Measurements by many multi-sensor systems can be considered as point-clouds. One such system is the tracker for the PANDA experiment. Charged particles passing through the tracker produce patterns representing their p...
详细信息
Measurements by many multi-sensor systems can be considered as point-clouds. One such system is the tracker for the PANDA experiment. Charged particles passing through the tracker produce patterns representing their paths. We present a new, graph-based, attribute-space morphological connected filter for reconstructing particle paths through such a detector. We introduce the concept of attribute-spaces and attribute-space connected filters on graphs, rather than binary images and show a new processing scheme to reduce the size of the memory required to store the attribute-space representations of binary images and graphs. The result is an O(Nlog(N)) algorithm with a total recognition error of approximately 0.10, a significant improvement compared to our previous state-of-the-art O(N-2) algorithm with a total error of 0.17. (C) 2020 Elsevier Ltd. All rights reserved.
The majority of existing traffic sign detection systems utilize color or shape information, but the methods remain limited in regard to detecting and segmenting traffic signs from a complex background. In this paper, ...
详细信息
The majority of existing traffic sign detection systems utilize color or shape information, but the methods remain limited in regard to detecting and segmenting traffic signs from a complex background. In this paper, we propose a novel graph-based traffic sign detection approach that consists of a saliency measure stage, a graph-based ranking stage, and a multithreshold segmentation stage. Because the graph-based ranking algorithm with specified color and saliency combines the information of color, saliency, spatial, and contextual relationship of nodes, it is more discriminative and robust than the other systems in terms of handling various illumination conditions, shape rotations, and scale changes from traffic sign images. Furthermore, the proposed multithreshold segmentation algorithm focuses on all the nodes with a nonzero ranking score, which can effectively solve problems such as complex background, occlusion, various illumination conditions, and so on. The results for three public traffic sign sets show that our proposed approach leads to better performance than the current state-of-the-art methods. Moreover, the results are satisfactory even for images containing traffic signs that have been rotated or undergone occlusion, as well as for images that were photographed under different weather and illumination conditions.
暂无评论