Rapid Deformable Object Detection using Bounding-based Techniques

Abstract : In this work we use bounding-based techniques, such as Branch-and-Bound (BB) and Cascaded Detection (CD) to efficiently detect objects with Deformable Part Models (DPMs). Instead of evaluating the classifier score exhaustively over all image locations and scales, we use bounding to focus on promising image locations. The core problem is to compute bounds that accommodate part deformations; for this we adapt the Dual Trees data structure to our problem. We evaluate our approach using DPMs. We obtain exactly the same results but can perform the part combination substantially faster; for a conservative threshold the speedup can be double, for a less conservative we can have tenfold or higher speedups. These speedups refer to the part combination process, after the unary part scores have been computed. We also develop a multiple-object detection variation of the system, where hypotheses for 20 categories are inserted in a common priority queue. For the problem of finding the strongest category in an image this can result in more than 100-fold speedups.
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download

https://hal.inria.fr/hal-00696120
Contributor : Iasonas Kokkinos <>
Submitted on : Thursday, May 10, 2012 - 10:58:45 PM
Last modification on : Thursday, February 7, 2019 - 5:29:19 PM
Long-term archiving on : Saturday, August 11, 2012 - 2:41:42 AM

File

RR7940.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00696120, version 1

Collections

Citation

Iasonas Kokkinos. Rapid Deformable Object Detection using Bounding-based Techniques. [Research Report] RR-7940, INRIA. 2012. ⟨hal-00696120⟩

Share

Metrics

Record views

313

Files downloads

448