4 results about "Cost aggregation" patented technology

This invention belongs to the field of production cost management and cost accounting, specifically involving a method, equipment, and medium for dynamic reconstruction of hierarchical codes in a cost calculation BOM. The method constructs a cost calculation BOM, assigns initial hierarchical codes, and detects cyclic nodes. Based on cyclic node information and calculation requirements, an adjustment strategy is determined, and a unified hierarchical reconstruction based on material codes or cost centers is performed. Hierarchical aggregation and alignment are performed on associated materials of joint by-products and object groups. The method achieves dynamic optimization of the BOM hierarchical codes through cyclic node awareness strategy selection, unified hierarchical reconstruction, and collaborative adjustment of special nodes. Reliability of cost convolution calculation is ensured through cyclic node detection and strategy binding. Hierarchical unification based on material codes or cost centers eliminates hierarchical redundancy for identical materials, improving the accuracy of cost aggregation. Collaborative adjustment of the hierarchical levels of joint by-products and associated materials of object groups ensures consistency between the cost convolution path and process configuration.

The present application relates to the technical field of three-dimensional reconstruction, and in particular to an object three-dimensional reconstruction system based on deep learning, which introduces an adaptive cost aggregation method with visibility perception for cost volume aggregation, acquires the visibility of pixel points in the view through a network, and can improve the reconstruction integrity of the occluded area; a variance-based method is used to predict the disparity range of each pixel, and a spatially-varying depth hypothesis surface is constructed for depth estimation in the next stage, and a residual and channel attention guided fusion depth map optimization module is proposed in the last stage to obtain an optimized depth map; an improved depth map fusion algorithm is used to combine the pixel point and 3D point re-projection error for consistency checking to obtain a dense point cloud. Quantitative and qualitative comparison results of the present application and other methods on the DTU dataset show that the present application can reconstruct a scene with better details, and achieves the purposes of reducing GPU memory consumption and computation time.

A method and a system for extracting a dense disparity map based on multi-sensor fusion are provided. The method includes: obtaining a left-eye image and a right-eye image in a same road scenario, and point cloud information about the road scenario; generating an initial cost volume map set in accordance with the left-eye image, the right-eye image and the point cloud information; performing multidirectional cost aggregation in accordance with the point cloud information and the initial cost volume map set, and creating an energy function in accordance with the cost aggregation; and solving an optimum disparity for each pixel in the left-eye image in accordance with the energy function, so as to generate the dense disparity map.

This invention discloses a robust stereo matching method based on feature pyramids and attention perception, comprising: setting a feature extraction pyramid to process the input binocular stereo image, and obtaining multi-scale feature maps of the left and right view input images respectively; constructing a multi-scale cost volume pyramid using the multi-scale feature maps, and implementing feedback interaction and cross-scale cost aggregation between cost volumes of different scales; converting the cost volume pyramid into a probability value pyramid using a softmax function, and processing the probability value pyramid using a soft-argmin function to generate an initial disparity map; designing a saliency attention perception module to extract and generate attention feature maps in the shallow layers of the stereo matching network, and fusing the feature maps with the initial disparity map to obtain a refined disparity map. This invention can effectively correct erroneous matching points, restore lost image details and sharp object edges, improve the robustness and precision of disparity prediction, and generate a fine and accurate disparity map.