A Novel Pedestrian Detector on Low-Resolution Images: Gradient LBP Using Patterns of Oriented Edges

スポンサーリンク

概要

• 論文の詳細を見る

• This paper introduces a simple algorithm for pedestrian detection on low resolution images. The main objective is to create a successful means for real-time pedestrian detection. While the framework of the system consists of edge orientations combined with the local binary patterns (LBP) feature extractor, a novel way of selecting the threshold is introduced. Using the mean-variance of the background examples this threshold improves significantly the detection rate as well as the processing time. Furthermore, it makes the system robust to uniformly cluttered backgrounds, noise and light variations. The test data is the INRIA pedestrian dataset and for the classification, a support vector machine with a radial basis function (RBF) kernel is used. The system performs at state-of-the-art detection rates while being intuitive as well as very fast which leaves sufficient processing time for further operations such as tracking and danger estimation.

• The Institute of Electronics, Information and Communication Engineersの論文

著者

• Tan Joo

  Kyushu Inst. Technol. Kitakyushu Jpn

• Kim Hyoungseop

  Kyushu Institute Of Technology

• Ishikawa Seiji

  Kyushu Institute Of Technology

• SHINOMIYA Takashi

  Japan University of Economics

• BOUDISSA Ahmed

  Kyushu Institute of Technology

関連論文

• Segmentation of artery area for Non-enhanced Fresh Blood Imaging from the MR Imaging(International Forum on Medical Imaging in Asia 2009 (IFMIA 2009))
• A Graphic System for Creating a 3-D Road Environment
• A METHOD OF ALLOCATING VIDEO ROAD DATA FOR PRODUCING A THREE-DIMENSIONAL MAP(International Workshop on Advanced Image Technology 2007)
• A METHOD OF ALLOCATING VIDEO ROAD DATA FOR PRODUCING A THREE-DIMENSIONAL MAP
• Human Motion Recognition Based on Directional Motion History Images(International Workshop on Advanced Image Technology 2007)
• Human Motion Recognition Based on Directional Motion History Images
• High-Speed Human Motion Recognition Based on a Motion History Image and an Eigenspace(Pattern Recognition)
• A CAD System for Osteoporosis from Computed Radiography Images(International Forum on Medical Imaging in Asia 2009 (IFMIA 2009))
• Automatic detection of spleen and gallbladder region employing rib information
• A Novel Pedestrian Detector on Low-Resolution Images: Gradient LBP Using Patterns of Oriented Edges

スポンサーリンク