8 December 2015 Geometric filtration of classification-based object detectors in realtime road scene recognition systems
Author Affiliations +
Proceedings Volume 9875, Eighth International Conference on Machine Vision (ICMV 2015); 98750O (2015) https://doi.org/10.1117/12.2228709
Event: Eighth International Conference on Machine Vision, 2015, Barcelona, Spain
Abstract
We study the issue of performance improvement of classification-based object detectors by including certain geometric-oriented filters. Configurations of the observed 3D scene may be used as a priori or a posteriori information for object filtration. A priori information is used to select only those object parameters (size and position on image plane) that are in accordance with the scene, restricting implausible combinations of parameters. On the other hand the detection robustness can be enhanced by rejecting detection results using a posteriori information about 3D scene. For example, relative location of detected objects can be used as criteria for filtration. We have included proposed filters in object detection modules of two different industrial vision-based recognition systems and compared the resulting detection quality before detectors improving and after. Filtering with a priori information leads to significant decrease of detector's running time per frame and increase of number of correctly detected objects. Including filter based on a posteriori information leads to decrease of object detection false positive rate.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Viktor Prun, Viktor Prun, Dmitry Bocharov, Dmitry Bocharov, Ivan Koptelov, Ivan Koptelov, Dmitry Sholomov, Dmitry Sholomov, Vassily Postnikov, Vassily Postnikov, } "Geometric filtration of classification-based object detectors in realtime road scene recognition systems", Proc. SPIE 9875, Eighth International Conference on Machine Vision (ICMV 2015), 98750O (8 December 2015); doi: 10.1117/12.2228709; https://doi.org/10.1117/12.2228709
PROCEEDINGS
5 PAGES


SHARE
Back to Top