Browsing by Author "Takahashi, Hiroyuki"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Development of Bicycle Surrogate for Bicyclist Pre-Collision System Evaluation
    (SAE, 2016-04) Yi, Qiang; Chien, Stanley; Brink, Jason; Niu, Wensen; Li, Lingxi; Chen, Yaobin; Chen, Chi-Chen; Sherony, Rini; Takahashi, Hiroyuki; Department of Electrical and Computer Engineering, School of Engineering and Technology
    As part of active safety systems for reducing bicyclist fatalities and injuries, Bicyclist Pre-Collision System (BPCS), also known as Bicyclist Autonomous Emergency Braking System, is being studied currently by several vehicles manufactures. This paper describes the development of a surrogate bicyclist which includes a surrogate bicycle and a surrogate bicycle rider to support the development and evaluation of BPCS. The surrogate bicycle is designed to represent the visual and radar characteristics of real bicyclists in the United States. The size of bicycle surrogate mimics the 26 inch adult bicycle, which is the most popular adult bicycle sold in the US. The radar cross section (RCS) of the surrogate bicycle is designed based on RCS measurement of the real adult sized bicycles. The surrogate bicycle is constructed with detachable components with shatter resistant material to prevent structural damage during a collision, and matches the look and RCS of a real 26 inch mountain bicycle from all 360 degree angles. The surrogate bicycle rider is a 168 cm tall adult with CNC machined realistic body shape. The skin of the surrogate bicycle rider has the RCS of a real human skin. Combined skin with realistic body shape, the surrogate bicyclist has the RCS matching to that of a same sized real human from 360 degree angles in the view of 77GHz automotive radar. The surrogate bicyclist has articulated leg motion which is important for micro Doppler sensing and can be supported on a sled or a mobile carrier. It can be moved at a speed of 20 mph and can be collided by vehicles from any direction and be reassembled in less than 5 minutes.
  • Thumbnail Image
    Item
    An Extreme Learning Machine-based Pedestrian Detection Method
    (Office of the Vice Chancellor for Research, 2013-04-05) Yang, Kai; Du, Eliza Y.; Delp, Edward J.; Jiang, Pingge; Jiang, Feng; Chen, Yaobin; Sherony, Rini; Takahashi, Hiroyuki
    Pedestrian detection is a challenging task due to the high variance of pedestrians and fast changing background, especially for a single in-car camera system. Traditional HOG+SVM methods have two challenges: (1) false positives and (2) processing speed. In this paper, a new pedestrian detection method using multimodal HOG for pedestrian feature extraction and kernel based Extreme Learning Machine (ELM) for classification is presented. The experimental results using our naturalistic driving dataset show that the proposed method outperforms the traditional HOG+SVM method in both recognition accuracy and processing speed.
  • Thumbnail Image
    Item
    Pedestrian/Bicyclist Limb Motion Analysis from 110-Car TASI Video Data for Autonomous Emergency Braking Testing Surrogate Development
    (SAE, 2016-04) Sherony, Rini; Tian, Renran; Chien, Stanley; Fu, Li; Chen, Yaobin; Takahashi, Hiroyuki; Department of Engineering Technology, School of Engineering and Technology
    Many vehicles are currently equipped with active safety systems that can detect vulnerable road users like pedestrians and bicyclists, to mitigate associated conflicts with vehicles. With the advancements in technologies and algorithms, detailed motions of these targets, especially the limb motions, are being considered for improving the efficiency and reliability of object detection. Thus, it becomes important to understand these limb motions to support the design and evaluation of many vehicular safety systems. However in current literature, there is no agreement being reached on whether or not and how often these limbs move, especially at the most critical moments for potential crashes. In this study, a total of 832 pedestrian walking or cyclist biking cases were randomly selected from one large-scale naturalistic driving database containing 480,000 video segments with a total size of 94TB, and then the 832 video clips were analyzed focusing on their limb motions. We modeled the pedestrian/bicyclist limb motions in four layers: (1) the percentages of pedestrians and bicyclists who have limb motions when crossing the road; (2) the averaged action frequency and the corresponding distributions on when there are limb motions; (3) comparisons of the limb motion behavior between crossing and non-crossing cases; and (4) the effects of seasons on the limb motions when the pedestrians/bicyclists are crossing the road. The results of this study can provide empirical foundations supporting surrogate development, benefit analysis, and standardized testing of vehicular pedestrian/bicyclist detection and crash mitigation systems.
  • Thumbnail Image
    Item
    Utility of Pathology Imagebase for Standardization of Prostate Cancer Grading
    (Wiley, 2018-07) Egevad, Lars; Delahunt, Brett; Berney, Dan M.; Bostwick, David G.; Cheville, John; Comperat, Eva; Evans, Andrew J.; Fine, Samson W.; Grignon, David J.; Humphrey, Peter A.; Hörnblad, Jonas; Iczkowski, Kenneth A.; Kench, James G.; Kristiansen, Glen; Leite, Katia R.M.; Magi-Galluzzi, Cristina; McKenney, Jesse; Oxley, Jon; Pan, Chin-Chen; Samaratunga, Hemamali; Srigley, John R.; Takahashi, Hiroyuki; True, Lawrence D.; Tsuzuki, Toyonori; van der Kwast, Theo; Varma, Murali; Zhou, Ming; Clements, Mark; Pathology and Laboratory Medicine, School of Medicine
    Aims: Despite efforts to standardise grading of prostate cancer, even among experts there is still a considerable variation in grading practices. In this study we describe the use of Pathology Imagebase, a novel reference image library, for setting an international standard in prostate cancer grading. Methods and results: The International Society of Urological Pathology (ISUP) recently launched a reference image database supervised by experts. A panel of 24 international experts in prostate pathology reviewed independently microphotographs of 90 cases of prostate needle biopsies with cancer. A linear weighted kappa of 0.67 (95% confidence interval = 0.62-0.72) and consensus was reached in 50 cases. The interobserver weighted kappa varied from 0.48 to 0.89. The highest level of agreement was seen for Gleason score (GS) 3 + 3 = 6 (ISUP grade 1), while higher grades and particularly GS 4 + 3 = 7 (ISUP grade 3) showed considerable disagreement. Once a two-thirds majority was reached, images were moved automatically into a public database available for all ISUP members at www.isupweb.org. Non-members are able to access a limited number of cases. Conclusions: It is anticipated that the database will assist pathologists to calibrate their grading and, hence, decrease interobserver variability. It will also help to identify instances where definitions of grades need to be clarified.