Shivani Agarwal

Associate Professor of Computer and Information Science
Associate Professor of Statistics and Data Science
University of Pennsylvania

Object Detection in Computer Vision

[Summary & Contributions] | [Relevant Publications]

Summary and Contributions

We applied machine learning to the problem of detecting objects in images (see figure below). Prior to our work, different research studies used different performance measures to evaluate object detection algorithms, which made it difficult to compare different approaches. A key contribution of our work was to propose a standardized performance measure for object detection; this was widely accepted in the computer vision community, and has led to over 2000 citations to our work.

Examples of predictions made by our object detection algorithm.

Relevant Publications

  • Shivani Agarwal, Aatif Awan and Dan Roth.
    Learning to detect objects in images via a sparse, part-based representation.
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(11):1475-1490, 2004.
    [pdf]

  • Shivani Agarwal and Dan Roth.
    Learning a sparse representation for object detection.
    In Proceedings of the 7th European Conference on Computer Vision (ECCV), 2002.
    Published as Lecture Notes in Computer Science, volume 2353, pages 113-130, Springer-Verlag, 2002.
    [pdf]

Back to Research