- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 15th Conference on Computer and Robot Vision (CRV) - Toronto, ON, Canada (2018.5.8-2018.5.10)] 2018 15th Conference on Computer and Robot Vision (CRV) - Disparity Filtering with 3D Convolutional Neural Networks
摘要： Stereo matching is an ill-posed problem and hence the disparity maps generated are often inaccurate and noisy. To alleviate the problem, a number of approaches were proposed to output accurate disparity values for selected pixels only. Instead of designing another disparity optimization method for sparse disparity matching, we present a novel disparity filtering step that detects and removes inaccurate matches. Based on 3D convolutional neutral networks, our detector is trained directly on 3D matching cost volumes and hence can work with different matching cost generation approaches. The experimental results show that it can effectively filter out mismatches while preserving the accurate ones. As a result, combining our approach with the simplest Winner-Take-All optimization will lead to a better performance than most existing sparse stereo matching algorithms on the Middlebury Stereo Evaluation site.
关键词： stereo matching,confidence measure,3D CNNs
更新于2025-09-23 15:23:52
-
[IEEE 2018 IEEE Congress on Evolutionary Computation (CEC) - Rio de Janeiro (2018.7.8-2018.7.13)] 2018 IEEE Congress on Evolutionary Computation (CEC) - Confidence Measures for Carbon-Nanotube / Liquid Crystals Classifiers
摘要： This paper focuses on a performance analysis of single-walled-carbon-nanotube / liquid crystal classifiers produced by evolution in materio. A new confidence measure is proposed in this paper. It is different from statistical tools commonly used to evaluate the performance of classifiers in that it is based on physical quantities extracted from the composite and related to its state. Using this measure, it is confirmed that in an un-trained state, ie: before being subjected to an algorithm-controlled evolution, the carbon-nanotube-based composites classify data at random. The training, or evolution, process brings these composites into a state where the classification is no longer random. Instead, the classifiers generalise well to unseen data and the classification accuracy remains stable across tests. The confidence measure associated with the resulting classifier’s accuracy is relatively high at the classes’ boundaries, which is consistent with the problem formulation.
关键词： confidence measure,evolution in materio,classifiers,liquid crystal,single-walled-carbon-nanotube
更新于2025-09-10 09:29:36