-
Article
Scene Understanding by Reasoning Stability and Safety
This paper presents a new perspective for 3D scene understanding by reasoning object stability and safety using intuitive mechanics. Our approach utilizes a simple observation that, by human design, objects in...
-
Chapter and Conference Paper
Normalized Joint Mutual Information Measure for Image Segmentation Evaluation with Multiple Ground-Truth Images
Supervised or ground-truth-based image segmentation evaluation paradigm plays an important role in objectively evaluating segmentation algorithms. So far, many evaluation methods in terms of comparing clusteri...
-
Chapter and Conference Paper
Contour Grou** by Clustering with Multi-feature Similarity Measure
Contour grou** is a key task in computer vision domain. It extracts the meaningful objects information from low-level image features and provides the input for the further processing. There have been many te...
-
Chapter and Conference Paper
Vague Neural Network Based Reinforcement Learning Control System for Inverted Pendulum
Reinforcement learning is a class of model-free learning control method that can solve Markov decision problems. But it has some problems in applications, especially in MDPs of continuous state spaces. In this...
-
Chapter and Conference Paper
Vague Neural Network Controller and Its Applications
Fuzzy neural network is a promising intelligence system that combines the artificial neural network and fuzzy logic. However fuzzy neural network has its shortages: fuzzy membership function has only one singl...