Search

This paper is an overview of the UGV (Unmanned Ground Vehicle)'s technical aspects. Among them, it contains information on the vision sensor which is responsible for the visual part using input image data. First, it describes role of vision sensor in Unmanned Ground Vehicle. Next, it explains image processing system applied to the necessary algorithms about UGV's obstacle detection. [ABSTRACT FROM PUBLISHER]

Real-time traffic sign recognition has been object of in-depth studies in the last years, and it has become one of the main pillars of Driver Support Systems (DSS). The purpose of this paper is to show a complete implementation of a real-time traffic sign recognition working on reconfigurable logic. The system has been proved to work at 60 frames per second with a video resolution of 1280×720 pixels, and is able to handle simultaneously up to 8 road signs in the same frame. [ABSTRACT FROM PUBLISHER]

According to the characteristic of traffic signs, several color components are used to extract several kinds of traffic signs, which improved the detection efficiency in pre-processing. Then the regions of interest (ROI) are set not only to save process time but also to increase the accuracy of road recognition. Meanwhile the geometric characters of the road signs are represented by morphological skeleton based on which the decision tree is designed to classify road signs. The presented methods are tested on some complex traffic images which are captured under different weather conditions. [ABSTRACT FROM PUBLISHER]

Image recognition in image understanding is very challenge research topic. However, the study of recognition and enhancement of the specific target for the computer generated image is very less. Compared with the natural image, this cause may be the characteristics (simple in overall) and the scene of applications (the 3D roaming, the game and so on) for the computer-generated image. For recognition and enhancement of the specific target (such as traffic sign) in the computer-generated image, the difficulty is how to accurately recognize and enhance the specific target, and maintaining other information of object do not been changed. In this paper, adopting stepwise refinement method attempts to solve the problem. The proposed method is based on three steps including image preprocessing, image recognition and enhancement. The experimental results show the method can be very good to deal with such issues. The research result shows that the image recognition and image enhancement is still not simple process. Therefore, we imagine that image recognition for complex real scene image also isn't simple issues. But the research idea of stepwise refinement which is proposed in the paper provides a methodological reference for complex image recognition. [ABSTRACT FROM PUBLISHER]

We present an approach for recognizing the broken area of the traffic signs. The method is based on the Recognition System for Traffic Signs (RSTS). This paper describes an approach to using the location histogram matching for the broken traffic signs recognition, after the general process of the image detection and image categorization. The recognition proceeds by using the SIFT matching to adjust the acquired image to a standard position, then the histogram bin will be compared the preprocessed image with reference image, and finally output the location and percent values of the broken area. [ABSTRACT FROM PUBLISHER]

It is important to detect and recognize the traffic sign for mobile robot localization and navigation. In this paper, an algorithm frame of feature detection and matching has been developed which includes shape detection, Harris corner detection, SIFT feature matching and robust estimation method. Firstly, the color threshold segmentation algorithm in RGB color space is adopted to get the candidate region of traffic signs and the region growing method is applied to remove the noise in this image. Secondly, the shape features on the edge image are detected using template matching. Thirdly, Harris corner features are calculated and sorted, then the SIFT feature descriptors are computed on the extraction corner points. Finally, according to the minimum Euclidean distance the matching characteristic vectors are obtained between two images, then random sampling algorithm with robust estimation is used to reduce mismatch. Experiment result shows that this algorithm is efficient. [ABSTRACT FROM PUBLISHER]

Aimed at the complexity of the traffic, this paper presents a triangle traffic sign detection method using Radon transform . the process of detection consists of three parts. Firstly, the background in image is filtered by the color characteristics of triangle traffic sign. Then the target image is transformed from two-dimensional space to Radon projection space. Finally, triangle traffic signs in image are extracted according to characteristics of triangle in Radon projection space. Experimental results show that the proposed method has a good effect on accuracy of detection and also can detect traffic sign area for triangle traffic signs of geometric distortion. [ABSTRACT FROM PUBLISHER]