Revisión de enfoques de técnicas empleadas para la extracción de características y reconocimiento de la marcha humana

Autores/as

DOI:

https://doi.org/10.30973/progmat/2026.18.1/3

Palabras clave:

Reconocimiento de la marcha, Biometría, Extracción de características, Visión por computadora, Aprendizaje profundo

Resumen

El reconocimiento de la marcha es una técnica biométrica que tiene como objetivo identificar a las personas en función de su forma de caminar, dado que son características únicas que definen a cada uno de los individuos. El aprendizaje profundo ha transformado los estudios y análisis de la marcha al emplear inteligencia artificial para la detección de esta. Los métodos de reconocimiento de la marcha basados en el aprendizaje profundo dominan el estado del arte en el campo y han fomentado aplicaciones en el mundo real. Este artículo revisa los avances recientes en el uso de técnicas de visión por computadora de la inteligencia artificial para la extracción de características y el reconocimiento para el análisis de la marcha humana. Se analizan redes neuronales convolucionales (CNN) y métricas para la evaluación de los modelos y la caminata. La revisión concluye que la integración de modelos de reconocimiento es necesario para aplicaciones clínicas, de vigilancia y de biometría.

Biografía del autor/a

Perla Pérez Carrasco, Universidad Autónoma de Querétaro, MÉXICO

Perla Perez Carrasco es Ingeniera biomédica por la Universidad de las Américas Puebla. Actualmente realiza estudios de Maestría en Ciencias en Inteligencia Artificial en la Universidad Autónoma de Querétaro (UAQ) donde efectúa investigaciones especializadas en el procesamiento de imágenes, enfocándose particularmente en el análisis de la marcha humana para desarrollar y entrenar modelos de aprendizaje profundo orientados a futuros trabajos de detección, con el objetivo de mejorar la precisión y eficiencia en aplicaciones futuras.

Osmar Antonio Espinosa Bernal, Universidad Autónoma de Querétaro, MÉXICO

Osmar Antonio Espinosa Bernal es Ingeniero Electromecánico por el Instituto Tecnológico de Zitácuaro, recibió su grado de Maestría en Ciencias en Inteligencia Artificial en la Universidad Autónoma de Querétaro. Actualmente es investigador y está realizando su Doctorado en Ingeniería en la Universidad Autónoma de Querétaro. Las líneas de investigación son Procesamiento Digital de Imágenes, Inteligencia Artificial enfocado a Visión por Computadora y Aprendizaje Maquina. Sus principales áreas de interés son reconstrucción 3D, procesamiento de imágenes y análisis de datos.

Jesús Carlos Pedraza Ortega, Universidad Autónoma de Querétaro, MÉXICO

Jesús Carlos Pedraza Ortega es Ingeniero Electrónica por el Instituto Tecnológico de Celaya, recibió su grado de Maestría en Ingeniería Eléctrica en la Universidad de Guanajuato y obtuvo su Doctorado en Ingeniería Mecánica por la University of Tsukuba en Japón. Es docente e investigador en la Facultad de Ingeniería de la Universidad Autónoma de Querétaro. Las líneas de investigación son; Procesamiento Digital de Imágenes, Inteligencia Artificial (Machine Learning y Deep Learning), así como Software Embebido. Sus principales áreas de interés incluyen la reconstrucción 3D de objetos por medio de proyección de franjas, procesamiento de imágenes médicas, reconocimiento facial y detección de emociones.

Saúl Tovar Arriaga, Universidad Autónoma de Querétaro, MÉXICO

Dr. Saúl Tovar Arriaga. Obtuvo su Doctorado en Ciencias Biomédicas por la Universidad de Erlangen-Nuremberg, Alemania, su Maestría en Ciencias en Mecatrónica por la Universidad de Siegen, Alemania, y es Ingeniero en Electrónica por el Instituto Tecnológico de Querétaro. Es profesor de tiempo completo de la de la Facultad de Ingeniería de la Universidad Autónoma de Querétaro y actualmente es coordinador de la Maestría en Ciencias en Inteligencia Artificial. Sus intereses de investigación incluyen diagnóstico médico automático e Inteligencia artificial. Es miembro del Sistema Nacional de Investigadores Nivel 1 y perfil PRODEP. Ha sido presidente del IEEE Sección Querétaro y del capítulo de IEEE Computational Intelligence. A

Citas

Birdal RG, Sertbaş A, Mühendisliği B. Human Identification Based on Gait Analysis A survey. In 2018 3rd Int. Conf. on Computer Science and Engineering (UBMK). 2018. p. 489–93. https://doi.org/10.1109/UBMK.2018.8566368

Bashir K, Xiang T, Gong S. Gait recognition without subject cooperation. Pattern Recognition Letters. 2010 Oct;31(13, SI) 2052–60. https://doi.org/10.1016/j.patrec.2010.05.027

Chao H, Wang K, He Y, Zhang J, Feng J. GaitSet Cross-View Gait Recognition Through Utilizing Gait As a Deep Set. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2022 Jul 1;44(7) 3467–78. https://doi.org/10.1109/TPAMI.2021.3057879.

Zeng W, Wang C, Yang F. Silhouette-based gait recognition via deterministic learning. Pattern Recognition. 2014 Nov;47(11) 3568–84. https://doi.org/10.1016/j.patcog.2014.04.014

Liu ZY, Sarkar S. Improved gait recognition by gait dynamics normalization. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006;28(6) 863–76. https://doi.org/10.1109/TPAMI.2006.122

Sepas-Moghaddam A, Etemad A. Deep Gait Recognition A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(1) 264–84. https://doi.org/10.1109/TPAMI.2022.3151865

Wan CS, Wang L, Phoha VV. A Survey on Gait Recognition. ACM Computing Surveys. 2019;51(5). https://doi.org/10.1145/3230633

Singh JP, Jain S, Arora S, Singh UP. Vision-Based Gait Recognition A Survey. IEEE Access. 2018;6 70497–527. https://doi.org/10.1109/ACCESS.2018.2879896

Deng MQ, Fan ZY, Lin P, Feng XR. Human Gait Recognition Based on Frontal-View Sequences Using Gait Dynamics and Deep Learning. IEEE Transactions on Multimedia. 2024;26 117–26. https://doi.org/10.1109/TMM.2023.3262131

Lishani AO, Boubchir L, Bouridane A. Haralick features for GEI-based human gait recognition. In 2014 26th Int. Conf. on Microelectronics (ICM). 2014. p. 36–9. https://doi.org/10.1109/ICM.2014.7071800

Hongye X, Zhuoya H. Gait recognition based on gait energy image and linear discriminant analysis. In 2015 IEEE Int. Conf. on Signal Processing, Communications and Computing (ICSPCC). 2015. p. 1–4. https://doi.org/10.1109/ICSPCC.2015.7338934

Múnera N, Alvarez C, Sastoque S, Iregui M. Human features extraction by using anatomical and low level image descriptors from whole body images. In 2016 XXI Symposium on Signal Processing, Images and Artificial Vision (STSIVA). 2016. p. 1–6. https://doi.org/10.1109/STSIVA.2016.7743308

Wang L, Han R, Feng W. Combining the Silhouette and Skeleton Data for Gait Recognition. In ICASSP 2023 - 2023 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP). 2023. p. 1–5. https://doi.org/10.1109/ICASSP49357.2023.10096986

Huang X, Zhu D, Wang H, Wang X, Yang B, He B, et al. Context-Sensitive Temporal Feature Learning for Gait Recognition. In 2021 IEEE/CVF Int. Conf. on Computer Vision (ICCV). 2021. p. 12889–98. https://doi.org/10.1109/ICCV48922.2021.01267

Wu Z, Huang Y, Wang L, Wang X, Tan T. A Comprehensive Study on Cross-View Gait Based Human Identification with Deep CNNs. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2017;39(2) 209–26. https://doi.org/10.1109/TPAMI.2016.2545669

Shiraga K, Makihara Y, Muramatsu D, Echigo T, Yagi Y. GEINet View-invariant gait recognition using a convolutional neural network. In 2016 Int. Conf. on Biometrics (ICB). 2016. p. 1–8. https://doi.org/10.1109/ICB.2016.7550060

Alvarez IRT, Sahonero-Alvarez G. Cross-View Gait Recognition Based on U-Net. In 2020 Int. Joint Conf. on Neural Networks (IJCNN). 2020. p. 1–7. https://doi.org/10.1109/IJCNN48605.2020.9207501

Huang Z, Xue D, Shen X, Tian X, Li H, Huang J, et al. 3D Local Convolutional Neural Networks for Gait Recognition. In 2021 IEEE/CVF Int. Conf. on Computer Vision (ICCV). 2021. p. 14900–9. 10.1109/ICCV48922.2021.01465

Manssor SAF, Sun S, Elhassan MAM. Real-Time Human Recognition at Night via Integrated Face and Gait Recognition Technologies. Sensors. 2021;21(13). https://doi.org/10.3390/s21134323

Dutta A, Lal R, Raychaudhuri DS, Ta CK, Roy-Chowdhury AK. POISE Pose Guided Human Silhouette Extraction under Occlusions. In 2024 IEEE/CVF Winter Conf. on Applications of Computer Vision (WACV). 2024. p. 6141–51. https://doi.org/10.1109/WACV57701.2024.00604

Mason JE, Traoré I, Woungang I. Introduction to Gait Biometrics. In Mason JE, Traoré I, Woungang I, editors. Machine Learning Techniques for Gait Biometric Recognition Using the Ground Reaction Force. Springer; 2016. p. 1–7. https://doi.org/10.1007/978-3-319-29088-1_2.

Johansson G. Visual perception of biological motion and a model for its analysis. Perception & Psychophysics. 1973;14(2) 201–11. https://doi.org/10.3758/BF03212378

Nixon MS, Carter JN. Advances in automatic gait recognition. In Sixth IEEE Int. Conf. on Automatic Face and Gesture Recognition, 2004 Proc. 2004. p. 139–44. https://doi.org/10.1109/AFGR.2004.1301521

Connor P, Ross A. Biometric recognition by gait A survey of modalities and features. Computer Vision and Image Understanding. 2018;167 1–27. https://doi.org/10.1016/j.cviu.2018.01.007

Abu-Faraj Z, Harris G, Smith P, Hassani S. Human Gait and Clinical Movement Analysis. 2015. p. 1–34. https://doi.org/10.1002/047134608X.W6606.pub2

Martín Nogueras A, Calvo Arenillas JL, Orejuela Rodríguez J, Barbero Iglesias FJ, Sánchez Sánchez C. Fases de la marcha humana. Revista Iberoamericana de Fisioterapia y Kinesiología [Internet]. 1999;2(1) 44–9. Disponible en https://www.elsevier.es/es-revista-revista-iberoamericana-fisioterapia-kinesiologia-176-articulo-fases-marcha-humana-13012714

Sudha LR, Bhavani R. Biometric Authorization System Using Gait Biometry. International Journal of Computer Science, Engineering and Applications. 2011 Aug;1(4) 1–13. https://doi.org/10.5121/ijcsea.2011.1401

Xie Y, Hong X, Tang X, Wei D. 3D Convolutional Neural Network for Gait Recognition And Demographic Factor Prediction Based on Plantar Pressure Images. In 2020 IEEE Int. Conf. on Information Technology, Big Data and Artificial Intelligence (ICIBA). 2020. p. 338–42. https://doi.org/10.1109/ICIBA50161.2020.9277305

Saleh AM, Hamoud T. Analysis and best parameters selection for person recognition based on gait model using CNN algorithm and image augmentation. Journal of Big Data [Internet]. 2020;8. Disponible en https://api.semanticscholar.org/CorpusID:230285453

Zhao Y, Zhou S. Wearable Device-Based Gait Recognition Using Angle Embedded Gait Dynamic Images and a Convolutional Neural Network. Sensors (Basel, Switzerland) [Internet]. 2017;17. Disponible en https://api.semanticscholar.org/CorpusID:10122909

Pavitra Vasudevan R, Faerie Mattins SSANGWRPRM. Gait Image Classification Using Deep Learning Models for Medical Diagnosis. Computers, Materials & Continua. 2023;74(3) 6039–6063. https://doi.org/10.32604/cmc.2023.032331

Arora P, Srivastava S. Gait recognition using gait Gaussian image. In 2015 2nd Int. Conf. on Signal Processing and Integrated Networks (SPIN). 2015. p. 791–4. https://doi.org/10.1109/SPIN.2015.7095388

Li X, Makihara Y, Xu C, Yagi Y. Multi-View Large Population Gait Database With Human Meshes and Its Performance Evaluation. IEEE Transactions on Biometrics, Behavior, and Identity Science. 2022;4(2) 234–48. https://doi.org/10.1109/TBIOM.2022.3174559

Lee CP, Tan AWC, Tan SC. Gait probability image An information-theoretic model of gait representation. Journal of Visual Communication and Image Representation. 2014;25(6) 1489–92. https://doi.org/10.1016/j.jvcir.2014.05.006

Yu S, Tan T, Huang K, Jia K, Wu X. A Study on Gait-Based Gender Classification. IEEE Transactions on Image Processing. 2009;18(8) 1905–10. https://doi.org/10.1109/TIP.2009.2020535

Su H, Liao ZW, Chen GY. A gait recognition method using L1-PCA and LDA. In 2009 Int. Conf. on Machine Learning and Cybernetics. 2009. p. 3198–203. https://doi.org/10.1109/ICMLC.2009.5212776

Bartlett MS, Movellan JR, Sejnowski TJ. Face recognition by independent component analysis. IEEE Transactions on Neural Networks. 2002;13(6) 1450–64. https://doi.org/10.1109/TNN.2002.804287

Mao C, Li Y, Sun F. Accelerometer-Based Gait Recognition Using PCA & LDA Algorithms. In 2018 IEEE 23rd Int. Conf. on Digital Signal Processing (DSP). 2018. p. 1–4. https://doi.org/10.1109/ICDSP.2018.8631706

Karg M, Jenke R, Seiberl W, Kühnlenz K, Schwirtz A, Buss M. A comparison of PCA, KPCA and LDA for feature extraction to recognize affect in gait kinematics. In 2009 3rd Int. Conf. on Affective Computing and Intelligent Interaction and Workshops. 2009. p. 1–6. https://doi.org/10.1109/ACII.2009.5349438

Jahagirdar AS, Nagmode MS. Silhouette-Based Human Action Recognition by Embedding HOG and PCA Features. En Bhalla S, Bhateja V, Chandavale AA, Hiwale AS, Satapathy SC, editores. Intelligent Computing and Information and Communication. Singapore Springer Singapore; 2018. p. 363–71

Monisha SJ, Sheeba GM. Gait Based Authentication with Hog Feature Extraction. In 2018 Second Int. Conf. on Inventive Communication and Computational Technologies (ICICCT). 2018. p. 1478–83. https://doi.org/10.1109/ICICCT.2018.8473007

Wu JC, Martin AF, Kacker RN. Measures, Uncertainties, and Significance Test in Operational ROC Analysis. Journal of Research of the National Institute of Standards and Technology. 2011 Jan;116(1) 517. https://doi.org/10.6028/jres.116.003

Nahm FS. Receiver operating characteristic curve overview and practical use for clinicians. Korean Journal of Anesthesiology. 2022 Jan 18;75(1) 25–36. https://doi.org/10.4097/kja.21209

Christodoulakis G, Satchell S. Assessing the Accuracy of Credit R.O.C. Estimates in the Presence of Macroeconomic Shocks.

Wagg DK, Nixon MS. On automated model-based extraction and analysis of gait. In Sixth IEEE Int. Conf. on Automatic Face and Gesture Recognition, 2004 Proceedings. 2004. p. 11–6. https://doi.org/10.1109/AFGR.2004.1301502

Saeh IS, Mustafa MW, Mohammed YS, Almaktar M. Static Security classification and Evaluation classifier design in electric power grid with presence of PV power plants using C-4.5. Renewable and Sustainable Energy Reviews. 2016;56 283–90. https://doi.org/10.1016/j.rser.2015.11.054

Oliveri P, Downey G. Chapter 13 - Discriminant and Class-Modelling Chemometric Techniques for Food PDO Verification. En de la Guardia M, Gonzálvez A, editores. Comprehensive Analytical Chemistry. Elsevier; 2013. p. 317–38. https://doi.org/10.1016/B978-0-444-59562-1.00013-X

Xu C, Makihara Y, Li X, Yagi Y, Lu J. Cross-View Gait Recognition Using Pairwise Spatial Transformer Networks. IEEE Transactions on Circuits and Systems for Video Technology. 2021;31(1) 260–74. https://doi.org/10.1109/TCSVT.2020.2975671

Cheriet M, Dentamaro V, Hamdan M, Impedovo D, Pirlo G. Multi-speed transformer network for neurodegenerative disease assessment and activity recognition. Computer Methods and Programs in Biomedicine. 2023;230 107344. https://doi.org/10.1016/j.cmpb.2023.107344

Guo J, Han K, Wu H, Tang Y, Chen X, Wang Y, et al. CMT Convolutional Neural Networks Meet Vision Transformers. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022. p. 12165–75. https://doi.org/10.1109/CVPR52688.2022.01186

Cui Y, Kang Y. GaitTransformer Multiple-Temporal-Scale Transformer for Cross-View Gait Recognition. In 2022 IEEE Int. Conf. on Multimedia and Expo (ICME). 2022. p. 1–6. https://doi.org/10.1109/ICME52920.2022.9859928

Li J, Wang Z, Wang C, Su W. GaitFormer Leveraging dual-stream spatial–temporal Vision Transformer via a single low-cost RGB camera for clinical gait analysis. Knowledge-Based Systems. 2024;295 111810. https://doi.org/10.1016/j.knosys.2024.111810

Mogan JN, Lee CP, Lim KM, Muthu KS. Gait-ViT Gait Recognition with Vision Transformer. Sensors. 2022;22(19). https://doi.org/10.3390/s22197362

Cosma A, Catruna A, Radoi E. Exploring Self-Supervised Vision Transformers for Gait Recognition in the Wild. Sensors. 2023;23(5). https://doi.org/10.3390/s23052680

Mogan JN, Lee CP, Lim KM, Ali M, Alqahtani A. Gait-CNN-ViT Multi-Model Gait Recognition with Convolutional Neural Networks and Vision Transformer. Sensors. 2023;23(8). https://doi.org/10.3390/s23083809

Güner Şahan P, Şahin S, Kaya Gülağız F. A survey of appearance-based approaches for human gait recognition techniques, challenges, and future directions. The Journal of Supercomputing. 2024;80(13) 18392–429. https://doi.org/10.1007/s11227-024-06172-z

Ascenso G, Yap MH, Allen T, Choppin SS, Payton C. A review of silhouette extraction algorithms for use within visual hull pipelines. Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization. 2020 Nov 1;8(6) 649–70. https://doi.org/10.1080/21681163.2020.1790040

Li X, Makihara Y, Xu C, Yagi Y, Yu S, Ren M. End-to-End Model-Based Gait Recognition. 2021. p. 3–20. 10.1007/978-3-030-69535-4_1

Takemura N, Makihara Y, Muramatsu D, Echigo T, Yagi Y. Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition. IPSJ Transactions on Computer Vision and Applications. 2018;10(1) 4. https://doi.org/10.1186/s41074-018-0039-6

Bo Y. Gait Silhouette Extraction Algorithm Using Gauss Model. Chinese Journal of Sensors and Actuators [Internet]. 2008. Disponible en https://api.semanticscholar.org/CorpusID:124304627

Chen J, Zhang Y. Silhouette extraction from human gait images sequence using cosegmentation. In ProcSPIE. 2012. p. 85580U. https://doi.org/10.1117/12.999992

Ng H, Tan WH, Tong HL, Abdullah J, Komiya R. Extraction of human gait features from enhanced human silhouette images. In 2009 IEEE Int. Conf. on Signal and Image Processing Applications. 2009. p. 425–30. https://doi.org/10.1109/ICSIPA.2009.5478691

Wang H, Xu X. Robust Gait Recognition Based on Spatio-Temporal Fusion Network. Neural Processing Letters. 2023;55(9) 11785–805. https://doi.org/10.1007/s11063-023-11370-6

Yu S, Chen H, Wang Q, Shen L, Huang Y. Invariant feature extraction for gait recognition using only one uniform model. Neurocomputing. 2017;239 81–93. https://doi.org/10.1016/j.neucom.2017.02.006

Zhang Y, Huang Y, Yu S, Wang L. Cross-View Gait Recognition by Discriminative Feature Learning. IEEE Transactions on Image Processing. 2020;29 1001–15. https://doi.org/10.1109/TIP.2019.2926208

Li N, Zhao X. A Strong and Robust Skeleton-Based Gait Recognition Method with Gait Periodicity Priors. IEEE Transactions on Multimedia. 2023;25 3046–58. https://doi.org/10.1109/TMM.2022.3154609

Descargas

Publicado

10-02-2025

Cómo citar

Pérez Carrasco, P., Espinosa Bernal, O. A., Pedraza Ortega, J. C., & Tovar Arriaga, S. (2025). Revisión de enfoques de técnicas empleadas para la extracción de características y reconocimiento de la marcha humana. Programación matemática Y Software, 18(1), 31–50. https://doi.org/10.30973/progmat/2026.18.1/3

Número

Sección

Artículos