David J. Brady

About

David J. Brady is a professor at Duke University associated with the Pratt School of Engineering. The page does not provide specific details about his research focus, background, or key contributions, and no biographical information is available beyond his title and affiliation.

Research topics

• Computer Science
• Optics
• Artificial Intelligence
• Physics
• Human–computer interaction
• Nanotechnology
• Algorithm
• Materials science
• Computer vision
• Cartography

Selected publications

• PANDA: A Gigapixel-Level Human-Centric Video Dataset

  2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2020 · 95 citations

  We present PANDA, the first gigaPixel-level humAN-centric viDeo dAtaset, for large-scale, long-term, and multi-object visual analysis. The videos in PANDA were captured by a gigapixel camera and cover real-world scenes with both wide field-of-view (~1 square kilometer area) and high-resolution details (~gigapixel-level/frame). The scenes may contain 4k head counts with over 100× scale variation. PANDA provides enriched and hierarchical ground-truth annotations, including 15,974.6k bounding boxes…

  DOI

• Low latency streaming from a multicamera array to a UHD display wall

  2026-03-05

  articleSenior author
  PublisherDOI

• Sparse Transformer for Ultra-sparse Sampled Video Compressive Sensing

  ArXiv.org · 2025-09-10

  preprintOpen access

  Digital cameras consume ~0.1 microjoule per pixel to capture and encode video, resulting in a power usage of ~20W for a 4K sensor operating at 30 fps. Imagining gigapixel cameras operating at 100-1000 fps, the current processing model is unsustainable. To address this, physical layer compressive measurement has been proposed to reduce power consumption per pixel by 10-100X. Video Snapshot Compressive Imaging (SCI) introduces high frequency modulation in the optical sensor layer to increase effec…

  PublisherOA PDFDOI

• Multiscale aperture synthesis imager

  ArXiv.org · 2025-11-08

  preprintOpen access

  Synthetic aperture imaging has enabled breakthrough observations from radar to astronomy. However, optical implementation remains challenging due to stringent wavefield synchronization requirements among multiple receivers. Here we present the multiscale aperture synthesis imager (MASI), which utilizes parallelism to break complex optical challenges into tractable sub-problems. MASI employs a distributed array of coded sensors that operate independently yet coherently to surpass the diffraction…

  PublisherOA PDFDOI

Recent grants

• Collaborative Research: IDBR: New Technology to Measure Oganismal Color Phenotypes: 3D, Hyperspectral, UV-Vis, Virtual Reality Models of Organismal Coloration

  NSF · $111k · 2009–2012

Frequent coauthors

• Zhan Ma

  Nanjing University

  89 shared

• Weipeng Zhao

  Zhongshan Hospital

  82 shared

• Yi Lin

  Sun Yat-sen University

  82 shared

• Lili Dong

  Fudan University

  82 shared

• Daniel L. Marks

  80 shared

• Xun Cao

  79 shared

• Yi Si

  Zhejiang University

  78 shared

• You Zhou

  Zhongshan Hospital

  77 shared

Labs

• David J. Brady LabPI

Similar researchers at Duke University

• Eric Brubakerh-96
• Avner Vengoshh-77
• Royston Edwin Carterh-62