Precise Foot Feature Point Localization and Automatic Parameters Measurement

doi:10.16183/j.cnki.jsjtu.2023.397

Abstract

Abstract:

In order to quickly obtain foot parameters and quantify the degree of foot deformation, an algorithm that can accurately locate foot feature points and automatically calculate foot parameters is proposed. First, a total of 93 patients participate and their foot models are obtained using the UPOD laser scanner. Then, the random sampling consensus algorithm and principal component analysis are used to align the foot coordinate system. The algorithm utilizes foot features to identify and locate feature points, enabling the parameter calculation of length, angle, and girth. The accuracy, repeatability, and consistency of the measurements are evaluated using mean absolute error (MAE), mean absolute percentage error (MAPE), interclass correlation coefficient (ICC), and Bland-Altman plots. The MAE of foot length and width is less than 2 mm, and for ball girth, instep girth, and heel girth, it is less than 4 mm. The MAPE is less than 2%, and the ICCs for the three replicates exceed 0.99. More than 95% of the scattered points in the Bland-Altman plots are within the consistency boundary. The results show that the proposed algorithm can automatically align the coordinate system, accurately locate feature points, and accurately measure foot parameters in the standing posture. The measurement accuracy meets clinical needs with high accuracy and reliability. The findings provide valuable data support for foot classification, intelligent assistive device adaptation, and personalized assistive device design, showing important clinical application potential.

Key words: foot measurement, coordinate alignment, feature point localization, 3D point clouds

CLC Number:

JI Mian, LIN Yanping, WANG Dongmei, CHEN Li, MA Xin. Precise Foot Feature Point Localization and Automatic Parameters Measurement[J]. Journal of Shanghai Jiao Tong University, 2025, 59(5): 703-710.

Figures/Tables 10

Fig.1

Fig.2

Fig.3

Tab.1

Fig.4

Fig.5

Fig.6

Fig.7

Tab.2

Fig.8

References 22

[1]	孙云, 罗向东. 基于生物力学的足部保健产品研究[J]. 包装工程, 2019, 40(10): 239-242.
	SUN Yun, LUO Xiangdong. Foot health product based on biomechanical characteristics[J]. Packaging Engineering, 2019, 40(10): 239-242.
[2]	袁佑芳. 重庆市社区老年人足部问题调查及护理干预研究[D]. 重庆: 重庆医科大学, 2020.
	YUAN Youfang. Investigation on the foot problems of the elderly in the community of Chongqing and study on nursing intervention[D]. Chongqing: Chongqing Medical University, 2020.
[3]	胡智宏, 叶倩, 孔叶平. 矫形鞋垫的作用机制及临床研究进展[J]. 中国康复, 2016, 31(3): 229-231.
	HU Zhihong, YE Qian, KONG Yeping. Mechanism and clinical research progress of orthopedic insole[J]. Chinese Journal of Rehabilitation, 2016, 31(3): 229-231.
[4]	WANG H W, LIU F C, FAN R. A research on foot size measurement algorithm based on image[J]. Journal of Physics: Conference Series, 2021, 1903(1): 012004.
[5]	ROGATI G, LEARDINI A, ORTOLANI M, et al. Semi-automatic measurements of foot morphological parameters from 3D plantar foot scans[J]. Journal of Foot and Ankle Research, 2021, 14(1): 18. doi: 10.1186/s13047-021-00461-z pmid: 33731179
[6]	WITANA C P, XIONG S P, ZHAO J H, et al. Foot measurements from three-dimensional scans: A comparison and evaluation of different methods[J]. International Journal of Industrial Ergonomics, 2006, 36(9): 789-807.
[7]	刘国忠, 王伯雄, 史辉, 等. 激光线扫描足部三维测量方法及其应用[J]. 清华大学学报(自然科学版), 2008, 48(5): 820-823.
	LIU Guozhong, WANG Boxiong, SHI Hui, et al. 3-D foot measurements using laser-linescanning[J]. Journal of Tsinghua University (Science and Technology), 2008, 48(5): 820-823.
[8]	KAASHKI N N, ROYEN R, DAI X X, et al. A deep-learning-based approach to automatically measuring foots from a 3D scan[C]// 2022 IEEE Asia-Pacific Conference on Computer Science and Data Engineering. Gold Coast, Australia: IEEE, 2022: 1-5.
[9]	SONG E, YOON S W, SON H, et al. Foot measurement using 3D scanning model[J]. International Journal of Fuzzy Logic and Intelligent Systems, 2018, 18(3): 167-174.
[10]	WU G, LI D, HU P P, et al. Automatic foot scanning and measurement based on multiple RGB-depth cameras[J]. Textile Research Journal, 2018, 88(2): 167-181.
[11]	WANG M, WANG X A, FAN Z C, et al. A 3D foot shape feature parameter measurement algorithm based on Kinect2[J]. EURASIP Journal on Image and Video Processing, 2018, 2018(1): 119.
[12]	TELFER S, WOODBURN J. The use of 3D surface scanning for the measurement and assessment of the human foot[J]. Journal of Foot and Ankle Research, 2010, 3: 19. doi: 10.1186/1757-1146-3-19 pmid: 20815914
[13]	LOCHNER S J, HUISSOON J P, BEDI S S. Parametric design of custom foot orthotic model[J]. Computer-Aided Design and Applications, 2012, 9(1): 1-11.
[14]	XIONG S P, ZHAO J H, JIANG Z H, et al. A computer-aided design system for foot-feature-based shoe last customization[J]. The International Journal of Advanced Manufacturing Technology, 2010, 46(1): 11-19.
[15]	SIMON J, DOEDERLEIN L, MCINTOSH A S, et al. The Heidelberg foot measurement method: Development, description and assessment[J]. Gait & Posture, 2006, 23(4): 411-424.
[16]	胡安铎, 苏显渝, 向立群, 等. 脚型三维测量与特征参数自动提取[J]. 四川大学学报(自然科学版), 2009, 46(6): 1691-1696.
	HU Anduo, SU Xianyu, XIANG Liqun, et al. 3D measurement and feature parameters automatic extraction of foot[J]. Journal of Sichuan University (Natural Science Edition), 2009, 46(6): 1691-1696.
[17]	朱晓兰, 吴壮志. 三维足型参数自动测量系统设计与实现[J]. 体育科学, 2010, 30(9): 44-48.
	ZHU Xiaolan, WU Zhuangzhi. Design and implementation of 3D foot size measurement system[J]. China Sport Science, 2010, 30(9): 44-48.
[18]	国家市场监督管理总局, 国家标准化管理委员会. 鞋楦尺寸检测方法: GB/T 3294—2018[S]. 北京: 中国标准出版社, 2018.
	State Administration for Market Regulation, Standardization Administration of the People’s Republic of China. Test method of inspection for last sizes: GB/T 3294—2018[S]. Beijing: Standards Press of China, 2018.
[19]	毋戈. 基于多个深度相机的足部三维重建及形态分析[D]. 上海: 东华大学, 2017.
	WU Ge. Three-dimensional reconstruction and shape analysis of human feet based on multiple depth cameras[D]. Shanghai: Donghua University, 2017.
[20]	丘理. 鞋楦设计与制作[M]. 第2版. 北京: 中国纺织出版社, 2015: 120-125.
	QIU Li. Last designing and making[M]. 2nd ed. Beijing: China Textile & Apparel Press, 2015: 120-125.
[21]	KOO T K, LI M Y. A guideline of selecting and reporting intraclass correlation coefficients for reliability research[J]. Journal of Chiropractic Medicine, 2016, 15(2): 155-163. doi: 10.1016/j.jcm.2016.02.012 pmid: 27330520
[22]	CARRASCO A C, SILVA M F, GUENKA L C, et al. Non-radiographic validity and reliability measures for assessing foot types: A systematic review[J]. Foot and Ankle Surgery: Official Journal of the European Society of Foot and Ankle Surgeons, 2021, 27(8): 839-850.

类别	参数	定义
长度	足长,L₁/mm	最长趾尖点P1与足后跟点P15在y方向的距离
	足弓长,L₂/mm	P15与第1跖趾关节外凸点P4在y方向的距离
	足跟到内踝长,L₃/mm	P15与内踝尖点P13在y方向的距离
	足跟到外踝长,L₄/mm	P15与外踝尖点P12在y方向的距离
	足宽,L₅/mm	P4与第5跖趾关节外凸点P5在x方向的距离
	中足宽,L₆/mm	50%足长处横坐标x最大的点P7与最小的点P8在x方向的距离
	足踝宽,L₇/mm	P12与P13在x方向的距离
	足跟宽,L₈/mm	过辅助点P14垂直y轴的直线与整足交点间的距离
	第1跖趾关节顶高,L₉/mm	拇指最高点P3到xOy平面的距离
	第1跖骨上缘点高,L₁₀/mm	第1跖骨最高点P6到xOy平面的距离
	足弓高,L₁₁/mm	内侧足弓最高点P10到xOy平面的距离
	中足高,L₁₂/mm	50%足长处足部最高点P9到xOy平面的距离
	内踝高,L₁₃/mm	P13到xOy平面的距离
	外踝高,L₁₄/mm	P12到xOy平面的距离
围度	跖围,C₁/mm	过P4、P5、P6的平面与足相交所得曲线长
	跗围,C₂/mm	过P10且垂直yOz的平面与足相交所得的最短曲线长
	兜跟围,C₃/mm	过P15和舟上弯点P11且垂直yOz的平面与足相交所得的曲线长
角度	拇外翻角,α₁/(°)	P4和拇指外凸点P2在xOy平面投影点连线与y轴夹角
	跖趾斜宽角,α₂/(°)	P4和P5在xOy平面投影点的连线与x轴夹角
	自然前翘角,α₃/(°)	P1和P3的连线与xOy平面的夹角

参数	测量值/mm				UPOD 测量值/mm	MAE/mm	MAPE/%	ICC(3, 1)
参数	第1次	第2次	第3次	平均值	UPOD 测量值/mm	MAE/mm	MAPE/%	ICC(3, 1)
足长	244.85	244.86	244.84	244.85	244.25	0.64±0.56	0.26±0.23	0.999
足宽	97.08	97.07	97.09	97.08	97.96	1.04±0.60	1.05±0.60	0.998
跖围	236.26	236.24	236.27	236.26	236.58	2.43±1.80	1.03±0.76	0.997
跗围	232.19	232.30	232.41	232.30	235.75	3.56±2.77	1.50±1.14	0.992
兜跟围	309.43	309.44	309.33	333.40	309.40	3.23±1.80	1.02±0.55	0.998