Modeling, evaluation and control of a road image processing chain

Authors:
Yves Lucas;Antonio Domingues;Driss Driouchi;Pierre Marché
Affiliations:
Vision and Robotics Lab, IUT Mesures Physiques, Orleans University, Bourges cedex, France;Vision and Robotics Lab, ENSI of Bourges, Bourges, France;Vision and Robotics Lab, ENSI of Bourges, Bourges, France;Theoretical and Applied Statistics Lab, Pierre & Marie Curie University, Paris, France
Venue:
SCIA'05 Proceedings of the 14th Scandinavian conference on Image Analysis
Year:
2005

Citing 8
Cited 1

Empirical Performance Evaluation of Graphics Recognition Systems

IEEE Transactions on Pattern Analysis and Machine Intelligence
Empirical Evaluation Techniques in Computer Vision

Empirical Evaluation Techniques in Computer Vision
Input Guided Performance Evaluation

Proceedings of the Theoretical Foundations of Computer Vision, TFCV on Performance Characterization in Computer Vision
Evaluation of Salient Point Techniques

CIVR '02 Proceedings of the International Conference on Image and Video Retrieval
Evaluation of global image thresholding for change detection

Pattern Recognition Letters
A Method for Objective Edge Detection Evaluation and Detector Parameter Selection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Machine learning for adaptive image interpretation

IAAI'04 Proceedings of the 16th conference on Innovative applications of artifical intelligence
A hierarchical approach to color image segmentation using homogeneity

IEEE Transactions on Image Processing

Design of experiments for performance evaluation and parameter tuning of a road image processing chain

EURASIP Journal on Applied Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Tuning a complete image processing chain (IPC) remains a tricky step. Until now researchers focused on the evaluation of single algorithms, based on a small number of test images and ad hoc tuning independent of input data. In this paper we explain how, by combining statistical modeling with design of experiments, numerical optimization and neural learning, it is possible to elaborate a powerful and adaptive IPC. To succeed, it is necessary to build a large image database, to describe input images and finally to evaluate the IPC output. By testing this approach on an IPC dedicated to road obstacle detection, we demonstrate that this experimental methodology and software architecture ensure a steady efficiency. The reason is simple: the IPC is globally optimized, from a large number of real images (180 out of a sequence of 30 000) and with adaptive processing of input data.