Gait Recognition by Fusing Direct Cross-view Matching Scores for Criminal Investigation

スポンサーリンク

概要

• 論文の詳細を見る

• We focus on gait recognition for criminal investigation. In criminal investigation, person authentication is performed by comparing target data at the crime scene and multiple gait data with slightly different views from that of the target data. For this task, we propose fusion of direct cross-view matching. Cross-view matching generally produces worse result than those of same-view matching when view-variant features are used. However, the correlation between cross-view matching with different view pairs is low and it provides improved accuracy. Experimental results performed utilizing large-scale dataset under settings resembling actual criminal investigation cases, show that the proposed approach works well.

• Information and Media Technologies 編集運営会議の論文

著者

• Yagi Yasushi

  Institute Of Scientific And Industrial Research Osaka University

• Muramatsu Daigo

  Institute of Scientific and Industrial Research, Osaka University

• Makihara Yasushi

  Institute of Scientific and Industrial Research, Osaka University

関連論文

• Video Capsule Endoscopy Analysis For Diagnostic Assistance
• Robust and Real-time Estimation of Camera Rotation with Translation-invariant Features
• Real-Time Estimation of Fast Egomotion with Feature Classification Using Compound Omnidirectional Vision Sensor
• Controlling the Display of Capsule Endoscopy Video for Diagnostic Assistance
• Super-resolution for an omnidirectional vision sensor
• Shape from Grid Pattern Based on Coplanarity Constraints for One-shot Scanning
• Gait Recognition by Fusing Direct Cross-view Matching Scores for Criminal Investigation
• Pedestrian Detection by Using a Spatio-Temporal Histogram of Oriented Gradients
• Gait Recognition by Fusing Direct Cross-view Matching Scores for Criminal Investigation
• Ringing Detector for Deblurring based on Frequency Analysis of PSF

スポンサーリンク