2 results about "Spatial coherence" patented technology

The present application relates to the technical field of ultrasonic nondestructive testing and industrial pipeline safety evaluation, in particular to a kind of stainless steel pipeline weld internal defect detection system, comprising: obtaining ultrasonic multi-angle scanning data, extracting waveform features and sound path information;Anisotropic propagation model is constructed, and sound beam deflection correction factor is solved;Generate corrected sound field spatial distribution data;Calculate the multi-view spatial coherence coefficient representing the consistency of signal phase under different sound beam paths;If the multi-view spatial coherence coefficient is greater than the coherence threshold, then determine that the corresponding signal is a defect echo, and reconstruct the defect spatial morphology;Otherwise, it is determined that the corresponding signal is structural scattering noise, and noise suppression processing is performed;Output the quality detection report of target component;The present application solves the missed detection hidden danger caused by geometric constraint and material attenuation, and ensures that the detection result of nuclear power and petrochemical high-risk pipeline under complex physical conditions meets the stringent full-coverage quality standard.

This invention discloses a novel multimodal semantic-spatial representation method for embodied perception and spatial reasoning, belonging to the field of embodied perception. Addressing the two major pain points of existing methods—insufficient spatial coherence in semantic reasoning and poor relation consistency and interpretability—this invention designs an optimization mechanism: on the one hand, it designs a transitive relation learning mechanism to correct relation conflicts and missing relations in reasoning under weak supervision, improving the completeness and logical consistency of spatial representation; on the other hand, relying solely on RGB images and depth maps, it integrates monocular depth estimation as a spatial modality into embodied perception, injecting implicit three-dimensional spatial attributes into the semantic structure, constructing a unified multimodal semantic-spatial representation, and enhancing the spatial coherence of semantic reasoning. This invention improves the performance of structured scene modeling and spatial grounding description generation through advanced spatial representation, and can be widely used in embodied spatial perception scenarios.