At present, the aging population is growing in Japan. Along with that, the need for the utilization of welfare equipment is increasing. Electric wheelchair, a convenient transportation tool, is popularized rapidly. However, many accidents have occurred by using electric wheelchair, and the dangers for driving are pointed out. Therefore, it needs to improve accident factors, reduce accidents and improve the convenience of electric wheelchair by automation. Environmental recognition is the key technology for developing autonomous electric wheelchair. Environmental recognition includes self-position estimation, recognition of sidewalks, crosswalks, traffic lights, and moving object prediction, etc. In order to solve these problems, this paper describes a system for the detection of sidewalks, crosswalks and traffic lights. We develop the object recognition methods using a modified YOLOv2 that is one of object detection algorithms applying convolutional neural networks (CNN). We detect the object through YOLOv2 and perform processing such as unnecessary bounding box deletion and interpolation. The experimental results demonstrate that the area under the curve (AUC) of the detection rate is 0.620.
This paper describes a technique for extracting moving objects from a video image sequence taken by a fixed or slowly moving camera by background subtraction. The background subtraction method is effective for extracting moving objects from a video provided by a fixed camera. But the latest background image should be employed for the subtraction in order not to be influenced by the light intensity change. A temporal median filter is proposed in this paper which detects the latest background images sequentially. From a video image stream provided by a slowly moving camera, the camera motion is estimated using a registration algorithm and the temporal median filter is applied to the common image area among a set of successive image frames to extract the background. In order that the camera motion estimation may become more exact effective, local correlation maps are calculated which can exclude outliers in estimated motion vectors. The technique was applied to the video images obtained from a hand-held camera and those taken from a camera set at the front seat of a car, and satisfactory results were obtained.
Image registration is an important and a fundamental task in computer vision and image processing field. For example, to make a surgical plan for head operation, the surgeons should gain more detailed information from CT angiography (CTA) and MR angiography (MRA) images. And the abnormalities can be easily detected from the fusion image which is obtained from two different modalities. One of the multiple modal image registration methods is matching the CTA and MRA, by which the image of head vascular could be enhanced. In general, the procedure for fusion is completed manually. It is time-consuming and subjective. Particularly the anatomical knowledge is required as well. Therefore, the development of automatic registration methods is expected in medical fields. In this paper, we propose a method for high accurate registration, which concentrates the structure of head vascular. We use 2-D projection images and restrict volume of interests to improve the processing affection. In experiments, we performed our proposed method for registration on five sets of CTA and MRA images and a better result from our previous method is obtained.
The fundamental step to get a Statistical Shape Model (SSM) is to align all the training samples to the same spatial modality. In this paper, we propose a new 3D alignment method for organic training samples matching, whose modalities are orientable and surface figures could be recognized. It is a feature based alignment method which matches two models depending on the distribution of surface curvature. According to the affine transformation on 2D Gaussian map, the distances between the corresponding parts on surface could be minimized. We applied our proposed method on 5 cases left lung training samples alignment and 4 cases liver training samples alignment. The experiment results were performed on the left lung training samples and the liver training samples. The availability of proposed method was confirmed.
This paper describes a robust color tracker employing an updateable two-dimensional color histogram with an anisotropic asymmetric Gaussian distribution model. A robust color tracking is achieved by updating the color model employing two-dimensional histogram of the h-s plane of the hsv color space. Performance of the proposed technique is robust to unknown illumination change, because the color model is acquired directly from the object and updated iteratively. Moreover, an anisotropic asymmetric Gaussian distribution model is adopted as a model of changeable color range of the object. The color model is added and deleted one by one in the update process. Not very different color is added and quite different color is discarded by estimating the changeable color range of the object. A color tracking system with a pan-tilt camera was developed and, using the system, performance of the proposed technique was examined in a various illumination conditions. The system achieved robust tracking of specified color in the experiment
'/%3e%3cuse xlink:href='%23a' transform='translate(0 -400)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -600)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -800)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -1000)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -1200)'/%3e%3cpath d='M0 0h1400v800H0z' style='fill:%23010066'/%3e%3cpath d='M576 100c-166.146 0-301 134.406-301 300s134.854 300 301 300c60.027 0 115.955-17.564 162.927-47.783-27.353 9.44-56.71 14.602-87.271 14.602-147.327 0-266.897-119.172-266.897-266.01 0-146.837 119.57-266.01 266.897-266.01 32.558 0 63.746 5.815 92.602 16.468C696.217 118.91 638.305 100 576 100z' style='fill:%23fc0'/%3e%3cpath d='m914.286 471.429-99.538-53.25 29.43 108.982-66.575-91.165-20.77 110.96-20.428-111.024-66.857 90.96L699.314 418l-99.701 52.943 74.065-85.192-112.8 4.441 103.694-44.62-103.555-44.94L673.8 305.42 600 220l99.538 53.25-29.43-108.982 66.575 91.165 20.77-110.96 20.428 111.023 66.857-90.959L814.97 273.43l99.702-52.944-74.065 85.193 112.8-4.441-103.694 44.62 103.555 44.94-112.785-4.79z' style='fill:%23fc0' transform='matrix(1.2738 0 0 1.2423 -89.443 -29.478)'/%3e%3c/svg%3e)