least a user constitutional datum and at least a user ailment state from at least a second computing device. At least a first computing device is configured to determine, with an adaptive machine learning module, at least a remedial process label. At least a first computing device is configured to derive a remedial attribute list, wherein the remedial attribute list further comprises a plurality of remedial attribute list entries. At least a first computing device is configured to generate a plurality of treatment schemas. At least a first computing device is configured to select a treatment schema from the plurality of treatment schemas. At least a first computing device is configured to transmit the selected treatment schema to at least a second computing device.

During operation, a computer provides, based at least in part on an initial lighting preference of an individual, instructions specifying initial lighting states of one or more lights in a lighting configuration in an environment, where an initial lighting state of a given light includes an intensity and a color of the given light. Then, the computer receives sensor data specifying a non-verbal physical response of the individual to initial lighting states. Moreover, the computer determines, based at least in part on the non-verbal physical response, a type of reaction of the individual to the initial lighting state. Next, the computer selectively modifies, based at least in part on a lighting behavior history of the individual and the determined type of reaction, the initial lighting preference of the individual to obtain an updated lighting preference.

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.

System, methods, and other embodiments described herein relate to self-supervised training of a depth model for monocular depth estimation. In one embodiment, a method includes processing a first image of a pair according to the depth model to generate a depth map. The method includes processing the first image and a second image of the pair according to a pose model to generate a transformation that defines a relationship between the pair. The pair of images are separate frames depicting a scene of a monocular video. The method includes generating a monocular loss and a pose loss, the pose loss including at least a velocity component that accounts for motion of a camera between the training images. The method includes updating the pose model according to the pose loss and the depth model according to the monocular loss to improve scale awareness of the depth model in producing depth estimates.

A method for optimizing an on-device neural network model by using a Sub-kernel Searching Module is provided. The method includes steps of a learning device (a) if a Big Neural Network Model having a capacity capable of performing a targeted task by using a maximal computing power of an edge device has been trained to generate a first inference result on an input data, allowing the Sub-kernel Searching Module to identify constraint and a state vector corresponding to the training data, to generate architecture information on a specific sub-kernel suitable for performing the targeted task on the training data, (b) optimizing the Big Neural Network Model according to the architecture information to generate a specific Small Neural Network Model for generating a second inference result on the training data, and (c) training the Sub-kernel Searching Module by using the first and the second inference result.

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.