Datasets

This dataset accompanies the paper "STREETS: A Novel Camera Network Dataset for Traffic Flow" at Neural Information Processing Systems (NeurIPS) 2019. Included are: *Over four million still images form publicly accessible cameras in Lake County, IL. The images were collected across 2.5 months in 2018 and 2019. *Directed graphs describing the camera network structure in two communities in Lake County. *Documented non-recurring traffic incidents in Lake County coinciding with the 2018 data. *Traffic counts for each day of images in the dataset. These counts track the volume of traffic in each community. *Other annotations and files useful for computer vision systems. Refer to the accompanying "readme.txt" or "readme.pdf" for further details.

If you use this dataset, please cite the IJRR data paper (bibtex is below). We present a dataset collected from a canoe along the Sangamon River in Illinois. The canoe was equipped with a stereo camera, an IMU, and a GPS device, which provide visual data suitable for stereo or monocular applications, inertial measurements, and position data for ground truth. We recorded a canoe trip up and down the river for 44 minutes covering 2.7 km round trip. The dataset adds to those previously recorded in unstructured environments and is unique in that it is recorded on a river, which provides its own set of challenges and constraints that are described in this paper. The data is divided into subsets, which can be downloaded individually. Video previews are available on Youtube: https://www.youtube.com/channel/UCOU9e7xxqmL_s4QX6jsGZSw The information below can also be found in the README files provided in the 527 dataset and each of its subsets. The purpose of this document is to assist researchers in using this dataset. Images ====== Raw --- The raw images are stored in the cam0 and cam1 directories in bmp format. They are bayered images that need to be debayered and undistorted before they are used. The camera parameters for these images can be found in camchain-imucam.yaml. Note that the camera intrinsics describe a 1600x1200 resolution image, so the focal length and center pixel coordinates must be scaled by 0.5 before they are used. The distortion coefficients remain the same even for the scaled images. The camera to imu tranformation matrix is also in this file. cam0/ refers to the left camera, and cam1/ refers to the right camera. Rectified --------- Stereo rectified, undistorted, row-aligned, debayered images are stored in the rectified/ directory in the same way as the raw images except that they are in png format. The params.yaml file contains the projection and rotation matrices necessary to use these images. The resolution of these parameters do not need to be scaled as is necessary for the raw images. params.yml ---------- The stereo rectification parameters. R0,R1,P0,P1, and Q correspond to the outputs of the OpenCV stereoRectify function except that 1s and 2s are replaced by 0s and 1s, respectively. R0: The rectifying rotation matrix of the left camera. R1: The rectifying rotation matrix of the right camera. P0: The projection matrix of the left camera. P1: The projection matrix of the right camera. Q: Disparity to depth mapping matrix T_cam_imu: Transformation matrix for a point in the IMU frame to the left camera frame. camchain-imucam.yaml -------------------- The camera intrinsic and extrinsic parameters and the camera to IMU transformation usable with the raw images. T_cam_imu: Transformation matrix for a point in the IMU frame to the camera frame. distortion_coeffs: lens distortion coefficients using the radial tangential model. intrinsics: focal length x, focal length y, principal point x, principal point y resolution: resolution of calibration. Scale the intrinsics for use with the raw 800x600 images. The distortion coefficients do not change when the image is scaled. T_cn_cnm1: Transformation matrix from the right camera to the left camera. Sensors ------- Here, each message in name.csv is described ###rawimus### time # GPS time in seconds message name # rawimus acceleration_z # m/s^2 IMU uses right-forward-up coordinates -acceleration_y # m/s^2 acceleration_x # m/s^2 angular_rate_z # rad/s IMU uses right-forward-up coordinates -angular_rate_y # rad/s angular_rate_x # rad/s ###IMG### time # GPS time in seconds message name # IMG left image filename right image filename ###inspvas### time # GPS time in seconds message name # inspvas latitude longitude altitude # ellipsoidal height WGS84 in meters north velocity # m/s east velocity # m/s up velocity # m/s roll # right hand rotation about y axis in degrees pitch # right hand rotation about x axis in degrees azimuth # left hand rotation about z axis in degrees clockwise from north ###inscovs### time # GPS time in seconds message name # inscovs position covariance # 9 values xx,xy,xz,yx,yy,yz,zx,zy,zz m^2 attitude covariance # 9 values xx,xy,xz,yx,yy,yz,zx,zy,zz deg^2 velocity covariance # 9 values xx,xy,xz,yx,yy,yz,zx,zy,zz (m/s)^2 ###bestutm### time # GPS time in seconds message name # bestutm utm zone # numerical zone utm character # alphabetical zone northing # m easting # m height # m above mean sea level Camera logs ----------- The files name.cam0 and name.cam1 are text files that correspond to cameras 0 and 1, respectively. The columns are defined by: unused: The first column is all 1s and can be ignored. software frame number: This number increments at the end of every iteration of the software loop. camera frame number: This number is generated by the camera and increments each time the shutter is triggered. The software and camera frame numbers do not have to start at the same value, but if the difference between the initial and final values is not the same, it suggests that frames may have been dropped. camera timestamp: This is the cameras internal timestamp of the frame capture in units of 100 milliseconds. PC timestamp: This is the PC time of arrival of the image. name.kml -------- The kml file is a mapping file that can be read by software such as Google Earth. It contains the recorded GPS trajectory. name.unicsv ----------- This is a csv file of the GPS trajectory in UTM coordinates that can be read by gpsbabel, software for manipulating GPS paths. @article{doi:10.1177/0278364917751842, author = {Martin Miller and Soon-Jo Chung and Seth Hutchinson}, title ={The Visual–Inertial Canoe Dataset}, journal = {The International Journal of Robotics Research}, volume = {37}, number = {1}, pages = {13-20}, year = {2018}, doi = {10.1177/0278364917751842}, URL = {https://doi.org/10.1177/0278364917751842}, eprint = {https://doi.org/10.1177/0278364917751842} }

Contains scattering data obtained for (TaSe4)2I at the Advanced Photon Source at Argonne National Laboratory. Beamline 6ID-D was used with a beam energy of 64.8 keV in a transmission geometry. Data was obtained at temperatures between 28 and 300 K. See the readme.txt file for more information.

This upload contains all datasets used in Experiment 2 of the EMMA paper (appeared in WABI 2023): Shen, Chengze, Baqiao Liu, Kelly P. Williams, and Tandy Warnow. "EMMA: A New Method for Computing Multiple Sequence Alignments given a Constraint Subset Alignment". The zip file has the following structure (presented as an example): salma_paper_datasets/ |_README.md |_10aa/ |_crw/ |_homfam/ |_aat/ | |_... |_... |_het/ |_5000M2-het/ | |_... |_5000M3-het/ ... |_rec_res/ Generally, the structure can be viewed as: [category]/[dataset]/[replicate]/[alignment files] # Categories: 1. 10aa: There are 10 small biological protein datasets within the `10aa` directory, each with just one replicate. 2. crw: There are 5 selected CRW datasets, namely 5S.3, 5S.E, 5S.T, 16S.3, and 16S.T, each with one replicate. These are the cleaned version from Shen et. al. 2022 (MAGUS+eHMM). 3. homfam: There are the 10 largest Homfam datasets, each with one replicate. 4. het: There are three newly simulated nucleotide datasets from this study, 5000M2-het, 5000M3-het, and 5000M4-het, each with 10 replicates. 5. rec\_res: It contains the Rec and Res datasets. Detailed dataset generation can be found in the supplementary materials of the paper. # Alignment files There are at most 6 `.fasta` files in each sub-directory: 1. `all.unaln.fasta`: All unaligned sequences. 2. `all.aln.fasta`: Reference alignments of all sequences. If not all sequences have reference alignments, only the sequences that have will be included. 3. `all-queries.unaln.fasta`: All unaligned query sequences. Query sequences are sequences that do not have lengths within 25% of the median length (i.e., not full-length sequences). 4. `all-queries.aln.fasta`: Reference alignments of query sequences. If not all queries have reference alignments, only the sequences that have will be included. 5. `backbone.unaln.fasta`: All unaligned backbone sequences. Backbone sequences are sequences that have lengths within 25% of the median length (i.e., full-length sequences). 6. `backbone.aln.fasta`: Reference alignments of backbone sequences. If not all backbone sequences have reference alignments, only the sequences that have will be included. >If all sequences are full-length sequences, then `all-queries.unaln.fasta` will be missing. >If fewer than two query sequences have reference alignments, then `all-queries.aln.fasta` will be missing. >If fewer than two backbone sequences have reference alignments, then `backbone.aln.fasta` will be missing. # Additional file(s) 1. `350378genomes.txt`: the file contains all 350,378 bacterial and archaeal genome names that were used by Prodigal (Hyatt et. al. 2010) to search for protein sequences.

Data sets from "DISCO+QR: Rooting Species Trees in the Presence of GDL and ILS." It contains trees and sequences simulated with gene duplication and loss under a variety of different conditions. Note: - trees.tar.gz contains the simulated gene-family trees used in our experiments (both true trees from SimPhy as well as trees estimated from alignments). - alignments.tar.gz contains simulated sequence data used for estimating the gene-family trees

This dataset contains four real-world sub-datasets with data embedded into Poincare ball models, including Olsson's single-cell RNA expression data, CIFAR10, Fashion-MNIST and mini-ImageNet. Each sub-dataset has two corresponding files: one is the data file, the other one is the pre-computed reference points for each class in the sub-dataset. Please refer to our paper (https://arxiv.org/pdf/2109.03781.pdf) and codes (https://github.com/thupchnsky/PoincareLinearClassification) for more details.

Curated networks and clustering output from the manuscript: Well-Connected Communities in Real-World Networks https://arxiv.org/abs/2303.02813

This dataset is for characterizing chemical short-range-ordering in CrCoNi medium entropy alloys. It has three sub-folders: 1. code, 2. sample WQ, 3. sample HT. The software needed to run the files is Gatan Microscopy Suite® (GMS). Please follow the instruction on this page to install the DM3 GMS: <a href="https://www.gatan.com/installation-instructions#Step1">https://www.gatan.com/installation-instructions#Step1</a> 1. Code folder contains three DM scripts to be installed in Gatan DigitalMicrograph software to analyze scanning electron nanobeam diffraction (SEND) dataset: Cepstrum.s: need [EF-SEND_sampleWQ_cropped_aligned.dm3] in Sample WQ and the average image from [EF-SEND_sampleWQ_cropped_aligned.dm3]. Same for Sample HT folder. log_BraggRemoval.s: same as above. Patterson.s: Need refined diffuse patterns in Sample HT folder. 2. Sample WQ and 3. Sample HT folders both contain the SEND data (.ser) and the binned SEND data (.dm3) as well as our calculated strain maps as the strain measurement reference. The Sample WQ folder additionally has atomic resolution STEM images; the Sample HT folder additionally has three refined diffuse patterns as references for diffraction data processing. * Only .ser file is needed to perform the strain measurement using imToolBox as listed in the manuscript. .emi file contains the meta data of the microscope, which can be opened together with .ser file using FEI TIA software.

This dataset is the raw data including SEM, TEM, PINEM images and FDTD simulation as well as pairwise interaction calculation results.

3DIFICE: 3-dimensional Damage Imposed on Frame structures for Investigating Computer vision-based Evaluation methods This dataset contains 1,396 synthetic images and label maps with various types of earthquake damage imposed on reinforced concrete frame structures. Damage includes: cracking, spalling, exposed transverse rebar, and exposed longitudinal rebar. Each image has an associated label map that can be used for training machine learning algorithms to recognize the various types of damage.

Simulated sequences provide a way to evaluate multiple sequence alignment (MSA) methods where the ground truth is exactly known. However, the realism of such simulated conditions often comes under question compared to empirical datasets. In particular, simulated data often does not display heterogeneity in the sequence lengths, a common feature in biological datasets. In order to imitate sequence length heterogeneity, we here present a set of data that are evolved under a mixture model of indel lengths, where indels have an occasional chance of being promoted to long indels (emulating large insertion/deletion events, e.g., domain-level gain/loss). This dataset is otherwise (e.g., in GTR parameters) analogous to the 1000M condition as presented in the SATe paper (doi: 10.1126/science.1171243) but with 5000 sequences and simulated with INDELible (http://abacus.gene.ucl.ac.uk/software/indelible/). For more information, see README.txt. For the INDELible control files, see https://github.com/ThisBioLife/5000M-234-het.

These datasets are for the four-dimensional scanning transmission electron microscopy (4D-STEM) and electron energy loss spectroscopy (EELS) experiments for cathode nanoparticles at different cutoff voltages and in different electrolytes. The raw 4D-STEM experiment datasets were collected by TEM image & analysis software (FEI) and were saved as SER files. The raw 4D-STEM datasets of SER files can be opened and viewed in MATLAB using our analysis software package of imToolBox available at <a href="https://github.com/flysteven/imToolBox">https://github.com/flysteven/imToolBox</a>. The raw EELS datasets were collected by DigitalMicrograph software and were saved as DM4 files. The raw EELS datasets can be opened and viewed in DigitalMicrograph software or using our analysis codes available at <a href="https://github.com/chenlabUIUC/OrientedPhaseDomain">https://github.com/chenlabUIUC/OrientedPhaseDomain</a>. All the datasets are from the work "Formation and impact of nanoscopic oriented phase domains in electrochemical crystalline electrodes" (2022). The 4D-STEM experiment data include four example datasets for cathode nanoparticles collected at different cutoff voltages and in different electrolytes as described below. Each dataset contains a stack of diffraction patterns collected at different probe positions scanned across the cathode nanoparticle. 1. Pristine cathode particle: "Pristine particle 4D-STEM.ser" 2. Cathode particle at the cutoff voltage of 0.09V during discharge at C/10 in the aqueous electrolyte: "Intermediate cutoff0_09V discharge (aqueous) 4D-STEM.ser" 3. Fully discharged cathode particle at C/10 in the aqueous electrolyte: "Fully discharged particle 4D-STEM.ser" 4. Fully discharged cathode particle at C/10 in the dry organic electrolyte: "Fully discharge particle (dry organic electrolyte).ser" The EELS experiment data includes three example datasets for cathode nanoparticles collected at different cutoff voltages during discharge in the aqueous electrolyte (in "EELS datasets.zip") as described below. Each EELS dataset contains the zero-loss and core-loss EELS spectra collected at different probe positions scanned across the cathode nanoparticle. 1. Pristine cathode particle: "Pristine particle EELS.zip" 2. Cathode particle at the cutoff voltage of 0.09V during discharge at C/10 in the aqueous electrolyte: "intermediate discharge (aqueous) EELS.zip" 3. Fully discharged cathode particle at C/10 in the aqueous electrolyte: "fully discharge (aqueous) EELS.zip" The details of the software package and codes that can be used to analyze the 4D-STEM datasets and EELS datasets are available at: https://github.com/chenlabUIUC/OrientedPhaseDomain. Once our paper is formally published, we will update the relationship of these datasets with our paper.

This upload includes the 16S.B.ALL in 100-HF condition (referred to as 16S.B.ALL-100-HF) used in Experiment 3 of the WITCH paper (currently accepted in principle by the Journal of Computational Biology). 100-HF condition refers to making sequences fragmentary with an average length of 100 bp and a standard deviation of 60 bp. Additionally, we enforced that all fragmentary sequences to have lengths > 50 bp. Thus, the final average length of the fragments is slightly higher than 100 bp (~120 bp). In this case (i.e., 16S.B.ALL-100-HF), 1,000 sequences with lengths 25% around the median length are retained as "backbone sequences", while the remaining sequences are considered "query sequences" and made fragmentary using the "100-HF" procedure. Backbone sequences are aligned using MAGUS (or we extract their reference alignment). Then, the fragmentary versions of the query sequences are added back to the backbone alignment using either MAGUS+UPP or WITCH. More details of the tar.gz file are described in README.txt.

This dataset contains sequencing data obtained from Illumina MiSeq device to prove the concept of the proposed 2DDNA framework. Please refer to README.txt for detailed description of each file.

Thank you for using these datasets! These files contain trees and reference alignments, as well as the selected query sequences for testing phylogenetic placement methods against and within the SCAMPP framework. There are four datasets from three different sources, each containing their source alignment and "true" tree, any estimated trees that may have been generated, and any re-estimated branch lengths that were created to be used with their requisite phylogenetic placement method. Three biological datasets (16S.B.ALL, PEWO/LTP_s128_SSU, and PEWO/green85) and one simulated dataset (nt78) is contained. See README.txt in each file for more information.

Provides RNASim-VS2 datasets used in Gillian's Master's thesis.

Atomic oxygen data from SCIAMACHY, for the MLT, 2002-2012, averaged for 26, 14 day periods, beginning January 1.

Atomic oxygen densities in the MLT, averaged for 2002-2018 for 26, 14 day periods, beginning January 1.

This dataset contains the ClonalKinetic dataset that was used in SimiC and its intermediate results for comparison. The Detail description can be found in the text file 'clonalKinetics_Example_data_description.txt' and 'ClonalKinetics_filtered.DF_data_description.txt'. The required input data for SimiC contains: 1. ClonalKinetics_filtered.clustAssign.txt => cluster assignment for each cell. 2. ClonalKinetics_filtered.DF.pickle => filtered scRNAseq matrix. 3. ClonalKinetics_filtered.TFs.pickle => list of driver genes. The results after running SimiC contains: 1. ClonalKinetics_filtered_L10.01_L20.01_Ws.pickle => inferred GRNs for each cluster 2. ClonalKinetics_filtered_L10.01_L20.01_AUCs.pickle => regulon activity scores for each cell and each driver gene. <b>NOTE:</b> “ClonalKinetics_filtered.rds” file which is mentioned in “ClonalKinetics_filtered.DF_data_description.txt” is an intermediate file and the authors have put all the processed in the pickle/txt file as described in the filtered data text.

This repository contains the weights for two StyleGAN2 networks trained on two composite T1 and T2 weighted open-source brain MR image datasets, and one StyleGAN2 network trained on the Flickr Face HQ image dataset. Example images sampled from the respective StyleGANs are also included. The datasets themselves are not included in this repository. The weights are stored as `.pkl` files. The code and instructions to load and use the weights can be found at https://github.com/comp-imaging-sci/pic-recon . Additional details and citations can be found in the file "README.md".

DNN weights used in the evaluation of the ApproxTuner system. Link to paper: https://dl.acm.org/doi/10.1145/3437801.3446108

*This is the third version of the dataset*. New changes in this 3rd version: <i>1.replaces simulations where the initial condition consists of a sinusoidal channel with topographic perturbations with simulations where the initial condition consists of a sinusoidal channel without topographic perturbations. These simulations better illustrate the transformation of a nondendritic network into a dendritic one. 2. contains two additional simulations showing how total domain size affects the landscape's dynamism. 3. changes dataset title to reflect the publication's title</i> This dataset contains data from 18 simulations using a landscape evolution model. A landscape evolution model simulates how uplift and rock incision shape the Earth's (or other planets) surface. To date, most landscape evolution models exhibit "extreme memory" (paper: https://doi.org/10.1029/2019GL083305 and dataset: https://doi.org/10.13012/B2IDB-4484338_V1). Extreme memory in landscape evolution models causes initial conditions to be unrealistically preserved. This dataset contains simulations from a new landscape evolution model that incorporates a sub-model that allows bedrock channels to erode laterally. With this addition, the landscapes no longer exhibit extreme memory. Initial conditions are erased over time, and the landscapes tend towards a dynamic steady state instead of a static one. The model with lateral erosion is named LEM-wLE (Landscape Evolution Model with Lateral Erosion) and the model without lateral erosion is named LEM-woLE (Landscape Evolution Model without Lateral Erosion). There are 16 folders in total. Here are the descriptions: <i>>LEM-woLE_simulations:</i> This folder contains simulations using LEM-woLE. Inside the folder are 5 subfolders containing 100 elevation rasters, 100 drainage area rasters, and 100 plots showing the slope-area relationship. Elevation depicts the height of the landscape, and drainage area represents a contributing area that is upslope. Each folder corresponds to a different initial condition. Driver files and code for these simulations can be found at https://github.com/jeffskwang/LEM-wLE. <i>>MOVIE_S#_data:</i> There are 13 data folders that contain raster data for 13 simulations using LEM-wLE. Inside each folder are 1000 elevation rasters, 1000 drainage area rasters, and 1000 plots showing the slope-area relationship. Driver files and code for these simulations can be found at https://github.com/jeffskwang/LEM-wLE. <i>>movies_mp4_format:</i> For each data folder there are 3 movies generated that show elevation (a), drainage area (b), and erosion rates (c). These files are formatted in the mp4 format and are best viewed using VLC media player (https://www.videolan.org/vlc/index.html). <i>>movies_wmv_format:</i> This folder contains the same movies as the "movies_mp4_format" folder, but they are in a wmv format. These movies can be viewed using Windows media player or other Windows platform movie software. Here are the captions for the 13 movies: Movie S1. 200 MYR (1,000 RUs eroded) simulation showing elevation (a), logarithm of drainage area (b), and change in elevation (c). Initial Condition: Sinusoidal channel without randomized perturbations. Boundary Condition: 1 open boundary at the bottom of the domain, and 3 closed boundaries elsewhere. KL/KV = 1. Movie S2. 200 MYR (1,000 RUs eroded) simulation showing elevation (a), logarithm of drainage area (b), and change in elevation (c). Initial Condition: Inclined with small, randomized perturbations. Boundary Condition: 1 open boundary at the bottom of the domain, and 3 closed boundaries elsewhere. KL/KV = 1. Movie S3. 200 MYR (1,000 RUs eroded) simulation showing elevation (a), logarithm of drainage area (b), and change in elevation (c). Initial Condition: Inclined with large, randomized perturbations. Boundary Condition: 1 open boundary at the bottom of the domain, and 3 closed boundaries elsewhere. KL/KV = 1. Movie S4. 200 MYR (1,000 RUs eroded) simulation showing elevation (a), logarithm of drainage area (b), and change in elevation (c). Initial Condition: V-shaped valley with randomized perturbations. Boundary Condition: 1 open boundary at the bottom of the domain, and 3 closed boundaries elsewhere. KL/KV = 1. Movie S5. 200 MYR (1,000 RUs eroded) simulation showing elevation (a), logarithm of drainage area (b), and change in elevation (c). Initial Condition: Sinusoidal channel with randomized perturbations. Boundary Condition: 1 open boundary at the bottom of the domain, and 3 closed boundaries elsewhere. KL/KV = 1. Movie S6. 200 MYR (1,000 RUs eroded) simulation showing elevation (a), logarithm of drainage area (b), and change in elevation (c). Initial Condition: Sinusoidal channel without randomized perturbations. Boundary Condition: 1 open boundary at the bottom of the domain, and 3 closed boundaries elsewhere. KL/KV = 0.25. Movie S7. 200 MYR (1,000 RUs eroded) simulation showing elevation (a), logarithm of drainage area (b), and change in elevation (c). Initial Condition: Sinusoidal channel without randomized perturbations. Boundary Condition: 1 open boundary at the bottom of the domain, and 3 closed boundaries elsewhere. KL/KV = 0.5. Movie S8. 200 MYR (1,000 RUs eroded) simulation showing elevation (a), logarithm of drainage area (b), and change in elevation (c). Initial Condition: Sinusoidal channel without randomized perturbations. Boundary Condition: 1 open boundary at the bottom of the domain, and 3 closed boundaries elsewhere. KL/KV = 0.75. Movie S9. 200 MYR (1,000 RUs eroded) simulation showing elevation (a), logarithm of drainage area (b), and change in elevation (c). Initial Condition: Flat with randomized perturbations. Boundary Condition: 1 open boundary at the bottom of the domain, and 3 closed boundaries elsewhere. KL/KV = 1. Movie S10. 200 MYR (1,000 RUs eroded) simulation showing elevation (a), logarithm of drainage area (b), and change in elevation (c). Initial Condition: Flat with randomized perturbations. Boundary Condition: 2 open boundaries at the top and bottom of the domain, and 2 closed boundaries on the left and right sides. KL/KV = 1. Movie S11. 200 MYR (1,000 RUs eroded) simulation showing elevation (a), logarithm of drainage area (b), and change in elevation (c). Initial Condition: Flat with randomized perturbations. Boundary Condition: 4 open boundaries. KL/KV = 1. Movie S12. 200 MYR (1,000 RUs eroded) simulation showing elevation (a), logarithm of drainage area (b), and change in elevation (c). Initial Condition: Flat with randomized perturbations. Boundary Condition: 4 open boundaries. KL/KV = 1. Compared to Movie S11, the length of the domain is 50% shorter, decreasing the total domain area. Movie S13. 200 MYR (1,000 RUs eroded) simulation showing elevation (a), logarithm of drainage area (b), and change in elevation (c). Initial Condition: Flat with randomized perturbations. Boundary Condition: 4 open boundaries. KL/KV = 1. Compared to Movie S11, the length of the domain is 50% longer, increasing the total domain area. The associated publication for this dataset has not yet been published, and we will update this description with a link when it is.

This dataset consists of raw ADC readings from a 3 transmitter 4 receiver 77GHz FMCW radar, together with synchronized RGB camera and depth (active stereo) measurements. The data is grouped into 4 distinct radar configurations: - "indoor" configuration with range <14m - "30m" with range <38m - "50m" with range <63m - "high_res" with doppler resolution of 0.043m/s # Related code https://github.com/moodoki/radical_sdk # Hardware Project Page https://publish.illinois.edu/radicaldata

This data set is a matrix of values. The element in the row "i" and the column "j" denotes the influence of hexagonal pyramidal distribution at node "i" on the node "j". The size of the matrix is 16641x16641. This matrix corresponds to a 129x129 grid. Influence coefficient matrix on a smaller grid can be obtained by appropriately choosing the elements from the bigger matrix.