Search NASA⌕ Search

SEARCH · Search NASA

Results for “Dataset Annotations”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5

Structure-aware annotation of leucine-rich repeat domains

Protein domain annotation is typically done by predictive models such as HMMs trained on sequence motifs. However, sequence-based annotation methods are prone to error, particularly in calling domain boundaries and motifs within them. These methods are limited by a lack of structural information accessible to the model. With the advent of deep learning-based protein structure prediction, existing sequenced-based domain annotation methods can be improved by taking into account the geometry of protein structures. We develop dimensionality reduction methods to annotate repeat units of the Leucine Rich Repeat solenoid domain. The methods are able to correct mistakes made by existing machine learning-based annotation tools and enable the automated detection of hairpin loops and structural anomalies in the solenoid. The methods are applied to 127 predicted structures of LRR-containing intracellular innate immune proteins in the model plant Arabidopsis thaliana and validated against a benchmark dataset of 172 manually-annotated LRR domains.

Xu, Boyan↗

TU-CD-BRB-04: Automated Radiomic Features Complement the Prognostic Value of VASARI in the TCGA-GBM Dataset

Purpose: To compare the complementary prognostic value of automated Radiomic features to that of radiologist-annotated VASARI features in TCGA-GBM MRI dataset. Methods: For 96 GBM patients, pre-operative MRI images were obtained from The Cancer Imaging Archive. The abnormal tumor bulks were manually defined on post-contrast T1w images. The contrast-enhancing and necrotic regions were segmented using FAST. From these sub-volumes and the total abnormal tumor bulk, a set of Radiomic features quantifying phenotypic differences based on the tumor intensity, shape and texture, were extracted from the post-contrast T1w images. Minimum-redundancy-maximum-relevance (MRMR) was used to identify the most informative Radiomic, VASARI and combined Radiomic-VASARI features in 70% of the dataset (training-set). Multivariate Cox-proportional hazards models were evaluated in 30% of the dataset (validation-set) using the C-index for OS. A bootstrap procedure was used to assess significance while comparing the C-Indices of the different models. Results: Overall, the Radiomic features showed a moderate correlation with the radiologist-annotated VASARI features (r = −0.37 – 0.49); however that correlation was stronger for the Tumor Diameter and Proportion of Necrosis VASARI features (r = −0.71 – 0.69). After MRMR feature selection, the best-performing Radiomic, VASARI, and Radiomic-VASARI Cox-PH models showed a validation C-index of 0.56 (p = NS), 0.58 (p = NS) and 0.65 (p = 0.01), respectively. The combined Radiomic-VASARI model C-index was significantly higher than that obtained from either the Radiomic or VASARI model alone (p = <0.001). Conclusion: Quantitative volumetric and textural Radiomic features complement the qualitative and semi-quantitative annotated VASARI feature set. The prognostic value of informative qualitative VASARI features such as Eloquent Brain and Multifocality is increased with the addition of quantitative volumetric and textural features from the contrast-enhancing and necrotic tumor regions. These results should be further evaluated in larger validation cohorts.

60 APPLIED LIFE SCIENCES↗

EXSCLAIM!: Harnessing materials science literature for self-labeled microscopy datasets

This work introduces the EXSCLAIM! toolkit for the automatic extraction, separation, and caption-based natural language annotation of images from scientific literature. EXSCLAIM! is used to show how rule-based natural language processing and image recognition can be leveraged to construct an electron microscopy data set containing thousands of keyword-annotated nanostructure images. Moreover, it is demonstrated how a combination of statistical topic modeling and semantic word similarity comparisons can be used to increase the number and variety of keyword annotations on top of the standard annotations from EXSCLAIM! With large-scale imaging datasets constructed from scientific literature, users are well positioned to train neural networks for classification and recognition tasks specific to microscopy-tasks often otherwise inhibited by a lack of sufficient annotated training data.

36 MATERIALS SCIENCE↗

Comprehensive SNP Data for 1,323 GWAS Population in Populus trichocarpa and Combined Annotation Files for P. trichocarpa v3.0 and v3.1

The VCF dataset includes genetic variations found in 1,323 Populus trichocarpa genotypes, providing valuable information for scientists studying plant genetics. Researchers have generated this dataset using whole-genome DNA short-read sequencing on the Illumina Genome Analyzer, HiSeq 2000, and HiSeq 2500 platforms. This sequencing effort ensured a minimum expected sequencing depth of 15×. The dataset comprises more than 9.7 million single nucleotide polymorphisms (SNPs) and indel variants. The combined annotation files are derived from P. trichocarpa v3.0 and v3.1. We merged these files to create a comprehensive annotation file used for GWAS analysis. In total, 38,830 genes overlapped between the two versions. For overlapping genes, we defined the start as the smaller and the end as the larger among the two versions to increase the likelihood of locating candidate genetic loci. Additionally, we included 2,505 unique genes from v3.0 and 4,120 unique genes from v3.1, resulting in a total of 45,455 genes in the updated annotation file.

09 BIOMASS FUELS↗

Bioinformatics resource manager v2.3: an integrated software environment for systems biology with microRNA and cross-species analysis tools

Background: MicroRNAs (miRNAs) are noncoding RNAs that direct post-transcriptional regulation of protein coding genes. Recent studies have shown miRNAs are important for controlling many biological processes, including nervous system development, and are highly conserved across species. Given their importance, computational tools are necessary for analysis, interpretation and integration of high-throughput (HTP) miRNA data in an increasing number of model species. The Bioinformatics Resource Manager (BRM) v2.3 is a software environment for data management, mining, integration and functional annotation of HTP biological data. In this study, we report recent updates to BRM for miRNA data analysis and cross-species comparisons across datasets. Results: BRM v2.3 has the capability to query predicted miRNA targets from multiple databases, retrieve potential regulatory miRNAs for known genes, integrate experimentally derived miRNA and mRNA datasets, perform ortholog mapping across species, and retrieve annotation and cross-reference identifiers for an expanded number of species. Here we use BRM to show that developmental exposure of zebrafish to 30 uM nicotine from 6–48 hours post fertilization (hpf) results in behavioral hyperactivity in larval zebrafish and alteration of putative miRNA gene targets in whole embryos at developmental stages that encompass early neurogenesis. We show typical workflows for using BRM to integrate experimental zebrafish miRNA and mRNA microarray datasets with example retrievals for zebrafish, including pathway annotation and mapping to human ortholog. Functional analysis of differentially regulated (p<0.05) gene targets in BRM indicates that nicotine exposure disrupts genes involved in neurogenesis, possibly through misregulation of nicotine-sensitive miRNAs. Conclusions: BRM provides the ability to mine complex data for identification of candidate miRNAs or pathways that drive phenotypic outcome and, therefore, is a useful hypothesis generation tool for systems biology. The miRNA workflow in BRM allows for efficient processing of multiple miRNA and mRNA datasets in a single software environment with the added capability to interact with public data sources and visual analytic tools for HTP data analysis at a systems level. BRM is developed using Java™ and other open-source technologies for free distribution (http://www.sysbio.org/dataresources/brm.stm).

59 BASIC BIOLOGICAL SCIENCES↗

LC-MS/MS-based proteome profiling in Daphnia pulex and Daphnia longicephala: the Daphnia pulex genome database as a key for high throughput proteomics in Daphnia

Background Daphniids, commonly known as waterfleas, serve as important model systems for ecology, evolution and the environmental sciences. The sequencing and annotation of the Daphnia pulex genome both open future avenues of research on this model organism. As proteomics is not only essential to our understanding of cell function, and is also a powerful validation tool for predicted genes in genome annotation projects, a first proteomic dataset is presented in this article. Results A comprehensive set of 701,274 peptide tandem-mass-spectra, derived from Daphnia pulex, was generated, which lead to the identification of 531 proteins. To measure the impact of the Daphnia pulex filtered models database for mass spectrometry based Daphnia protein identification, this result was compared with results obtained with the Swiss-Prot and the Drosophila melanogaster database. To further validate the utility of the Daphnia pulex database for research on other Daphnia species, additional 407,778 peptide tandem-mass-spectra, obtained from Daphnia longicephala, were generated and evaluated, leading to the identification of 317 proteins. Conclusion Peptides identified in our approach provide the first experimental evidence for the translation of a broad variety of predicted coding regions within the Daphnia genome. Furthermore it could be demonstrated that identification of Daphnia longicephala proteins using the Daphnia pulex protein database is feasible but shows a slightly reduced identification rate. Data provided in this article clearly demonstrates that the Daphnia genome database is the key for mass spectrometry based high throughput proteomics in Daphnia.

59 BASIC BIOLOGICAL SCIENCES↗

Metagenome and metatranscriptome data for Rifle CMT-03 laboratory microcosm experiment completed in April 2014

Sediment samples were collected during installation of monitoring borehole CMT-03. Microcosms were constructed and inoculated under anerobic conditions with these sediments and anaerobic Rifle artificial groundwater. Microcosm metagenomes and metatranscriptomes were sampled every 5 days for a period of 20 days. The dataset gives gene-level annotations, binning, metagenomic and metatranscriptomic coverages for these microcosms.

54 ENVIRONMENTAL SCIENCES↗

Phenotypically anchored transcriptomics across diverse agrichemicals reveals conserved pathways and unique gene expression signatures in zebrafish

Agrichemicals such as herbicides, fungicides, insecticides, and biocides are widely used in agriculture, yet some are associated with adverse effects in humans and the environment. While many of these chemicals have been extensively studied in vitro and are included in the EPA’s ToxCast program, comprehensive in vivo comparisons using RNA sequencing across structurally diverse agrichemicals, in a single screening platform, are lacking. In this study, we examined structurally diverse agrichemicals found in the U.S. Environmental Protection Agency’s (EPA) Toxcast Phase I and II library by statically exposing early life stage zebrafish at 6 h post fertilization (hpf) until 120 hpf at concentrations ranging from 0.25 to 100 µM. Morphological outcomes were assessed at 120 hpf across 10 endpoints, including yolk sac edema, craniofacial malformations, and axis abnormalities. Chemicals that produced robust concentration-response relationships were selected for transcriptomic profiling. For transcriptomic analysis, zebrafish were statically exposed to each chemical and sampled at 48 hpf, prior to the onset of morphological effects observed at 120 hpf. Differential expression analysis identified between 0 and 4,538 differentially expressed genes (DEGs) per chemical, with no clear correlation to morphological severity. Both DEG and co-expression network analyses revealed chemical-specific expression patterns that converged on shared biological pathways, including neurodevelopment and cytoskeletal organization. Key regulatory genes such as mylpfa and krt4 were identified within co-expression modules, suggesting their potential role in conserved toxicity mechanisms. Semantic similarity analysis of enriched gene ontology (GO) terms, when compared to existing datasets, highlighted gaps in the annotation of neurodevelopmental processes, indicating that some in vivo effects may not be fully captured by current curated resources. The results provide new insights into the modes of action of diverse agrichemicals and establish a framework for understanding how agrichemical structure relates to biological function in a vertebrate model.

agrichemical↗

Machine Vision based Sample-Tube Localization for Mars Sample Return

A potential Mars Sample Return (MSR) architecture is being jointly studied by NASA and ESA. As currently envisioned, the MSR campaign consists of a series of 3 missions: sample cache, fetch and return to Earth. In this paper, we focus on the fetch part of the MSR, and more specifically the problem of autonomously detecting and localizing sample tubes deposited on the Martian surface. Towards this end, we study two machine-vision based approaches: First, a geometrydriven approach based on template matching that uses hardcoded filters and a 3D shape model of the tube; and second, a data-driven approach based on convolutional neural networks (CNNs) and learned features. Furthermore, we present a large benchmark dataset of sample-tube images, collected in representative outdoor environments and annotated with ground truth segmentation masks and locations. The dataset was acquired systematically across different terrain, illumination conditions and dust-coverage; and benchmarking was performed to study the feasibility of each approach, their relative strengths and weaknesses, and robustness in the presence of adverse environmental conditions.

Detry, R.↗

scPlantAnnotate: an accurate and robust transformer-based model for plant cell type annotation

Accurate cell type annotation remains a major bottleneck in plant single-cell RNA sequencing (scRNA-seq), where existing tools are often adapted from animal studies and perform sub-optimally on plant data. The lack of plant-specific computational frameworks limits the construction of plant cell atlases and downstream biological discovery. We develop and evaluate scPlantAnnotate, a Transformer-based reference annotation framework tailored for plant scRNA-seq data, and benchmark it against state-of-the-art deep learning and conventional methods across multiple plant species. Species-specific scPlantAnnotate models were trained using curated datasets from Arabidopsis thaliana, Zea mays, Oryza sativa, and Glycine max. We compared scPlantAnnotate with leading baselines under both standard random-split evaluation and a more stringent leave-one-dataset-out setting, which tests robustness to completely unseen datasets and tissue types. scPlantAnnotate consistently outperforms existing approaches across all four species under random-split evaluation. In the leave-one-dataset-out setting for A. thaliana, where performance drops markedly for all methods due to strong batch effects and dataset heterogeneity, scPlantAnnotate nonetheless achieves the highest Accuracy, Macro-F1, Balanced Accuracy, and Macro-AUROC on average and ranks first on most held-out datasets. These results demonstrate improved robustness to dataset shifts, a critical yet underexplored challenge in plant scRNA-seq analysis. A freely accessible web server enables users to annotate their own datasets using pretrained models. scPlantAnnotate provides a plant-specific, Transformer-based framework for single-cell annotation that delivers state-of-the-art performance and enhanced robustness to unseen datasets. By addressing limitations of existing tools and enabling scalable reference-based annotation, scPlantAnnotate supports the development of comprehensive plant cell atlases and facilitates broader use of single-cell genomics in plant biology.

Bioinformatics↗

Small-wedge synchrotron and serial XFEL datasets for Cysteinyl leukotriene GPCRs

Structural studies of challenging targets such as G protein-coupled receptors (GPCRs) have accelerated during the last several years due to the development of new approaches, including small-wedge and serial crystallography. Here, we describe the deposition of seven datasets consisting of X-ray diffraction images acquired from lipidic cubic phase (LCP) grown microcrystals of two human GPCRs, Cysteinyl leukotriene receptors 1 and 2 (CysLT 1 R and CysLT 2 R), in complex with various antagonists. Five datasets were collected using small-wedge synchrotron crystallography (SWSX) at the European Synchrotron Radiation Facility with multiple crystals under cryo-conditions. Two datasets were collected using X-ray free electron laser (XFEL) serial femtosecond crystallography (SFX) at the Linac Coherent Light Source, with microcrystals delivered at room temperature into the beam within LCP matrix by a viscous media microextrusion injector. All seven datasets have been deposited in the open-access databases Zenodo and CXIDB. Here, we describe sample preparation and annotate crystallization conditions for each partial and full datasets. We also document full processing pipelines and provide wrapper scripts for SWSX and SFX data processing. A Correction to this paper has been published: https://doi.org/10.1038/s41597-020-00759-w

97 MATHEMATICS AND COMPUTING↗

Computerized comprehensive data analysis of Lung Imaging Database Consortium (LIDC)

Purpose: Lung Image Database Consortium (LIDC) is the largest public CT image database of lung nodules. In this study, the authors present a comprehensive and the most updated analysis of this dynamically growing database under the help of a computerized tool, aiming to assist researchers to optimally use this database for lung cancer related investigations. Methods: The authors developed a computer scheme to automatically match the nodule outlines marked manually by radiologists on CT images. A large variety of characteristics regarding the annotated nodules in the database including volume, spiculation level, elongation, interobserver variability, as well as the intersection of delineated nodule voxels and overlapping ratio between the same nodules marked by different radiologists are automatically calculated and summarized. The scheme was applied to analyze all 157 examinations with complete annotation data currently available in LIDC dataset. Results: The scheme summarizes the statistical distributions of the abovementioned geometric and diagnosis features. Among the 391 nodules, (1) 365 (93.35%) have principal axis length {<=}20 mm; (2) 120, 75, 76, and 120 were marked by one, two, three, and four radiologists, respectively; and (3) 122 (32.48%) have the maximum volume overlapping ratios {>=}80% for the delineations of two radiologists, while 198 (50.64%) have the maximum volume overlapping ratios <60%. The results also showed that 72.89% of the nodules were assessed with malignancy score between 2 and 4, and only 7.93% of these nodules were considered as severely malignant (malignancy {>=}4). Conclusions: This study demonstrates that LIDC contains examinations covering a diverse distribution of nodule characteristics and it can be a useful resource to assess the performance of the nodule detection and/or segmentation schemes.

60 APPLIED LIFE SCIENCES↗

The Porcelain Crab Transcriptome and PCAD, the Porcelain Crab Microarray and Sequence Database

Background: With the emergence of a completed genome sequence of the freshwater crustacean Daphnia pulex, construction of genomic-scale sequence databases for additional crustacean sequences are important for comparative genomics and annotation. Porcelain crabs, genus Petrolisthes, have been powerful crustacean models for environmental and evolutionary physiology with respect to thermal adaptation and understanding responses of marine organisms to climate change. Here, we present a large-scale EST sequencing and cDNA microarray database project for the porcelain crab Petrolisthes cinctipes. Methodology/Principal Findings: A set of ~;;30K unique sequences (UniSeqs) representing ~;;19K clusters were generated from ~;;98K high quality ESTs from a set of tissue specific non-normalized and mixed-tissue normalized cDNA libraries from the porcelain crab Petrolisthes cinctipes. Homology for each UniSeq was assessed using BLAST, InterProScan, GO and KEGG database searches. Approximately 66percent of the UniSeqs had homology in at least one of the databases. All EST and UniSeq sequences along with annotation results and coordinated cDNA microarray datasets have been made publicly accessible at the Porcelain Crab Array Database (PCAD), a feature-enriched version of the Stanford and Longhorn Array Databases.Conclusions/Significance: The EST project presented here represents the third largest sequencing effort for any crustacean, and the largest effort for any crab species. Our assembly and clustering results suggest that our porcelain crab EST data set is equally diverse to the much larger EST set generated in the Daphnia pulex genome sequencing project, and thus will be an important resource to the Daphnia research community. Our homology results support the pancrustacea hypothesis and suggest that Malacostraca may be ancestral to Branchiopoda and Hexapoda. Our results also suggest that our cDNA microarrays cover as much of the transcriptome as can reasonably be captured in EST library sequencing approaches, and thus represent a rich resource for studies of environmental genomics.

99 GENERAL AND MISCELLANEOUS↗

16s Amplicon Analysis of Soil Data for Interactive effects of depth and differential irrigation on soil microbiome composition and functioning

Genomic DNA was isolated from soil and rhizosphere samples using the Zymo Quick-DNA fecal/soil microbe miniprep kit (catalog no. D6010) according to the manufacturer’s instructions (Zymo Research; Irvine, CA) with the modification of eluting in 100 uL elution buffer. Sample concentrations were quantified using the Qubit dsDNA HS assay kit (Thermo Fisher). For rhizosphere samples only, DNA was subsequently purified using Zymo’s ZR-96 DNA Clean & Concentrator kit (catalog no. D4024) to account for low DNA concentrations of these samples. . In each replicate block, there were five drip irrigation treatments (T1 = 100% normal irrigation, T2 = 56.25%, T3 = 37.5%, T4 = 18.75% and T5=no irrigation. On July 20, the strength of the drought treatments was increased: T1 remained at 100%, whereas T2 changed from 75% to 56.25%, T2 changed from 50% to 37.5%, and T4 changed from 25% to 18.75%. Sequencing was performed as described previously (Naylor, Fansler, et al. 2020). Sequences were amplified on the MiSeq platform (Illumina, San Diego, CA) using 16S primers (515F and 806R) specific to the V4 region. Raw sequence data was processed with the pipeline Hundo for amplicon quality control and annotation. Downstream statistical analyses on 16S datasets were performed using the program R and the packages ‘phyloseq’ and ‘vegan’.

Soil microbiome, metatranscriptomics↗

Characterizing Families of Spectral Similarity Scores and Their Use Cases for Gas Chromatography–Mass Spectrometry Small Molecule Identification

Metabolomics provides a unique snapshot into the world of small molecules and the complex biological processes that govern the human, animal, plant, and environmental ecosystems encapsulated by the One Health modeling framework. However, this “molecular snapshot” is only as informative as the number of metabolites confidently identified within it. The spectral similarity (SS) score is traditionally used to identify compound(s) in mass spectrometry approaches to metabolomics, where spectra are matched to reference libraries of candidate spectra. Unfortunately, there is little consensus on which of the dozens of available SS metrics should be used. This lack of standard SS score creates analytic uncertainty and potentially leads to issues in reproducibility, especially as these data are integrated across other domains. In this work, we use metabolomic spectral similarity as a case study to showcase the challenges in consistency within just one piece of the One Health framework that must be addressed to enable data science approaches for One Health problems. Here, using a large cohort of datasets comprising both standard and complex datasets with expert-verified truth annotations, we evaluated the effectiveness of 66 similarity metrics to delineate between correct matches (true positives) and incorrect matches (true negatives). We additionally characterize the families of these metrics to make informed recommendations for their use. Our results indicate that specific families of metrics (the Inner Product, Correlative, and Intersection families of scores) tend to perform better than others, with no single similarity metric performing optimally for all queried spectra. This work and its findings provide an empirically-based resource for researchers to use in their selection of similarity metrics for GC-MS identification, increasing scientific reproducibility through taking steps towards standardizing identification workflows.

59 BASIC BIOLOGICAL SCIENCES↗

VERIFICATION & VALIDATION OF A SEMANTIC IMAGE TAGGING FRAMEWORK VIA GENERATION OF GEOSPATIAL IMAGERY GROUND TRUTH

As a result of increasing geospatial image libraries, many algorithms are being developed to automatically extract and classify regions of interest from these images. However, limited work has been done to compare, validate and verify these algorithms due to the lack of datasets with high accuracy ground truth annotations. In this paper, we present an approach to generate a large number of synthetic images accompanied by perfect ground truth annotation via learning scene statistics from few training images through Maximum Entropy (ME) modeling. The ME model [1,2] embeds a Stochastic Context Free Grammar (SCFG) to model object attribute variations with Markov Random Fields (MRF) with the final goal of modeling contextual relations between objects. Using this model, 3D scenes are generated by configuring a 3D object model to obey the learned scene statistics. Finally, these plausible 3D scenes are captured by ray tracing software to produce synthetic images with the corresponding ground truth annotations that are useful for evaluating the performance of a variety of image analysis algorithms.

Markov Random Field (MRF)↗

BigNeuron: a resource to benchmark and predict performance of algorithms for automated tracing of neurons in light microscopy datasets

BigNeuron is an open community bench-testing platform with the goal of setting open standards for accurate and fast automatic neuron tracing. We gathered a diverse set of image volumes across several species that is representative of the data obtained in many neuroscience laboratories interested in neuron tracing. Here, we report generated gold standard manual annotations for a subset of the available imaging datasets and quantified tracing quality for 35 automatic tracing algorithms. The goal of generating such a hand-curated diverse dataset is to advance the development of tracing algorithms and enable generalizable benchmarking. Together with image quality features, we pooled the data in an interactive web application that enables users and developers to perform principal component analysis, t-distributed stochastic neighbor embedding, correlation and clustering, visualization of imaging and tracing data, and benchmarking of automatic tracing algorithms in user-defined data subsets. The image quality metrics explain most of the variance in the data, followed by neuromorphological features related to neuron size. Furthermore, we observed that diverse algorithms can provide complementary information to obtain accurate results and developed a method to iteratively combine methods and generate consensus reconstructions. The consensus trees obtained provide estimates of the neuron structure ground truth that typically outperform single algorithms in noisy datasets. However, specific algorithms may outperform the consensus tree strategy in specific imaging conditions. Finally, to aid users in predicting the most accurate automatic tracing results without manual annotations for comparison, we used support vector machine regression to predict reconstruction quality given an image volume and a set of automatic tracings.

97 MATHEMATICS AND COMPUTING↗

Profile Images and Annotations for Vehicle Re-identification Algorithms (PRIMAVERA)

This dataset contains 636,246 profile images of vehicles representing 13,963 unique vehicles. The data was collected by a set of roadside sensors over the course of three years. Each time a vehicle passed by one of the sensors, a series of images was collected. The images were processed to detect and localize each vehicle, and a license plate reader collocated with the sensor was used to provide a unique ID for the vehicle. Actual license plate numbers have been obfuscated by replacing with an arbitrary numerical ID for each vehicle. After localizing the vehicle in each image, the original RGB image was rotated, scaled, and shifted to produce a new RGB image of size 234x234 pixels such that the outermost two wheels are located at predetermined pixel locations in the image. In this way, all vehicle images are aligned to one another. This registration process occasionally results in a portion of certain vehicles being cutoff at the edges of the image. The dataset has been partitioned into two sets called training and validation. The two partitions no common vehicles, i.e., a vehicle present in one partition is guaranteed not to be present in the other. In this way, an algorithm can be validated against a set of new vehicles that were not seen during the training process. The training set contains 543,926 images from 64,440 vehicle passes representing 11,918 unique vehicles, while the validation set contains 92,320 images from 10,991 vehicle passes representing 2,045 unique vehicles. Vehicle images are organized by directories corresponding to unique vehicles. The file naming scheme is as follows: veh_{vehID}_tr_{passID}_{frameID}_{elevation}_{timeofday}.jpg where {vehID} is the vehicle ID (unique across the entire dataset), {passID} is an identifier for each tracked vehicle pass (unique across the entire dataset), {frameID} is the index of the frame within the given vehicle pass starting at 0, {elevation} is a two-letter string indicating whether the sensor was elevated (el) or at ground-level (gl), and {timeofday} is a two-letter string indicating whether the image was captured during daytime (dt) or nighttime (nt).

image↗