13 results about "Map decoding" patented technology

Systems and methods for error detection in quantum computing systems are provided. In one example, the method includes obtaining a multi-dimensional quantum error detection map. The multi-dimensional quantum error detection map represents one or more quantum error detection measurements over a period of time. The method includes determining a partitioning scheme and a fusion scheme for the multi-dimensional quantum error detection map based at least in part on the decoding delay and the fusion delay. The method includes partitioning the multi-dimensional quantum error detection map into a plurality of blocks based at least in part on the partitioning scheme. The method includes decoding each of the plurality of blocks. The method includes fusing the plurality of blocks into a decoded detection map based at least in part on the fusion scheme. The method includes operating a quantum computing system based at least in part on the decoded detection map.

This application discloses a land use change prediction method, apparatus, device, and medium based on map representation generation learning, relating to the fields of spatiotemporal big data mining and urban planning technology. The method includes: constructing multi-source map submaps and performing binarization and attention weighting to obtain binarized land use submaps and weighted geographic environment submap features; extracting deep aggregated spatial features from both to generate latent vector representations; flattening the representation into a one-dimensional feature sequence and querying the index of each element in a landscape codebook to form a vectorized index sequence; combining relative distance encoding, using a map sequence generation learning model to predict future vectorized index sequences, and querying the landscape codebook to obtain future vectorized tensors; iteratively decoding the tensor using a map decoder to generate land use change results. This application achieves more accurate land use change prediction by capturing mesoscale spatial local information and reducing unit-level error accumulation.

The application provides a vector map construction method and system based on prior map and multi-stage diffusion reasoning. A unified vector encoder is used to encode multiple prior maps to generate prior features. Real-time data obtained is converted into bird's-eye view features, and multi-stage diffusion reasoning is performed to map the bird's-eye view features of the degradation domain to diffusion features of the normal domain. The prior features and the diffusion features are fused to obtain fused features. The fused features are input into a constructed map decoder to generate an online vector map. In the scheme, multiple prior maps are introduced, and a unified vector encoder is used to efficiently encode different prior maps, thereby enhancing the robustness and accuracy of online map construction. Through multi-stage diffusion reasoning technology, image details are gradually optimized, which not only uniformly processes multiple image degradation problems, but also provides high-quality image restoration and enhancement effect in complex environments, thereby providing strong support for an automatic driving perception system.

A feature map encoding device (100) determines, from feature maps of a plurality of channels, an active channel to be encoded, generates one packing feature frame by packing only the feature map of the active channel, and generates a bit stream by encoding the packing feature frame.

This application discloses a gain map encoding method and apparatus, a gain map decoding method and apparatus, a device, and a medium. The method of this application includes: determining a first picture region and a second picture region in a gain map, where a brightness of a pixel point in the first picture region is greater than a first threshold, and a brightness of a pixel point in the second picture region is less than or equal to the first threshold; determining an encoding strategy of the gain map based on the first picture region and the second picture region; and encoding the gain map based on the encoding strategy, to obtain encoded information of the gain map.

The invention relates to a map generation method, a map generation device and a computer program product. The map generation method comprises the following steps: carrying out feature coding on vehicle environment information to obtain current aerial view features; obtaining an absolute position of the current aerial view feature according to the current self-parking space posture, and downloading a prior aerial view feature from a server according to the current aerial view feature and the absolute position; performing position correction on the current aerial view feature according to the prior aerial view feature to obtain a corrected current aerial view feature; fusing the corrected current aerial view feature and the prior aerial view feature to obtain a local aerial view feature; obtaining a plurality of map queries, and inputting the plurality of map queries and the local aerial view features into a pre-trained map decoder for processing to obtain a decoding result; and generating a plurality of map elements according to the decoding result, and generating a local map according to the plurality of map elements. According to the invention, the construction performance of the on-line vectorization high-precision map realized based on the vehicle can be improved.

This application discloses a gain map encoding method and apparatus, a gain map decoding method and apparatus, a device, and a medium, and pertains to the field of communication technologies. The method in this application includes: obtaining at least one target image block in a gain map, where a luminance value of a pixel in the target image block is greater than a first threshold (301); determining target image block identification information of the gain map and an image block group based on the at least one target image block (302); and encoding the target image block identification information and the image block group to obtain encoding information of the gain map (303).

This provides technology for encoding and decoding feature maps. [Solution] The present invention provides a feature map encoding device comprising: a feature map reduction model registration unit that registers a feature map reduction model and a corresponding feature map restoration model at the position indicated by a first model index in a feature map reduction model storage unit; a feature map reduction model selection unit that determines a second model index; a feature map reduction unit that generates a single-scale feature map using the feature map reduction model identified by the second model index; and a feature map restoration parameter encoding unit that transmits information indicating the first model index, the second model index, and the feature map restoration model identified by the second model index.

A feature map encoding device according to one embodiment of the present application comprises: a neural network feature amount extraction unit (101) that generates a multi-scale feature map from an image; a feature map reduction unit (102) that converts the multi-scale feature map into a single-scale feature map; a feature map conversion unit (103) that converts the single-scale feature map into a packing feature frame; a distribution characteristic calculation unit (111) that calculates distribution characteristics of the multi-scale feature map and distribution characteristics of the single-scale feature map on a frame-by-frame basis; and a feature map internal encoding unit (104) that encodes the packing feature frame and the distribution characteristics.

The invention relates to a multi-scale high-precision map construction method based on double-space interaction, and belongs to the technical field of high-precision map construction. According to the method, a double-space feature modeling and interaction mechanism is introduced. The method comprises the following steps: firstly, performing feature extraction on multi-view image data, projecting the multi-view image data to a bird's-eye view space, and generating multi-scale BEV feature representation; and then, carrying out scale-by-scale fusion on the multi-scale BEV features of the current frame and the historical prior BEV features in an Euclidean space so as to enhance the continuity and stability of a map structure. On the basis, the fused multi-scale BEV features are mapped to a hyperbolic space, modeling is carried out on the hierarchical relationship among different scale features by using the geometric characteristics of the hyperbolic space, and cross-scale feature interaction is realized. And finally, the advantages of the Euclidean space features and the hyperbolic space features are integrated through a double-space feature fusion mode, BEV feature representation used for high-precision map decoding is generated, and therefore the overall precision of map construction is improved.

This provides technology for encoding and decoding feature maps. [Solution] The present invention provides a feature map encoding device comprising: a feature map reduction unit that converts a multi-scale feature map to generate a single-scale feature map; a packing unit that identifies the scan type of the single-scale feature map, packs the single-scale feature map into a frame based on the identified scan type to generate a packed feature frame; an encoding unit that encodes the scan type; and a feature map internal encoding unit that encodes the packed feature frame.