Chiou-Shann Fuh

Road-sign detection and tracking

In a visual driver-assistance system, road-sign detection and tracking is one of the major tasks. This study describes an approach to detecting and tracking road signs appearing in complex traffic scenes. In the detection phase, two neural networks are developed to extract color and shape features of traffic signs from the input scenes images. Traffic signs are then located in the images based on the extracted features. This process is primarily conceptualized in terms of fuzzy-set discipline. In the tracking phase, traffic signs located in the previous phase are tracked through image sequences using a Kalman filter. The experimental results demonstrate that the proposed method performs well in both detecting and tracking road signs present in complex scenes and in various weather and illumination conditions.

Fast block matching algorithm based on the winner-update strategy

Block matching is a widely used method for stereo vision, visual tracking, and video compression. Many fast algorithms for block matching have been proposed in the past, but most of them do not guarantee that the match found is the globally optimal match in a search range. This paper presents a new fast algorithm based on the winner-update strategy which utilizes an ascending lower bound list of the matching error to determine the temporary winner. Two lower bound lists derived by using partial distance and by using Minkowskis inequality are described. The basic idea of the winner-update strategy is to avoid, at each search position, the costly computation of the matching error when there exists a lower bound larger than the global minimum matching error. The proposed algorithm can significantly speed up the computation of the block matching because: 1) computational cost of the lower bound we use is less than that of the matching error itself; 2) an element in the ascending lower bound list will be calculated only when its preceding element has already been smaller than the minimum matching error computed so far; 3) for many search positions, only the first several lower bounds in the list need to be calculated. Our experiments have shown that, when applying to motion vector estimation for several widely-used test videos, 92% to 98% of operations can be saved while still guaranteeing the global optimality. Moreover, the proposed algorithm can be easily modified either to meet the limited time requirement or to provide an ordered list of best candidate matches. Our source codes of the proposed algorithm are available at http://smart.iis.sinica.edu.tw/html/winup.html.

Multiple Kernel Learning for Dimensionality Reduction

In solving complex visual learning tasks, adopting multiple descriptors to more precisely characterize the data has been a feasible way for improving performance. The resulting data representations are typically high-dimensional and assume diverse forms. Hence, finding a way of transforming them into a unified space of lower dimension generally facilitates the underlying tasks such as object recognition or clustering. To this end, the proposed approach (termed MKL-DR) generalizes the framework of multiple kernel learning for dimensionality reduction, and distinguishes itself with the following three main contributions: First, our method provides the convenience of using diverse image descriptors to describe useful characteristics of various aspects about the underlying data. Second, it extends a broad set of existing dimensionality reduction techniques to consider multiple kernel learning, and consequently improves their effectiveness. Third, by focusing on the techniques pertaining to dimensionality reduction, the formulation introduces a new class of applications with the multiple kernel learning framework to address not only the supervised learning problems but also the unsupervised and semi-supervised ones.

An automatic road sign recognition system based on a computational model of human recognition processing

This paper presents an automatic road sign detection and recognition system that is based on a computational model of human visual recognition processing. Road signs are typically placed either by the roadside or above roads. They provide important information for guiding, warning, or regulating the behaviors drivers in order to make driving safer and easier. The proposed recognition system is motivated by human recognition processing. The system consists of three major components: sensory, perceptual, and conceptual analyzers. The sensory analyzer extracts the spatial and temporal information of interest from video sequences. The extracted information then serves as the input stimuli to a spatiotemporal attentional (STA) neural network in the perceptual analyzer. If stimulation continues, focuses of attention will be established in the neural network. Potential features of road signs are then extracted from the image areas corresponding to the focuses of attention. The extracted features are next fed into the conceptual analyzer. The conceptual analyzer is composed of two modules: a category module and an object module. The former uses a configurable adaptive resonance theory (CART) neural network to determine the category of the input stimuli, whereas the later uses a configurable heteroassociative memory (CHAM) neural network to recognize an object in the determined category of objects. The proposed computational model has been used to develop a system for automatically detecting and recognizing road signs from sequences of traffic images. The experimental results revealed both the feasibility of the proposed computational model and the robustness of the developed road sign detection system.

Local Ensemble Kernel Learning for Object Category Recognition

This paper describes a local ensemble kernel learning technique to recognize/classify objects from a large number of diverse categories. Due to the possibly large intraclass feature variations, using only a single unified kernel-based classifier may not satisfactorily solve the problem. Our approach is to carry out the recognition task with adaptive ensemble kernel machines, each of which is derived from proper localization and regularization. Specifically, for each training sample, we learn a distinct ensemble kernel constructed in a way to give good classification performance for data falling within the corresponding neighborhood. We achieve this effect by aligning each ensemble kernel with a locally adapted target kernel, followed by smoothing out the discrepancies among kernels of nearby data. Our experimental results on various image databases manifest that the technique to optimize local ensemble kernels is effective and consistent for object recognition.

Hierarchical color image region segmentation for content-based image retrieval system

In this work, we propose a model of a content-based image retrieval system by using the new idea of combining a color segmentation with relationship trees and a corresponding tree-matching method. We retain the hierarchical relationship of the regions in an image during segmentation. Using the information of the relationships and features of the regions, we can represent the desired objects in images more accurately. In retrieval, we compare not only region features but also region relationships.

Motion displacement estimation using an affine model for image matching

A model is developed for estimating the displacement field in spatio-temporal image sequences that allows for affine shape deformations of corresponding spatial regions and for affine transformations of the image intensity range. This model includes the block matching method as a special case. The model parameters are found by using a least-squares algorithm. We demonstrate experimentally that the affine matching algorithm performs better in estimating displacements than other standard approaches, especially for long-range motion with possible changes in scene illumination. The algorithm is successfully applied to various classes of moving imagery, including the tracking of cloud motion.

Automatic change detection of driving environments in a vision-based driver assistance system

Detecting critical changes of environments while driving is an important task in driver assistance systems. In this paper, a computational model motivated by human cognitive processing and selective attention is proposed for this purpose. The computational model consists of three major components, referred to as the sensory, perceptual, and conceptual analyzers. The sensory analyzer extracts temporal and spatial information from video sequences. The extracted information serves as the input stimuli to a spatiotemporal attention (STA) neural network embedded in the perceptual analyzer. If consistent stimuli repeatedly innervate the neural network, a focus of attention will be established in the network. The attention pattern associated with the focus, together with the location and direction of motion of the pattern, form what we call a categorical feature. Based on this feature, the class of the attention pattern and, in turn, the change in driving environment corresponding to the class are determined using a configurable adaptive resonance theory (CART) neural network, which is placed in the conceptual analyzer. Various changes in driving environment, both in daytime and at night, have been tested. The experimental results demonstrated the feasibilities of both the proposed computational model and the change detection system.

A novel automatic white balance method for digital still cameras

Automatic white balance is an important function of digital still cameras. The goal of white balance is to adjust the image such that it looks as if it is taken under canonical light. We proposed a novel technique to detect reference white points in an image. Our algorithm uses dynamic threshold for white point detection and is more flexible than other existing ad hoc algorithms. We have tested the algorithm on 50 images taken under various light sources. The results show that the algorithm is superior or comparable to other methods in both objective and subjective evaluations. The complexity of the algorithm is quite low, which makes it attractive for real-world applications.

Coregulation of transcription factors and microRNAs in human transcriptional regulatory network

BackgroundMicroRNAs (miRNAs) are small RNA molecules that regulate gene expression at the post-transcriptional level. Recent studies have suggested that miRNAs and transcription factors are primary metazoan gene regulators; however, the crosstalk between them still remains unclear.MethodsWe proposed a novel model utilizing functional annotation information to identify significant coregulation between transcriptional and post-transcriptional layers. Based on this model, function-enriched coregulation relationships were discovered and combined into different kinds of functional coregulation networks.ResultsWe found that miRNAs may engage in a wider diversity of biological processes by coordinating with transcription factors, and this kind of cross-layer coregulation may have higher specificity than intra-layer coregulation. In addition, the coregulation networks reveal several types of network motifs, including feed-forward loops and massive upstream crosstalk. Finally, the expression patterns of these coregulation pairs in normal and tumour tissues were analyzed. Different coregulation types show unique expression correlation trends. More importantly, the disruption of coregulation may be associated with cancers.ConclusionOur findings elucidate the combinatorial and cooperative properties of transcription factors and miRNAs regulation, and we proposes that the coordinated regulation may play an important role in many biological processes.