Descriptor: Smart Event Face Dataset (SEFD)

dc.contributor.authorIslam, Riadul
dc.contributor.authorTummala, Sri Ranga Sai Krishna
dc.contributor.authorMule, Joey
dc.contributor.authorKankipati, Rohith
dc.contributor.authorJalapally, Suraj Kumar
dc.contributor.authorChallagundla, Dhandeep
dc.contributor.authorHoward, Chad
dc.contributor.authorRobucci, Ryan
dc.date.accessioned2025-04-23T20:31:19Z
dc.date.available2025-04-23T20:31:19Z
dc.date.issued2024-10-23
dc.description.abstractSmart focal-plane and in-chip image processing has emerged as a crucial technology for vision-enabled embedded systems with energy efficiency and privacy. However, the lack of special datasets providing examples of the data that these neuromorphic sensors compute to convey visual information has hindered the adoption of these promising technologies. Neuromorphic imager variants, including event-based sensors, produce various representations such as streams of pixel addresses representing time and locations of intensity changes in the focal plane, temporal-difference data, data sifted/thresholded by temporal differences, image data after applying spatial transformations, optical flow data, and/or statistical representations. To address the critical barrier to entry, we provide an annotated, temporal-threshold-based vision dataset specifically designed for face detection tasks derived from the same videos used for Aff-Wild2. By offering multiple threshold levels (e.g., 4, 8, 12, and 16), this dataset allows for comprehensive evaluation and optimization of state-of-the-art neural architectures under varying conditions and settings compared to traditional methods. The accompanying tool flow for generating event data from raw videos further enhances accessibility and usability. We anticipate that this resource will significantly support the development of robust vision systems based on smart sensors that can process based on temporal-difference thresholds, enabling more accurate and efficient object detection and localization and ultimately promoting the broader adoption of low-power, neuromorphic imaging technologies. IEEE SOCIETY/COUNCIL Signal Processing Society (SPS) DATA TYPE/LOCATION Images; MD, USA DATA DOI/PID 10.21227/bw2e-dj78
dc.description.sponsorshipThis work was supported in part by the National Science Foundation (NSF) under Grant 2138253, in part by the Maryland Industrial Partnerships (MIPS) program under Grant MIPS0012, and in part by the UMBC Startup grant
dc.description.urihttps://ieeexplore.ieee.org/abstract/document/10732017
dc.format.extent8 pages
dc.genrejournal articles
dc.identifierdoi:10.13016/m2qxw5-9twc
dc.identifier.citationIslam, Riadul, Sri Ranga Sai Krishna Tummala, Joey Mulé, Rohith Kankipati, Suraj Jalapally, Dhandeep Challagundla, Chad Howard, and Ryan Robucci. “Descriptor: Smart Event Face Dataset (SEFD).” IEEE Data Descriptions 1 (2024): 33–40. https://doi.org/10.1109/IEEEDATA.2024.3485026.
dc.identifier.urihttps://doi.org/10.1109/IEEEDATA.2024.3485026
dc.identifier.urihttp://hdl.handle.net/11603/38038
dc.language.isoen_US
dc.publisherIEEE
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Student Collection
dc.relation.ispartofUMBC Faculty Collection
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department
dc.rightsAttribution 4.0 International CC BY 4.0 Deed
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/deed.en
dc.subjectUMBC Covail Lab
dc.subjectsparse vision
dc.subjectLocation awareness
dc.subjectconvolutional neural network (CNN)
dc.subjectIntelligent sensors
dc.subjectHeuristic algorithms
dc.subjectSensors
dc.subjectVoltage control
dc.subjectFace detection
dc.subjectDVS
dc.subjectEvent detection
dc.subjectData models
dc.subjectUMBC Multi-Scale Thermal Transport Research Lab
dc.subjectface detection
dc.subjectConvolutional neural networks
dc.subjectUMBC VLSI-SOC GROUP
dc.subjectVideos
dc.subjectAff-Wild
dc.subjectUMBC Cybersecurity Institute
dc.subjectComputer architecture
dc.subjectface dataset
dc.titleDescriptor: Smart Event Face Dataset (SEFD)
dc.typeText
dcterms.creatorhttps://orcid.org/0000-0002-4649-3467
dcterms.creatorhttps://orcid.org/0009-0002-8522-0872
dcterms.creatorhttps://orcid.org/0009-0003-9737-2782
dcterms.creatorhttps://orcid.org/0000-0001-7491-1710
dcterms.creatorhttps://orcid.org/0009-0008-4077-0313

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Descriptor_Smart_Event_Face_Dataset_SEFD.pdf
Size:
4.13 MB
Format:
Adobe Portable Document Format