Enhancing the robustness of forensic gait analysis against near-distance viewing direction differences

Enhancing the robustness of forensic gait analysis against near-distance viewing direction differences
复制标题

增强法医步态分析针对近距离观看方向差异的鲁棒性

DOI:
10.1007/s11042-022-12751-0
复制
发表时间:
2022
影响因子:
3.6
通讯作者:
Kurosawa Kenji
Kurosawa Kenji
中科院分区:
计算机科学4区
文献类型:
--
作者:
Imoto Daisuke;Hirabayashi Manato;Honma Masakatsu;Kurosawa Kenji

文献摘要

参考文献

被引文献

相似文献

步态分析是一种很有前途的生物特征识别技术,可以直观、定量地分析个体的行走方式。在日本,基于轮廓的定量步态分析已被实施为法医工具,然而,由于应用范围狭窄,仍然存在一些挑战。其中一个尚未解决的问题是存在“轻微”但关键的观看方向差异,这导致即使使用基于深度学习的特征提取,也会在分析中对人做出错误的判断。为了缓解关键的观看方向差异的问题,我们开发了一种新的步态分析技术,包括三个组成部分:三维校准,步态能量图像空间配准,和回归的距离矢量。GUI开发和模拟鉴定测试的结果表明,所提出的方法可以帮助实现在法医学领域的实际改进。
Gait analysis is a promising biometric technology to visually and quantitatively analyze an individual’s walking style. In Japan, silhouette-based quantitative gait analyses have been implemented as a forensic tool; however, several challenges remain owing the narrow range of application. One of the yet-unsolved issues pertains to the existence of a ‘slight’ but critical viewing direction difference, which leads to the incorrect judgment in the analyses of a person even when using deep learning-based feature extraction. To alleviate the critical viewing direction difference problem, we developed a novel gait analysis technique involving three components: 3D calibration, gait energy image space registration, and regression of the distance vector. Results of the GUI development and mock appraisal tests indicated that the proposed method can help achieve practical improvements in the forensic science domain.
使用摄影测量和生物力学步态分析来识别个体
DOI: --
发表时间: 2010
期刊: 2010 18th European Signal Processing Conference
影响因子: --
作者:
P. Larsen;E. Simonsen;N. Lynnerup
通讯作者: N. Lynnerup
DOI: 10.1016/j.scijus.2013.04.005
发表时间: 2013
期刊: Science & justice : journal of the Forensic Science Society
影响因子: --
作者:
I. Birch;Louis Raymond;Anastasia Christou;Milan Angelo Fernando;Nigel P Harrison;Flo Paul
通讯作者: Flo Paul
DOI: 10.1038/s41592-018-0261-2
发表时间: 2019-01-01
期刊: NATURE METHODS
影响因子: 48
作者:
Falk, Thorsten;Mai, Dominic;Ronneberger, Olaf
通讯作者: Ronneberger, Olaf
灰姑娘的故事?法医“科学”的社会生产
DOI: --
发表时间: 2016
影响因子: 1.8
作者:
G. Edmond;E. Cunliffe
通讯作者: E. Cunliffe
康复中的步态分析方法
DOI: 10.35248/2167-7921.21.10.e008
发表时间: 2021
期刊: Journal of Arthritis
影响因子: --
作者:
X. Chang
通讯作者: X. Chang