Provided are a method and device for obtaining a position of a stationary target. The method of obtaining a position of a stationary target may include generating a fusion track based on data collected from a radar and data collected from a camera, determining whether the fusion track is in a stationary state, in response to the fusion track being in the stationary state, collecting radar points associated with the fusion track, and obtaining a center point of the stationary target based on the collected radar points.

Location mapping and navigation user interfaces may be generated and presented via mobile computing devices. A mobile device may detect its location and orientation using internal systems, and may capture image data using a device camera. The mobile device also may retrieve map information from a map server corresponding to the current location of the device. Using the image data captured at the device, the current location data, and the corresponding local map information, the mobile device may determine or update a current orientation reading for the device. Location errors and updated location data also may be determined for the device, and a map user interface may be generated and displayed on the mobile device using the updated device orientation and/or location data.

A progressive localization method for text-to-video clip localization. The method comprises: first, respectively extracting features of two modes, namely a video mode and a text mode by using different feature extraction methods; then progressively selecting different step sizes, and learning the correlation between the video and the text in multiple stages; and finally, training a model in an end-to-end manner based on the correlation loss of each stage. Moreover, the fine time granularity stage is fused with information of the coarse time granularity stage by means of a condition feature update module and up-sampling connection, such that different stages are mutually promoted. Different stages can pay attention to clips with different time granularities, and the model can cope with the situation that the length of a target clip is obviously changed based on the interrelation between the stages.

A feature point detection apparatus for detecting feature points in image data includes an image data providing unit for providing the image data, a key point determination unit for determining key points in the image data, a feature determination unit for determining features associated with the key points, each describing a local environment of a key point in the image data, and a feature point providing unit for providing the feature points. A feature point is represented by the position of a key point in the image data and the associated features. The image data comprise intensity data and associated depth data, and the determination of the key points and the associated features is based on a local analysis of the image data in dependence on both the intensity data and the depth data.

The present teaching relates to method, system, medium, and implementations for detecting liveness. When an image is received with visual information claimed to represent a palm of a person, a region of interests (ROI) in the image that corresponds to the palm is identified. Each of a plurality of fake palm detectors individually generates an individual decision on whether the ROI corresponds to a specific type of fake palm that the fake palm detector is to detect. Such individual decisions from the plurality of fake palm detectors are combined to derive a liveness detection decision with respect to the ROI.

The described aspects and implementations enable efficient detection and classification of objects with machine learning models that deploy a bird's-eye view representation and are trained using depth ground truth data. In one implementation, disclosed are system and techniques that include obtaining images, generating, using a first neural network (NN), feature vectors (FVs) and depth distributions pixels of images, wherein the first NN is trained using training images and a depth ground truth data for the training images. The techniques further include obtaining a feature tensor (FT) in view of the FVs and the depth distributions, and processing the obtained FTs, using a second NN, to identify one or more objects depicted in the images.

The image matching apparatus (2000) acquires a ground-view image (20) and an aerial-view image (30). The image matching apparatus (2000) extracts features from the ground-view image (20). The image matching apparatus (2000) extracts features from the aerial-view image (30). The image matching apparatus (2000) extracts a plurality of partial aerial regions (32) from the aerial-view image (30), and extracts features from each partial aerial region (32). The image matching apparatus (2000) computes, for each partial aerial region (32), a combined aerial feature by combining the features of the partial aerial region (32) and the features of the aerial-view image (30). The image matching apparatus (2000) determines, for each partial aerial region (32), whether the partial aerial region (32) matches the ground-view image (20) by comparing the combined aerial feature of the partial aerial region (32) and the features of the ground-view image (20).

The present disclosure pertains to the field of health monitoring technologies, and discloses a life early warning system based on sensor acquisition, including a sign sensor, a camera, a location analysis module, an attachment location correction module, a sign detection module, an alarm feedback module, a detection optimizer, a medical comparison library, a medical platform, and a client, where the sign sensor is configured to attach to a specified location of a user body, and acquire user sign information in real time. In the present disclosure, a location of the sign sensor is analyzed by using a cascade network, which can ensure accuracy of an attachment location of each sensor, avoid reduction in precision of subsequent detection due to a sensor location abnormality, greatly improve detection accuracy, further prevent an abnormal sign report due to misusing by a child, and improve user experience.

A consensus-based decentralized multi-robot approach is presented for reconstructing a discrete distribution of features, modeled as an occupancy grid map, that represent information contained in a bounded planar 2D environment, such as visual cues used for navigation or semantic labels associated with object detection. The robots explore the environment according to a random walk modeled by a discrete-time discrete-state (DTDS) Markov chain and estimate the feature distribution from their own measurements and the estimates communicated by neighboring robots, using a distributed Chernoff fusion protocol. Under this decentralized fusion protocol, each robot's feature distribution converges to the ground truth distribution in an almost sure sense.

An information processing apparatus comprising, at least one first processor configured to carry out a first process on data input from at least one sensor to produce first processed data, a selector configured to select, according to a first predetermined condition, at least one of a plurality of second processes, and at least one second processor configured to receive the first processed data from the at least one first processor and to carry out the selected at least one of the plurality of second processes on the first processed data to produce second processed data, each of the plurality of second processes having a lower processing load than the first process.