Publication Date: 25th Dec. 2015, ISSN 2186-9154, Total Pages: 63
Abstract: This paper reports a new method of detecting ruts using lasers and in-vehicle stereo camera. We process laser lines reflected in image data to obtain feature values of rut. And we determine whether it is rut or not from shapes of the laser lines. The proposed algorithm ensures processing time and cost reduction in comparison with conventional methods.
Keywords: Rut detection ; Computer vision ; Inspection vehicle
Abstract: To obtain a person’s location information with high accuracy using mobile devices, it is
necessary for a mobile device to switch its localization method depending on whether the user is
indoors or outdoors. We propose a method to determine indoor and outdoor location using only the
sensors on a mobile device. To obtain a decision with high accuracy for many devices, the method
must consider individual differences between devices. We confirmed that using a majority decision
method reduces the influence of individual device difference. Moreover, for highly accurate decisions in various environments, it is necessary to consider the differences in environments, such as large cities surrounded by high-rise buildings versus suburban areas. We measured classification features in different environments; the accuracy of the classifier constructed using these features was 99.6%.
Keywords: GPS, Wi-Fi, Localization, Mobile Device
Abstract: Autonomous driving is an emerging technology in which a car performs recognition,
decision making, and control in place of a human driver. Localization is one of the core issues for
autonomous driving. In particular, driving on urban roads requires highly dependable localization
techniques, because the traffic environment is more complicated than that of an expressway. In this paper, we propose a localization algorithm for an autonomous vehicle, which estimates the vehicle’s position by means of template matching. The results show that this algorithm is better suited to make estimations in various environments than the Global Navigation Satellite System and Inertial Measurement Unit (GNSS/IMU) system. Specifically, the method used in this study enables autonomous operation the vehicle up to 13km on public roads, while the GNSS/IMU system cannot achieve this.
Keywords: autonomous vehicle; localization; LIDAR; infrared reflectivity; template matching
Abstract: Cognitive dysfunction patients are sometimes unable to drive safely by symptoms such as executive dysfunction. We experimented with subjects equipped with wearable sensors using real cars on public roads for analyzing the driving behavior of cognitive dysfunction patients. From
experimental data obtained from cognitive dysfunction patients and healthy adults (control subjects), we found there exists a difference in deceleration behaviors of cognitive dysfunction patients and healthy adults at an intersection. The result indicates that our approach may be used to evaluate cognitive dysfunction patients’ driving.
Keywords: Cognitive dysfunction; Wearable Sensor; Deceleration Behavior; Driving Skill
Abstract: In the technology of Advanced Safety Vehicle (ASV), it is an important element to detect
pedestrians by vision. However, pedestrians have pose variations such as a rotation. That’s why we cannot always get similar feature values. In order to solve this problem, we use the rotation-invariant histogram of oriented gradient (RI-HOG), but this method needs very high costs because it’s not optimized for pedestrian recognition. Therefore, we improved calculation method of RI-HOG for pedestrian recognition and compared this proposed method with the conventional method. As a result, recognition rate was increased by about 20%.
Keywords: Pedestrian recognition; rotation-invariant descriptor; optimal basis functions
Abstract: In this study, we propose and evaluate the unified laundry folding method for robot arm
which can fold many kinds of laundries in the same way. The basic concept of this method is to make the laundry to square shape by using the developed some unified rules. The edges of the laundry are detected and the image of the laundry is enclosed in a rectangle by image processing, then the folding line to fold the protruding part inside of the laundry is defined for making the laundry square. We confirmed that the proposed unified laundry folding method can deal with T-shirt, pants and towels in the same way. And, we evaluated the proposed unified method by comparing with the human’s laundry folding method. As a result, we confirmed that our proposed unified method and the human’s folding method are similar and the proposed method will be useful for robot arm laundry folding task.
Keywords: laundry folding task, image processing
Abstract: A vision-based user interface of a mobile robotic arm for people with severe disabilities is described in this paper. The robotic arm’s main body can be contained in a laptop computer’s briefcase without removing any parts. The user interface consists of a single web camera to obtain user’s the eye movements, computer running a detection program of the center of the iris and pupil from the captured images, and display unit to indicate feedback information to the user. Control boxes to detect user’s eye movements were also made and superimposed on the processed images. It is clear from the experimental results that an able-bodied subject can operate the proposed user interface without any difficulty, and that using it promises to support to select one of foods on a table.
Keywords: Robotic arm; self-feeding system; people with severe disabilities; eye movement; image processing
Abstract: To achieve both weight reduction and crash safety improvement in automobile bodies, we have developed Three-Dimensional Hot Bending and Direct Quench (3DQ) technology, the first in the world. In this paper, we describe the overview and the effect of 3DQ with robot.
Keywords: 3DQ, automobile body, hot bending, quench
Abstract: In this paper, we propose the computation model of illusion of Hellman grid image. We
simulate the phenomenon that dark spots appear on intersections of the white lines by using wavelet transforms. Additionally, we reproduced the phenomenon that the dark spot disappears in attention by the computation model based on spatial frequency. In order to confirm validity of the proposed method, we show the relationship between the illusion and the spatial frequency by the qualitative experiments with subjects.
Keywords: Illusion, Simulation, Hellman grid, Spatial Frequency, Wavelet Transform
Abstract: There is great pressure on population growth and water resources shortage in China. Aiming to monitor the early stage of crop growth, this paper presents a photosynthesis-based monitoring model for grain production. Not only the normalized difference vegetation index and elements such as the growing degree day are considered, the factors of sunshine and the cost of water resource are also considered in the model.
Combining the meteorological data with the vegetation index that is adopted from remote sensing, the model contains the elements of solar radiation, effective air temperature, vegetation biomass, stomatal opening, water stress, and the influence of temperature on grain plants, such as low-temperature sterility and high-temperature injury.
Keywords: Crop production index; Photosynthesis; Remote sensing; Monitoring; Water resource
Abstract: The desertification process to China’s capital, Beijing area, is analyzed by using the state of vegetation, soil moisture and meteorological data collected by the satellites. The growth of vegetation, soil moisture and long-term changes of temperature and precipitation in the selected two study regions that are near Beijing is analyzed and compared (from 2002 to 2011). Thus the trend of desertification can be predicted, and the effective long-term protection and control strategy can be set up.
Keywords: Desertification prevention; Vegetation index; Soil moisture; Temperature and precipitation; remote sensing
© 2017 Applied Science and Computer Science Publications.
Enter the destination URL
Or link to existing content