Computer Vision - ECCV 2004

Volume 3023 of the series Lecture Notes in Computer Science pp 224-237

Recognizing Objects in Range Data Using Regional Point Descriptors

  • Andrea FromeAffiliated withUniversity of California Berkeley
  • , Daniel HuberAffiliated withCarnegie Mellon University
  • , Ravi KolluriAffiliated withUniversity of California Berkeley
  • , Thomas BülowAffiliated withUniversity of California Berkeley
  • , Jitendra MalikAffiliated withUniversity of California Berkeley

* Final gross prices may vary according to local VAT.

Get Access


Recognition of three dimensional (3D) objects in noisy and cluttered scenes is a challenging problem in 3D computer vision. One approach that has been successful in past research is the regional shape descriptor. In this paper, we introduce two new regional shape descriptors: 3D shape contexts and harmonic shape contexts. We evaluate the performance of these descriptors on the task of recognizing vehicles in range scans of scenes using a database of 56 cars. We compare the two novel descriptors to an existing descriptor, the spin image, showing that the shape context based descriptors have a higher recognition rate on noisy scenes and that 3D shape contexts outperform the others on cluttered scenes.