We present a new method for recognizing plants automatically and nondestructively by measuring plants three-dimensionally, including height, width, and leaf area, which are important clues for determining a plant condition. We use only two cameras and small plant preparation. A pair of color images for a plant is obtained by a binocular stereo camera, then leaf and stalk areas are extracted from color images, range data is calculated from stereo images, three-dimensional reconstruction for the plant is generated by using the Delaunay triangulation and the plant is measured in the generated reconstruction. Two experimental results are shown for actual plants.
It is difficult for visually impaired individuals to recognize escalators in everyday environments. If the individuals ride on escalators in the wrong direction, they will stumble on the steps. This paper proposes a novel method to assist visually impaired individuals in finding available escalators by the use of smartphone cameras. Escalators are recognized by analyzing optical flows in video frames captured by the cameras, and auditory feedback is provided to the individuals. The proposed method was implemented on an Android smartphone and applied to actual escalator scenes. The experimental results demonstrate that the proposed method is promising for helping visually impaired individuals use escalators.
8 January 2020 in Journal of Signal Processing Systems
In this paper, we propose a detection method of pulmonary nodules in X-ray computed tomography (CT) scans by use of three image filters and appearance-based k-means clustering. First, voxel values are suppressed in radial directions so as to eliminate extra regions in the volumes of interest (VOIs). Globular regions are enhanced by moment-of-inertia tensors where the voxel values in the VOIs are regarded as mass. Excessively enhanced voxels are reduced based on displacement between the VOI centers and the gravity points of the voxel values in the VOIs. Initial nodule candidates are determined by these filtering processings. False positives are reduced by, first, normalizing the directions of intensity distributions in the VOIs by rotating the VOIs based on the eigenvectors of the moment-of-inertia tensors, and then applying an appearance-based two-step k-means clustering technique to the rotated VOIs. The proposed method is applied to actual CT scans and experimental results are shown.
1 June 2020 in International Journal of Computer Assisted Radiology and Surgery