Corpus ID: 16404908

Performance evaluation of road detection and following algorithms

  title={Performance evaluation of road detection and following algorithms},
  author={Tsai Hong and Ayako Takeuchi and M Foedissch and Michael Shneier},
We describe a methodology for evaluating algorithms to provide quantitative information about how well road detection and road following algorithms perform. The approach relies on generating a set of standard data sets annotated with ground truth. We evaluate the algorithms used to detect roads by comparing the output of the algorithms with ground truth, which we obtain by having humans annotate the data sets used to test the algorithms. Ground truth annotations are acquired from more than one… Expand
Novel Index for Objective Evaluation of Road Detection Algorithms
  • J. Álvarez, A. López
  • Computer Science, Engineering
  • 2008 11th International IEEE Conference on Intelligent Transportation Systems
  • 2008
A composite index to quantitatively assess the performance of road detection algorithms is presented, based on a weighted combination of different evaluations which use a trade-off between precision and recall scores. Expand
Performance analysis of a new road following algorithm based on color models
This paper describes and evaluates a vision system that accurately segments unstructured, non-homogeneous roads of arbitrary shape under various lighting conditions. The idea behind the roadExpand


An Objective Comparison Methodology of Edge Detection Algorithms Using a Structure from Motion Task
This paper presents a task-oriented evaluation methodology for edge detectors using real image sequences from 2 different scenes varying in the complexity and scenery types to measure performance based on the task of structure from motion. Expand
Edge Detector Evaluation Using Empirical ROC Curves
This work demonstrates a method for evaluating edge detector performance based on receiver operating characteristic (ROC) curves and analyzes the performance of 11 different edge detectors reported in the literature. Expand
Performance analysis of a simple vehicle detection algorithm
An end-to-end analysis of a simple model-based vehicle detection algorithm for aerial parking lot images by combining four elongated edge operators designed to collect edge responses from the sides of a vehicle is performed. Expand
Internal self-diagnosis and external evaluation of the obt ained results are of major importance for the relevance of any automatic system for practical appl ications. Obviously, this statement isExpand
Performance Assessment Through Bootstrap
A new performance evaluation paradigm for computer vision systems is proposed that exploits a resampling technique recently introduced in statistics, the bootstrap, to derive confidence in the adequacy of the assumptions embedded into the computational procedure for the given input. Expand
Automated performance evaluation of range image segmentation
An automated framework for objectively evaluating the performance of region segmentation algorithms is developed and demonstrated with range image data sets, but is applicable to any type of imagery. Expand
Contextual and non-contextual performance evaluation of edge detectors
Two new evaluation methods for edge detectors are presented, non-contextual and concerns the evaluation of edge detector performance in terms of detection errors and contextual method, which evaluates the performance of edge detectors in the context of image reconstruction. Expand
Performance Evaluation and Analysis of Monocular Building Extraction From Aerial Imagery
An end-to-end performance evaluation of four existing monocular building extraction systems, using image space and object space-based metrics on 83 test images of 18 sites, and demonstrates the utility of rigorous photogrammetric object space modeling and primitive-based representations for building extraction. Expand
Algorithmic modelling for performance evaluation
Unless algorithms are evaluated – and in a manner that can be used to predict the capabilities of a technique on an unseen data set – it is unlikely to be re-implemented and used. Expand