Shen Cherng

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.

Critical Motion Detection of Nearby Moving Vehicles in a Vision-Based Driver-Assistance System

Driving always involves risk. Various means have been proposed to reduce the risk. Critical motion detection of nearby moving vehicles is one of the important means of preventing accidents. In this paper, a computational model, which is referred to as the dynamic visual model (DVM), is proposed to detect critical motions of nearby vehicles while driving on a highway. The DVM is motivated by the human visual system and consists of three analyzers: 1) sensory analyzers, 2) perceptual analyzers, and 3) conceptual analyzers. In addition, a memory, which is called the episodic memory, is incorporated, through which a number of features of the system, including hierarchical processing, configurability, adaptive response, and selective attention, are realized. A series of experimental results with both single and multiple critical motions are demonstrated and show the feasibility of the proposed system.

Physics-based extraction of intrinsic images from a single image

A technique for extracting intrinsic images, including the reflectance and illumination images, from a single color image is presented. The technique first convolves the input image with a prescribed set of derivative filters. The pixels of filtered images are then classified into reflectance-related or illumination-related based on a set of chromatic characteristics of pixels calculated from the input image. Chromatic characteristics of pixels are defined by a photometric reflectance model based on the Kubelka-Munk color theory. From the classification results of the filtered images, the intrinsic images of the input image can be computed. Real images have been utilized in our experiments. The results have indicated that the proposed technique can effectively extract the intrinsic images from a single image.

Vision-based traffic measurement system

We present a vision-based traffic measurement system. The system automatically counts the vehicles passing through a designated segment of roadway and measures their speeds. Based on the obtained number of vehicles and their speeds, a variety of traffic parameters are readily calculated. A number of experiments with the video sequences taken under different weather, illumination and traffic conditions have been conducted. The results have revealed that the proposed system could perform well under different conditions.

Intrinsic Image Extraction from a Single Image

An image is often modeled as a product of two principal components: illumination and reflectance components. The former is related to the amount of light incident on the scene and the latter is associated with the scene characteristics. The images formed from the two components are referred to as the illumination and the reflectance images; both are called the intrinsic images of the original image. The illumination components of the images of a fixed scene vary from image to image, while the reflectance components of the images in principle remain constant. Both reflectance and illumination images have their own applications. Intrinsic image extraction has long been an important task for computer vision applications. However, this task is not at all simple because it is an illconditioned problem. The proposed approach convolves an input image with a prescribed set of derivative filters. The pixels of the derivative images are next classified as being reflectance or illumination according to three measures: chromatic, intensity contrast and edge sharpness, which are calculated in advance for each pixel from the input image. Finally, a de-convolution process is applied to the classified derivative images to obtain the intrinsic images. The results reveal the feasibility of the proposed technique in both rapidly and effectively decomposing intrinsic images from one single image.

Foreground Object Detection Using Two Successive Images

Detecting foreground object often need to face the problems of illumination change and image noise. In this paper, we propose an object detection method using two successive image frames. Illumination change would be very small in such short time, and then we can handle the first problem more easily. Image noise will confuse the detection of an object boundary. To handle this problem, we apply level set method to enclose the foreground object regions. The experiments show that our method can be applied to extract foreground objects in various environments and different cameras.

Dichromatic reflection separation from a single image

A feature-based technique for separating specular and diffuse components of a single image is presented. In the proposed approach, Shafers dichromatic reflection model is utilized, which assumed a light reflected from a surface point is linearly composed of diffuse and specular reflections. The major idea behind the proposed method is to classify the boundary pixels of the input image to be specular-related or diffuse-related. A fuzzy integral process is proposed to classify boundary pixels based on their local evidences, including specular and diffuse estimation information. Based on the classification result of boundary pixels, an integration method is evoked to reconstruct the specular and diffuse components of the input image, respectively. Unlike previous researches, the proposed method has no color segmentation and iterative operations. The experimental results have demonstrated that the proposed method can perform dichromatic reflectance separation effectively with small misadjustments and rapid convergence.

Omni-Directional Camera Networks and Data Fusion for Vehicle Tracking in an Indoor Parking Lot

A fixed single camera is not sufficient for monitoring a wide area. More cameras can be used, but a problem with integrating all of them will arise. In this paper, a monitoring system to detect and track moving objects in an indoor environment using multiple omni-directional cameras is proposed. Objects captured from different cameras can be integrated automatically, and we can add more cameras to enlarge the monitoring range without changing the system architecture. Such a system is currently being applied to a model of a parking lot for detecting the paths of vehicles.

A Functional Microstrip Circuit Module for Annular Slot Antenna

A functional microstrip circuit module for annular slot antenna is proposed. This module consists of an annular microstrip line component, two PIN diodes and a DC bias circuit. Reconflgurable circular polarizations can be simply controlled by this functional module. Axial ratio is adjustable by changing the clip angle of the notch made by the annular microstrip line component. Simulated and experimental results have shown good impedance bandwidth for return loss and antenna gains in circularly polarized states.

The invariance properties of chromatic characteristics

An approach to analyzing the degrees of invariance of chromatic characteristics is proposed in this paper. In many vision applications, it is desirable that the chromatic characteristics of objects in images taken under different lighting conditions could remain constant. However, the invariance properties of chromatic characteristics are subject to the lighting conditions. In order to be able to apply to dynamic scenes, we consider three fundamental lighting sources: diffuse, ambient, and directed lightings. Any illumination condition can be approximated as a combination of the three lighting sources. The proposed degree of chromatic invariance is defined based on the chromatic characteristic behaviors under different illumination conditions. A lot of image samples under different illumination conditions are utilized, and from experimental results, we conclude that chromatic characteristics {H, C, Cλ} are most stable and suitable for the vision applications.