440 results about "Spatial encoding" patented technology

The present disclosure provides methods and assay systems for use in spatially encoded biological assays, including assays to determine a spatial pattern of abundance, expression, and / or activity of one or more biological targets across multiple sites in a sample. In particular, the biological targets comprise proteins, and the methods and assay systems do not depend on imaging techniques for the spatial information of the targets. The present disclosure provides methods and assay systems capable of high levels of multiplexing where reagents are provided to a biological sample in order to address tag the sites to which reagents are delivered; instrumentation capable of controlled delivery of reagents; and a decoding scheme providing a readout that is digital in nature.

The invention belongs to the technical field of marine environment prediction, and discloses a ship navigation sea wave dynamic space-time prediction method and system based on deep learning. The method comprises the following steps: carrying out space-time alignment, missing value repair and standardization processing on acquired ship AIS data and an ERA5 reanalysis data set, and generating node feature vectors containing latitudes and longitudes, timestamps, wind speeds and significant wave heights; through node feature coding, centrality coding, space coding and time coding, ship trajectory node importance and time-space interaction relation are quantified. Constructing a SeaGraph model, and outputting an effective wave height prediction value of a target waypoint; and performing verification. According to the method, the space-time constraint of a traditional static modeling framework is broken through, the advantages of a self-attention mechanism and a graph network are integrated, the predictive modeling capability of dynamic evolution of a wave field in front of a ship navigation track is enhanced, and high-precision sea wave forecasting support is provided for intelligent ship navigation under complex sea conditions.

The invention relates to the technical field of people flow prediction, and discloses an urban people flow prediction method based on an urban point-of-interest spatio-temporal data set, which comprises the following steps: acquiring the urban point-of-interest spatio-temporal data set; performing multi-modal feature dynamic fusion by adopting a hierarchical perception attention fusion mechanism to obtain a point-of-interest feature vector; performing spherical spatial dependency modeling by adopting a regional adaptive spherical convolutional coding method to obtain a spatial coding vector; using a periodic mask generator to carry out business time constraint coding to obtain a time feature vector; and according to the interest point feature vector, the space coding vector and the time feature vector, space-time coupling features are extracted, regional perception time sequence modeling is performed on the space-time coupling features, and a people flow prediction value and crowding degree grade probability distribution are generated through multi-task sharing prediction. According to the urban people flow prediction method based on the urban interest point spatio-temporal data set, the urban people flow prediction performance is improved.

The invention discloses a time-space interaction vehicle trajectory prediction method based on speed perception, and the method comprises the steps: obtaining driving trajectory data of a target vehicle and surrounding vehicles in a perception range of the target vehicle, inputting the driving trajectory data into a pre-trained trajectory prediction model, and obtaining the trajectory data of the target vehicle in a prediction time period; the trajectory prediction model comprises an encoder module, a speed sensing interaction modeling module and a decoder module; in the encoder module, a spatial-temporal feature encoder is used for obtaining spatial-temporal feature codes based on the driving tracks of the target vehicle and other vehicles; the scene perception encoder is used for extracting a global spatial dependency relationship between vehicles to obtain a scene perception spatial code; the speed perception interaction modeling module is used for extracting space-time interaction features and scene interaction features of the target vehicle and surrounding vehicles by using a multi-head attention mechanism based on the space-time features and scene perception space codes, and further obtaining global interaction features; and the decoder module is used for obtaining a driving track of the target vehicle in the prediction time period based on the space-time interaction characteristics and the global interaction characteristics. According to the method, the vehicle-scene spatial dependency can be accurately captured, and the trajectory prediction accuracy is improved.

The invention discloses a city-level CIM scene streaming rendering method based on multi-modal fusion, and the method comprises the following steps: S1, collecting city data, and carrying out the preprocessing of the city data; s2, establishing a cross-modal entity alignment relationship, and constructing a city object structure body; s3, dividing a space by adopting a quadtree method, generating rendering sub-blocks and distributing a unique space code; s4, binding the rendering sub-blocks with the urban object structure body, constructing a multi-modal fusion network, and generating a multi-modal rendering unit set; s5, constructing an inter-frame rendering cost function, and scheduling and sequencing the multi-modal rendering unit set to form an inter-frame scheduling sequence; s6, loading the rendering units according to the inter-frame scheduling sequence to form a city-level three-dimensional view of continuous frames; and S7, updating the scheduling sequence, dynamically adjusting the loading sequence, and realizing stable and efficient streaming rendering of the city-level CIM scene. According to the method, the fusion efficiency and rendering performance of the urban large-scale three-dimensional data are improved, and the method has remarkable engineering applicability and popularization value.

The invention belongs to the technical field of power system load prediction, and relates to a long-range multivariable load prediction method and system based on time-frequency domain collaboration, and the system carries out the normalization and stabilization of a multivariate load time sequence through a data preprocessing module; the feature embedding module performs linear embedding on the block sequence to construct high-dimensional feature representation; the state space coding module extracts long-range dependency features and generates depth time sequence representation; the decoding prediction module maps the coding features into a preliminary prediction sequence; the time sequence alignment module identifies a leading-lagging relation among multiple variables and aligns a time sequence; the frequency domain optimization module realizes frequency domain component fusion based on adaptive filtering; and the model training optimization module is used for performing training and optimization through a signal attenuation loss function. The method can effectively improve the precision and robustness of long-range multivariable load prediction, and especially has obvious advantages in the aspects of processing complex dependency relationships and dynamic time delay.

The invention discloses a patterned wafer defect detection system and method based on double-optical-comb space-time coding, and the system comprises a double-optical-comb light source module, a space coding illumination module, a time programming control module, a signal collection and processing module, and a data analysis and processing module. And the data analysis processing module receives and analyzes the restored three-dimensional shape information of the surface of the wafer to be detected, extracts defect related characteristics, establishes a mapping relation between spectral characteristics and defects, and identifies the defects on the surface of the wafer to obtain corresponding defect types and position information. According to the invention, a wafer defect detection technology based on double-optical-comb space-time coding is adopted, rapid scanning and parallel detection are realized by using a double-optical-comb interference technology, the detection efficiency is greatly improved, and absolute distance information of the wafer surface can be obtained. The result is fed back to the precise air floating motion platform, so that an automatic focusing optical path system and a feedback control part can be omitted, the detection efficiency is improved, and the size, complexity and cost of the whole wafer detection system are reduced.

The invention relates to the field of ocean data buoy data quality control, and discloses a buoy meteorological data restoration method based on a space-time double-attention neural network, and the method comprises the following steps: data collection and preprocessing; establishing a space-time double-attention neural network model, wherein the model comprises a time coding link, a space coding link and a feature fusion layer; model training: inputting the time features containing the target elements to be predicted into a time coding link, inputting the meteorological elements into a space coding link, and outputting the target elements at the moment to be predicted by the model; after model training, evaluating the model by using the test set; and predicting a vacancy value or an abnormal value in the multi-dimensional meteorological element data acquired in real time by using the model which is qualified in evaluation, so as to realize data restoration. According to the method disclosed by the invention, time and space constraints are effectively combined, and abnormal values and vacant values in the meteorological data are predicted and replaced, so that the meteorological data are repaired.

The invention discloses an open set hyperspectral image instance graph construction method based on a distillation diffusion model, and the method comprises the following steps: extracting the spatial and spectral features of a target domain HSI through a spatial encoder and a spectral encoder, executing forward diffusion in a diffusion classifier by taking a real label as a starting point, and carrying out the condition reverse denoising, and finally, closed set category prediction is obtained. A single sample prediction set is generated through Monte Carlo sampling, a prediction variance is calculated, uncertainty distribution is constructed, an unknown class probability is calculated by using a cumulative distribution function, and finally, a known class probability and an unknown class probability are fused to generate teacher open set prediction through a mapping module. A K neighbor graph structure of a sample is constructed in a feature space, teacher open set prediction and student open set prediction are respectively used as nodes to construct a teacher / student instance graph, a Wasserstein distance of prediction probability distribution of the teacher / student instance graph and the student open set prediction is minimized through a graph isomorphic knowledge distillation module, and knowledge distillation based on prediction manifold alignment is realized.

The invention provides an event sequence prediction method based on a space-time diffusion generation network. Comprising two parts: an event sequence spatio-temporal feature extraction and de-noising diffusion module; the spatio-temporal feature extraction of the event sequence comprises an event space correlation modeling module, an event space correlation embedding module and an event time correlation learning and embedding module; the denoising diffusion module receives sequence time coding information and space coding information generated by the space-time feature extraction module, predicts time and space information of event occurrence by adopting a denoising diffusion model, and jointly learns space-time coding features by using a denoising network through a reverse denoising step to respectively obtain time and space attention output; and a de-noising result is obtained for multiple times through an iterative calculation method, and a space-time prediction result is finally generated. According to the scheme, the structural relationship and the spatial representation information between the sequence events are adaptively generated according to the spatial features of the sequence, and a better learning effect is achieved for different spatial distribution data.

The invention discloses a traffic scene image data analysis and target segmentation method and device, and the method comprises the steps: enabling an input image of a traffic scene to obtain a target segmentation result through a traffic scene object segmentation model Tramba; the traffic scene object segmentation model Tramba comprises an S-stage visual state space encoder, S-1 double-frequency-domain visual state space modules, S-1-stage spiral visual state space decoders, an up-sampling module and a segmentation head. And the S-1 double-frequency-domain visual state space modules are used for performing high-frequency and low-frequency frequency domain enhancement on the RGB features of the first S-1 layers through a shift window scanning mechanism and an expansion scanning mechanism respectively and then connecting the RGB features to the input end of the spiral visual state space decoder of the corresponding level in a jumping manner. The invention aims to solve the problems that perception of a scanning mechanism in an existing Mama model on image details and a global structure needs to be enhanced and deep understanding on a traffic scene is lacked.

A pharmaceutical hyperspectral reconstruction method based on a coded aperture snapshot spectral imaging (CASSI) system includes: collecting and processing original pharmaceutical hyperspectral images to obtain augmented pharmaceutical hyperspectral images; performing simulated spatial encoding on the augmented pharmaceutical hyperspectral images to obtain encoded measurement images; performing spectral inverse shift on the encoded measurement images, then performing inverse encoding to obtain inversely encoded three-dimensional hyperspectral images, using the augmented pharmaceutical hyperspectral images as target images, and constructing a training set and a testing set according to the inversely encoded three-dimensional hyperspectral images and the target images; constructing a deep symmetric neural reconstruction network, and training and testing the deep symmetric neural reconstruction network; and deploying a tested deep symmetric neural reconstruction network onto the CASSI system, real-time collecting pharmaceutical measurement images using the snapshot coded imaging system, and performing computational reconstruction on the pharmaceutical measurement images to obtain reconstructed three-dimensional hyperspectral images.

The invention discloses a peasant household credit assessment method and system based on multi-modal data federated learning, and relates to the technical field of computer intelligence, and the method comprises the steps: constructing a dual-channel representation mode of land assets based on GIS space coding and property and age limit information, and generating multi-dimensional feature input of peasant household production capacity and asset conditions in combination with multi-source data; a three-level federated learning structure is constructed, data is safely exchanged through TLS communication encryption and equipment identity authentication, and differential privacy noise is injected; a Top-K gradient selection algorithm is adopted to carry out parameter sparse transmission, a sparse rate is dynamically adjusted in combination with a round increasing strategy, a grouping sparse convolution and parameter freezing mechanism is introduced, and a federal deep learning model is compressed and an adaptive edge is deployed through 8-bit distillation quantification; according to the method, multi-modal feature construction, layered federated training and a privacy enhancement mechanism are fused, and fine modeling, lightweight deployment and data security collaboration of peasant household credit assessment are realized.

The invention discloses a terminal node security management method using a block chain technology, and particularly relates to the application field of a block chain in mobile terminal dynamic access and behavior management, and the method comprises the steps: collecting the real-time positioning information of a mobile terminal node, inputting the positioning information into a space coding function, and generating a unique space identifier; querying a chain domain mapping table by using the space identifier, wherein the chain domain mapping table records a binding relationship between the space identifier and the chain domain identifier; the returned chain domain identifier is used as an on-chain home domain identifier of the current terminal node in the block chain system; and comparing the current chain domain identifier with the chain domain identifier recorded last time. By constructing an on-chain affiliation binding mechanism based on spatial coding and chain domain mapping, dynamic chain domain redirection when the physical position of a terminal node jumps is realized, and the problems of fuzzy terminal affiliation and identity breakage under a traditional block chain architecture are effectively solved, so that on-chain identity continuity under spatial drift is guaranteed.

The invention discloses a traffic flow prediction method based on a time-space synchronization embedded graph Transform model. The method comprises the following steps: acquiring historical traffic flow sequence data of a target area and preprocessing the historical traffic flow sequence data; defining a traffic network of a target area as an undirected graph, calculating a static adjacent matrix based on a graph structure, and obtaining spatial coding features through a full connection layer; extracting original traffic features through a full connection layer based on the preprocessed data; embedding the characteristic representations of the week cycle, the day cycle and the timestamp through a full connection layer to obtain week cycle, day cycle and timestamp characteristics; based on a space-time adaptive embedding mechanism, obtaining adaptive space-time features; hidden space-time representation is obtained through feature splicing; extracting space-time dependence characteristics of traffic flow along a time dimension and a space dimension through a double-channel attention mechanism to obtain enhanced space-time characteristic representation; and generating a traffic flow predicted value of each node in a future time period through a full-connection output layer. According to the invention, the traffic flow prediction precision is improved.

The invention discloses a spatio-temporal data compression method and system based on lightweight processing, and relates to the technical field of image data processing, and the method comprises the steps: based on spatio-temporal data to be compressed, establishing standardized data entries, forming a window set through time axis segmentation, carrying out the periodic discrimination of windows according to the frequency domain energy distribution, and constructing spatio-temporal blocks, establishing an error control parameter table based on the global error budget; generating a time coding stream, performing integerization on the three-dimensional coordinates and the attribute values, generating a space coding stream through double difference and run length coding, performing edge folding lightweight and texture compression on the grid data, and generating a joint coding result; and based on a joint coding result, dividing the compressed data into a base layer and a plurality of enhancement layers, and establishing a relevance hierarchical storage structure and a block-level index table to generate the compressed data capable of being transmitted in a streaming manner. According to the method, collaborative compression can be carried out by utilizing spatial-temporal data internal relevance.

The invention relates to the technical field of automatic driving, in particular to a multi-view-angle perception-driven automatic driving test scene twin reconstruction method, which comprises the following steps of: S1, acquiring and preprocessing multi-view-angle image perception data to form a multi-view-angle image sequence under a unified coordinate system; s2, spatial coding and modeling based on an orthogonal three-plane structure; s3, on the basis of a view perception-space interaction encoder of a Transform architecture, completing space coding processing represented by an orthogonal three-plane structure; s4, structure and semantics combined twinborn reconstruction decoding is carried out; and S5, generating a simulation compatible format and deploying a platform. According to the method, the terrain, facilities, traffic elements and other contents of a real road scene can be automatically restored, the storage and calculation cost is remarkably reduced while the spatial information integrity is ensured, various simulation platform support formats can be flexibly output, the method serves for closed-loop testing of automatic driving, and the reconstruction efficiency and the system suitability are improved.

The invention discloses a planning and navigation method and system for a puncture robot. The method comprises the steps that a preoperative high-resolution image and ultrasonic simulation data are registered through a two-channel convolutional neural network, high-precision space alignment is carried out, and multi-modal fusion body image data Ifuse are generated; carrying out topological structure analysis on the multi-modal fusion body image data Ifuse, and carrying out semantic enhancement three-dimensional model construction; based on the semantic enhancement three-dimensional model, performing global path planning through obstacle space coding and reinforcement learning pre-planning; according to the global path planning result, navigation parameters and a lightweight model capable of being imported into a navigation system are generated, and preoperative navigation data are output. The system comprises a two-channel convolutional neural network registration module, a semantic enhancement three-dimensional model construction module, a global path planning module and a navigation data encapsulation module. According to the invention, the precision and stability of registration are improved, the problem of multi-modal image data fusion can be effectively solved, and accurate preoperative navigation data output is realized.

The invention discloses a continuous variable quantum key distribution method, device and system, and belongs to the field of wireless communication. Firstly, a sending end generates continuous light pulses for discrete coding, a one-dimensional discrete modulation signal is generated, quantum signal light is generated through an attenuator, and the quantum signal light is coupled to a quantum channel for transmission. Then, a receiving end adopts a homodyne detector to measure the regular component of the quantum signal in a self-calibration manner; and after a local measurement base direction and a phase drift angle introduced by a dynamic compensation quantum channel are adjusted in real time, a covariance matrix is calculated and input into a post-processing module, the code rate of the system is further calculated, and a security key is generated by using a protocol between a receiving end and a transmitting end. According to the device, the intensity modulator is connected between the laser and the attenuator, so that one-dimensional discrete modulation is realized, and dependence on a phase reference signal is avoided. According to the system, a traditional phase locking module is removed, an asymmetric phase space coding mechanism is adopted, dependence on a phase reference signal is eliminated, and the safety and stability of the system are improved.

The invention discloses an underwater image enhancement method based on dual-path feature decoupling and gating fusion. The method comprises the following steps: firstly, constructing a training data set; then, an encoder-bottleneck layer-decoder is used as a trunk, and a dual-path encoding and decoding mechanism is adopted to construct an underwater image enhancement model; the encoder is used for extracting direction encoding features and space encoding features; the bottleneck layer is used for extracting global and local features and fusing and outputting bottleneck features; the decoder is used for decoding and multi-scale refinement so as to reconstruct and obtain an underwater enhanced image; then training is carried out to obtain a trained underwater image enhancement model; and finally, the device is deployed to acquire the underwater image in real time for underwater image enhancement. According to the method, independent modeling is carried out for anisotropic scattering / edge attenuation and spatial non-uniform atomization / local brightness imbalance, and mutual interference of different degradation causes in the same feature space can be reduced.

The present disclosure is directed to a traffic signal apparatus communication system and methods of communicating traffic information to vehicles using same. The traffic signal apparatus communication system includes a traffic signal apparatus for providing a message to a vehicle. The apparatus includes at least one spatially encoded marker, and the vehicle is configured to receive returns of a radar signal from the spatially-encoded marker. At least one controller of the vehicle is configured to determine the message encoded by the spatially-encoded marker based on the returns and to control the vehicle based on the message. The message may include a value indicating a time to a transition of a new state of the traffic signal apparatus, where the new state includes emission of light from one of a first light source, a second light source, or a third light source of the traffic signal apparatus.

The invention relates to a hyperspectral de-mixing method based on a double-branch cross-weighted network, and the method comprises the following steps: obtaining a hyperspectral multi-mode data set which comprises hyperspectral image data and laser radar data, and inputting the hyperspectral image data and the laser radar data into the double-branch cross-weighted network; processing the hyperspectral image data through a spectral encoder to obtain primary spectral features; a spatial encoder processes laser radar image data to obtain primary spatial features, the primary spectral features and the primary spatial features are input into an adaptive feature selection module to be processed to obtain precise spectral features and precise spatial features, and the obtained precise spectral features and precise spatial features are added to be fused; and obtaining an abundance coefficient graph and an end member from a fused result through an activation function, and obtaining a reconstructed hyperspectral image by using a decoder. According to the invention, the unmixing effect of different substances of similar materials in a multi-modal scene can be improved.

The invention discloses an indoor high-precision positioning system and method based on a UWB technology, and particularly relates to the technical field of positioning, and the system comprises a region division module which divides an indoor space into N dynamic region units based on the structural layout of a building and the coverage range of UWB anchor nodes; establishing a bidirectional mapping relationship between the region and the UWB tag by taking the key building nodes as boundaries; each area unit is associated with moving track data of the label, a space encoder is introduced to generate an area feature vector, and an original three-dimensional coordinate is obtained to represent the positioning characteristic of the area; according to the method, multi-source data of the UWB signal layer data, the motion sensing layer data and the environment sensing layer data are analyzed and processed, the superposition error of environment reflection and hardware deviation is effectively reduced, and the geometric convergence precision of position calculation can be remarkably improved in a complex space.

The invention relates to the field of optical detection, in particular to an interference confocal measurement system based on space coding and a measurement method thereof.White light generated by a light source is collimated through a first collimating lens and then divided into S polarized light and P polarized light through a polarization splitting prism, the S polarized light enters a reference plane mirror through a first quarter-wave plate, and the P polarized light enters a second quarter-wave plate; p polarized light enters a blazed grating through a second quarter-wave plate for transverse dispersion and then is changed into monochromatic polarized light with different wavelengths and the same focal length through a first achromatic lens, and the monochromatic polarized light and the monochromatic polarized light are jointly focused at the same depth position of an object to be measured. Information of the object to be measured is carried and returned to the polarization splitting prism, two beams of polarized light are combined and then focused on a target surface of a photoelectric detector of an imaging spectrometer with a mask plate through a focusing lens, an interference image of the object to be measured is obtained, and spectrum and interference analysis is carried out. According to the invention, the transverse scanning speed can be improved, the measurement time can be shortened, and the resolution can be improved.

The invention discloses a face generation method based on a key point guide text graph diffusion model, which comprises the following steps of: firstly, collecting data information, forming a training data pair by a face image, text description information and face key points, encoding the text description information by using a text encoder and converting the text description information into an embedded vector, mapping the face key point image information to an implicit space by using an implicit space encoder; splicing the implicit spatial tensor of the Gaussian noise map and the implicit spatial tensor of the face key point image information; establishing and training an implicit diffusion model, continuously iteratively denoising the spliced implicit space tensor to obtain a face image corresponding to the key point and the text description information, and distributing additional training attention for the key point condition by using a denoising loss module under the guidance of a thermodynamic diagram, and a denoising result in the implicit space is mapped to a pixel space by using an implicit space decoder, and finally a face image with high generation quality and high consistency of image and text description information is reconstructed.

The invention discloses a tooth CBCT image super-resolution reconstruction method based on a potential diffusion model, and relates to an image processing and generating technology in the field of computer vision. The in-vivo medical image is trained based on hidden space coding and probability diffusion, so that the network has a better super-resolution effect on the real in-vivo tooth CBCT image.

The embodiment of the invention provides a space coding method and device based on a space grid and a processing method and device based on the space grid. The method comprises the following steps: acquiring latitude and longitude and resolution requirements of a geometric object to be coded; determining a target Beidou grid level meeting the resolution requirement from the Beidou grid levels, and determining a target H3 grid level meeting the resolution requirement from the H3 grid level; according to the target Beidou grid level and the longitude and latitude, carrying out space coding on the geometric object to obtain a Beidou code; according to the target H3 grid hierarchy and the longitude and latitude, carrying out space coding on the geometric object to obtain an H3 code; and establishing a mapping relationship between the Beidou code and the H3 code of the geometric object. The method is used for achieving the effect of comprehensively using respective advantages of the two codes in different application scenes according to the mapping relation between the Beidou code and the H3 code.

The invention provides a sleep staging method based on spatial-temporal feature coding and multi-source fusion, and belongs to the technical field of big data analysis. According to the method, collected multi-channel multi-source physiological data including electroencephalogram, myoelectricity and electro-oculogram signals are utilized to construct a sleep staging neural network model fusing the multi-channel multi-source physiological data; establishing a graph space encoder for modeling multi-channel spatial features, and encoding interaction and position information among different channels; establishing a multi-signal source fusion module for fusing multi-source signals, and identifying different contributions of multi-signal sources to stages based on an attention mechanism; a time sequence Transform encoder used for modeling time features is established, and local and global time features are encoded at the same time. According to the method, automatic staging of sleep can be realized, the staging accuracy is improved, personal help can be provided for individuals, a convenient tool is provided for doctors, and heuristic auxiliary guidance is provided for precision medical treatment.

The invention discloses an end-to-end polarization hyperspectral image classification method and system, belongs to the technical field of deep learning and optical imaging, and solves the technical problems of low reconstruction process speed, limited precision, low information utilization rate in a classification process and weak feature extraction capability in the prior art. The method comprises the following steps: carrying out target shooting based on a snapshot type space coding hyperspectral polarization imaging system, and carrying out system coding on a shot image to obtain two-dimensional aliasing data; reconstructing the two-dimensional aliasing data into a polarization hyperspectral data cube by using the trained reconstruction network; training the classification network based on the polarization hyperspectral data cube to obtain a trained classification network; and performing joint fine tuning on the trained reconstruction network and the trained classification network to obtain a polarization hyperspectral image classification model, and performing polarization hyperspectral image classification by using the polarization hyperspectral image classification model. The method is used for realizing high-quality reconstruction and accurate classification of the polarization hyperspectral image.

In various examples, three-dimensional multi-camera perception systems and applications is described herein. Systems and methods are disclosed herein that process image data generated using multiple cameras located throughout an environment in order to directly determine three-dimensional (3D) information associated with objects located within the environment. For instance, the image data may be processed using one or more feature extractors (e.g., one or more backbones) to determine multi-view image features associated with images represented by the image data. These multi-view image features, along with calibration data associated with the cameras, may then be processed using one or more spatio-temporal transformers (e.g., one or more spatial encoders, one or more temporal encoders, etc.) in order to determine 3D locations of objects within the environment.