7 results about "Spatial change" patented technology

The embodiment of the invention provides a three-dimensional space change detection method and device, equipment and a storage medium, and relates to the field of digital image processing. The method comprises the following steps: acquiring image sequences of the same area shot by the unmanned aerial vehicle in two periods; for each image sequence, performing point cloud reconstruction on the region based on the image sequence to obtain the group of point cloud data; point cloud registration is carried out according to the similarity between the feature descriptors of all the points in the two sets of point cloud data, a matching point pair set comprising a plurality of matching point pairs is obtained, and two points in each matching point pair belong to two pieces of point cloud data and are closest to each other; and for each matching point pair, geometric information of two points in the matching point pair in respective point cloud data is acquired, and if it is determined that the difference between the two pieces of geometric information meets a preset difference condition, it is determined that the corresponding position of the matching point pair in the region is changed. According to the embodiment of the invention, the problem of insufficient spatial change detection precision in a complex scene is solved.

An apparatus, method and computer program is described comprising: detecting, at a second user device, one or more display patterns displayed at a display of a first user device, wherein the one or more display patterns comprise features with spatial variations configured to be detected by a radar module of the second user device; determining at least one of an orientation, position, or size of the first user device based, at least in part, on the one or more display patterns; and determining at least one of an orientation or position of the second user device relative to the first user device within a coordinate system of the first user device.

The invention relates to the technical field of human-computer interaction, and discloses a motion track reproduction method and device, computer equipment and a storage medium. The method comprises the steps of collecting respective motion data of a first object and a second object; based on the motion data, acquiring spatial change information of the first object relative to the second object, including relative pose change and relative position change of the first object; spatial change information of the first object relative to the second object is analyzed, and independent motion data, including pose change and position change, of the first object in the space relative to the second object is separated; and reproducing a motion track of the first object based on the independent motion data. The motion data of the first object and the motion data of the second object are subjected to conjoint analysis, the relative space relation between the first object and the second object is analyzed, interference factors generated by driving of the second object are effectively eliminated, the independent motion data of the first object are extracted, and misjudgment caused by coupling influence in a traditional method is avoided.

An embodiment relates to a computer-implemented method for denoising a noisy image. The method includes obtaining a noisy input image and estimating a time map (214) based on the noisy input image and noise in the noisy input image, where the time map is spatially varying, and the method includes performing a diffusion process on the noisy input image over two or more time steps. At each time step, the method includes estimating a denoised image based on the noisy input image, a current time-step image, and a time step using a machine-learned model; obtaining a next time-step image based on the denoised image and the current time-step image; updating, for each pixel, the next time-step image with a corresponding value from the denoised image; setting the next time-step image as the current time-step image; and decrementing the time step. The estimating, obtaining, updating, setting, and decrementing are repeated while the time step is positive. The method further includes outputting the denoised image.

This application relates to the field of optical measurement technology, and in particular to a thickness detection method and a non-contact optical scanning system, comprising: acquiring a two-dimensional characterization image of the sample to be measured; determining an effective detection area; planning a detection path; acquiring raw thickness data of multiple feature sampling points along the detection path; identifying candidate anomalies among the feature sampling points, wherein candidate anomalies are feature sampling points whose spatial change rate exceeds a set threshold; after identifying candidate anomalies, a first correction process can be executed, including: performing region segmentation on the two-dimensional characterization image to generate an attribute mask for distinguishing regions with different physical properties; extracting local neighborhood attribute features of the corresponding positions of candidate anomalies in the attribute mask; correcting the attributes of candidate anomalies; and filtering the raw thickness data of multiple feature sampling points based on the corrected attributes to generate the thickness of the sample to be measured. This application can demonstrate extremely high efficiency in high-precision measurement and large-scale automated production.

A method for determining dimensional data of an object includes emitting terahertz radiation by a first transmitter onto a surface of the object. The terahertz radiation emitted by the first transmitter is received by a first receiver after the terahertz radiation has passed through the object. Terahertz radiation comprising a bandwidth of less than 5% of a carrier frequency of the terahertz radiation is emitted by a second transmitter onto at least one location on the surface of the object. The terahertz radiation emitted by the second transmitter is received by a second receiver after the terahertz radiation has passed through the object. A dimension of the object is determined from one of: (i) the terahertz radiation received by the second transmitter; and (ii) a temporal or spatial change of the terahertz radiation received by the second receiver in consideration of that received by the first receiver.

The invention provides an all-weather robust multimode image fusion method driven by a fine-grained language instruction. The method comprises the following steps: firstly, analyzing a language instruction input by a user to obtain a function condition of a degradation type which is specified to be removed, and determining a space condition of a region which needs to be enhanced; and then processing function conditions and space conditions through a multi-condition coupling network to generate composite control priori, thereby providing a high-quality interaction medium for a dynamic adjustment fusion process. And further seamlessly embedding the generated compound control prior into the fusion process by using a mixed attention fusion module, thereby realizing controllable information fusion. And finally, under the joint constraint of degradation perception reconstruction loss and language feature alignment loss, driving the network to follow a user instruction, and realizing robust fusion in a composite degradation scene with spatial variation. The method has better degradation removal capability and information integration capability, realizes high-quality scene representation under severe conditions, and can provide clean, clear and pleasant fusion visual results.