A method includes receiving a first image, receiving a motion dataset, determining a motion level, determining an initialization state, and determining a tracking level. In a first condition, the method includes generating a first image pyramid, detecting a plurality of features in the first image pyramid using a first detector threshold, and generating a first set of detected keypoints from the plurality of features. In a second condition, the method includes generating a second image pyramid, detecting the plurality of features in the second image pyramid using a second detector threshold, the second detector threshold being less restrictive than the first detector threshold, and generating a second set of detected keypoints. In a third condition, the method includes detecting the plurality of features in the first image according to the first detector threshold and generating a third set of detected keypoint.

A method includes receiving a first image, receiving a motion dataset, determining a motion level, determining an initialization state, and determining a tracking level. In a first condition, the method includes generating a first image pyramid, detecting a plurality of features in the first image pyramid using a first detector threshold, and generating a first set of detected keypoints from the plurality of features. In a second condition, the method includes generating a second image pyramid, detecting the plurality of features in the second image pyramid using a second detector threshold, the second detector threshold being less restrictive than the first detector threshold, and generating a second set of detected keypoints. In a third condition, the method includes detecting the plurality of features in the first image according to the first detector threshold and generating a third set of detected keypoint.

A method for controlling a distance measurement apparatus including a light emitting device capable of changing a direction of emission of a light beam and a light receiving device that detects a reflected light beam includes acquiring data representing a plurality of images acquired at different points in time by an image sensor that acquires an image of a scene, determining, on the basis of the data representing the plurality of images, a degree of priority of distance measurement of one or more physical objects included in the plurality of images, and executing distance measurement of the one or more physical objects by causing the light emitting device to emit the light beam in a direction corresponding to the degree of priority and in an order corresponding to the degree of priority and causing the light receiving device to detect the reflected light beam.

A method for controlling a distance measurement apparatus including a light emitting device capable of changing a direction of emission of a light beam and a light receiving device that detects a reflected light beam includes acquiring data representing a plurality of images acquired at different points in time by an image sensor that acquires an image of a scene, determining, on the basis of the data representing the plurality of images, a degree of priority of distance measurement of one or more physical objects included in the plurality of images, and executing distance measurement of the one or more physical objects by causing the light emitting device to emit the light beam in a direction corresponding to the degree of priority and in an order corresponding to the degree of priority and causing the light receiving device to detect the reflected light beam.

Techniques are provided for recognition of activity in a sequence of video image frames that include depth information. A methodology embodying the techniques includes segmenting each of the received image frames into a multiple windows and generating spatio-temporal image cells from groupings of windows from a selected sub-sequence of the frames. The method also includes calculating a four dimensional (4D) optical flow vector for each of the pixels of each of the image cells and calculating a three dimensional (3D) angular representation from each of the optical flow vectors. The method further includes generating a classification feature for each of the image cells based on a histogram of the 3D angular representations of the pixels in that image cell. The classification features are then provided to a recognition classifier configured to recognize the type of activity depicted in the video sequence, based on the generated classification features.

Techniques are provided for recognition of activity in a sequence of video image frames that include depth information. A methodology embodying the techniques includes segmenting each of the received image frames into a multiple windows and generating spatio-temporal image cells from groupings of windows from a selected sub-sequence of the frames. The method also includes calculating a four dimensional (4D) optical flow vector for each of the pixels of each of the image cells and calculating a three dimensional (3D) angular representation from each of the optical flow vectors. The method further includes generating a classification feature for each of the image cells based on a histogram of the 3D angular representations of the pixels in that image cell. The classification features are then provided to a recognition classifier configured to recognize the type of activity depicted in the video sequence, based on the generated classification features.

Systems and methods for perceiving a field around a mobile device include a sensor system has a distance sensor arranged on a mobile device. The sensor system captures distance measurements of a field of view. The distance measurements are captured at a unique set of angular scan positions per revolution of the distance sensor over a sequence of scan rotations. A perception system generates a three-dimensional point cloud representation of the field of view based on the distance measurements for each scan rotation in the sequence of scan rotations. The perception system generates a composite three-dimensional depth map of the field of view by compiling each of the three-dimensional point cloud representations for the sequence of scan rotations. Each of the three-dimensional point cloud representations has a resolution that is lower than a resolution of the composite three-dimensional depth map of the field of view.

An image-based method of modeling and rendering a three-dimensional model of an object is provided. The method comprises: obtaining a three-dimensional point cloud at each frame of a synchronized, multi-view video of an object, wherein the video comprises a plurality of frames; extracting a feature descriptor for each point in the point cloud for the plurality of frames without storing the feature descriptor for each frame; producing a two-dimensional feature map for a target camera; and using an anti-aliased convolutional neural network to decode the feature map into an image and a foreground mask.

The present disclosure discloses a path planning method and device and a mobile device. The method comprises: collecting environmental information in a viewing angle by a sensor of a mobile device, processing the environmental information by using an SLAM algorithm, and constructing a grid map; dividing the grid map to obtain a plurality of pixel blocks, using an area constituted of pixel blocks not occupied by obstacles as a search area for path planning, and obtaining a processed grid map; determining reference points by using pixel points in the search area, and deploying topological points on the processed grid map according to the reference point determined and constructing a topological map; and calculating an optimal path from a starting point to a preset target point by using a predetermined algorithm according to the topological map constructed. The present disclosure improves path planning efficiency and saves storage resources.

A method of providing image includes obtaining at least one first image of a surrounding area (52) from a first camera (26, 33, 38A, 38B, 40A, and 40B). At least one second image of the surrounding area (52) is obtained from a second camera (26, 33, 38A, 38B, 40A, and 40B). The at least one first image is fused with the at least one second image to generate a three-dimensional model (51) of the surrounding area (52). A first image (54A) of the three dimensional model is provided to a display by determining a first position of an operator. A second image (54B) of the three-dimensional model is provided to the display by determining when the operator is in a second position to simulate motion parallax.