This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Efficient, Simultaneous Detection of Multiple Object Classes

Philipp Zehnder, Esther Koller-Meier, Luc Van Gool
18th International Conference on Pattern Recognition (ICPR 2006)
August 2006


At present, the object categorisation literature is still dominated by the use of individual class detectors. Detect- ing multiple classes then implies the subsequent application of multiple such detectors, but such an approach is not scal- able towards high numbers of classes. This paper presents an alternative strategy, where multiple classes are detected in a combined way. This includes a decision tree approach, where ternary rather than binary nodes are used, and where nodes share features. This yields an efficient scheme, which scales much better. The paper proposes a strategy where the object samples are first distinguished from the background. Then, in a second stage, the actual object class membership of each sample is determined. The focus of the paper lies en- tirely on the first stage, i.e. the distinction from background. The tree approach for this step is compared against two al- ternative strategies, one of them being the popular cascade approach. While classification accuracy tends to be better or comparable, the speed of the proposed method is system- atically better. This advantage gets more outspoken as the number of object classes increases.

Download in pdf format
  author = {Philipp Zehnder and Esther Koller-Meier and Luc Van Gool},
  title = {Efficient, Simultaneous Detection of Multiple Object Classes},
  booktitle = {18th International Conference on Pattern Recognition (ICPR 2006)},
  year = {2006},
  month = {August},
  keywords = {object detection}