Generación de Regiones con Potencial de Contener Peatones usando Reconstrucción 3D No Densa a partir de Visión Monocular

Ignacio Zubiaguirre-Bergen, Miguel Torres-Torriti, Marco Flores-Calero

Resumen

Los accidentes de tráfico son un problema de salud pública a escala mundial, por el alto número de víctimas humanas y los elevados costos económicos y sociales que generan. En este contexto, los peatones se encuentran entre los elementos más importantes y vulnerables de la escena vial que necesitan ser protegidos. Es así que en este trabajo se presenta una innovadora propuesta utilizado la información visual monocular para emular la visión estéreo, y a partir de ello: i) generar regiones de interés (ROIs) con alta posibilidad de contener un peatón, y ii) estimar la trayectoria del vehículo. Los experimentos han sido desarrollados sobre una base de datos de imágenes tomadas en varias calles de la ciudad de Santiago (Región-Metropolitana), Chile. Esta información fue obtenida usando una plataforma experimental en condiciones reales de conducción durante el día. La tasa de detección de ROIs es del 86;6 % para distancias menores a 20 metros, 82;9 % para distancias menores a 30 metros y del 76;2 % para distancias menores a 40 metros.


Palabras clave

Peatones; Accidentes; Tráfico; Visión monocular; Visión estéreo; Trayectoria; ROIs

Texto completo:

PDF

Referencias

Agencia Nacional de Tránsito del Ecuador, 2016. Siniestros octubre 2015. URL: http://www.ant.gob.ec/index.php/descargable/file/3368-siniestros-diciembre-2015

Bouguet, Jean-Yves, 2015. Camera calibration toolbox for matlab. URL: http://www.vision.caltech.edu/bouguetj/calib_doc/

CONASET, 2014. Informes de peatones. URL: http://www.conaset.cl/informes-peatones/

Dalal, N., 2006. Finding people in images and videos. Ph.D. Thesis, Institut National Polytechnique de Grenoble.

Ess, A., Leibe, B., Schindler, K., , van Gool, L., June 2008. A mobile vision system for robust multi-person tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR'08). IEEE Press. https://doi.org/10.1109/CVPR.2008.4587581

Fischler, M., Bolles, R., 1981. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM 24 (6), 381–395. https://doi.org/10.1145/358669.358692

Flores-Calero, M., Armingol, A., de-la Escalera, A., july 2010. Driver drowsiness warning system using visual information for both diurnal and nocturnal illumination conditions. EURASIP journal on advances in signal processing 2010 (3). https://doi.org/10.1155/2010/438205

Flores-Calero, M., Armingol, A., de-la Escalera, A., 2011. Sistema Avanzado de Asistencia a la Conducción para la Detección de la Somnolencia. Revista Iberoamericana de Automática e Informática Industrial 8 (3), 216–228. https://doi.org/10.1016/j.riai.2011.06.009

Flores-Calero, M., Robayo, D., Saa, D., May 2015. Histograma del gradiente con múltiples orientaciones (HOG-MO): Detección de personas. Revista Vínculos 12 (2), 138–147.

Forsyth, D. A., Ponce, J., 2003. Computer Vision, A Modern Approach, 1st Edition. Prentice Hall.

Fundación MAFRE, 2012. Datos de seguridad vial. URL: https://www.profesoresyseguridadvial.com/colombia-datos-de-seguridad-vial/

Horgan, J., Hughes, C., McDonald, J., Yogamani, S., 2015. Vision-Based Driver Assistance Systems: Survey, Taxonomy and Advances. In: IEEE 18th International Conference on Intelligent Transportation Systems (ITSC). pp. 2032–2039. https://doi.org/10.1109/ITSC.2015.329

Keller, C., Enzweiler, M., Gavrila, D., July 2011. A new benchmark for stereobased pedestrian detection. In: IEEE Intelligent Vehicles Symposium (IV). pp. 691–696.

Kohler, S., Goldhammer, M., Zindler, K., Doll, K., Dietmeyer, K., September 2015. Stereo-vision-based pedestrian's intention detection in a moving vehicle. In: 2015 IEEE 18th International Conference on Intelligent Transportation Systems. pp. 2317–2322. https://doi.org/10.1109/ITSC.2015.374

La Tercera, 2014. Chile es el país con mayor tasa de peatones fallecidos entre los países de la OCDE. URL: http://www.latercera.com/noticia/nacional/2014/10/680-601399-9-chile-//es-el-pais-con-mayor-tasa-de-peatones-fallecidos-entre-//los-paises-de-la.shtml

Li, X., Flohr, F., Yang, Y., Xiong, H., Braun, M., Pan, S., Li, K., Gavrila, D. M., June 2016. A new benchmark for vison-based cyclist detection. In: IEEE Intelligent Vehicles Symposium. pp. 1109–1114.

Ma, G., Muller, D., Park, S.-B., Muller-Schneiders, S., Kummert, A., march 2009. Pedestrian detection using a single monochrome camera. Intelligent Transport Systems, IET 3 (1), 42 –56. https://doi.org/10.1049/iet-its:20080001

Mammeri, A., Zuo, T., Boukerche, A., April 2016. Extending the Detection Range of Vision-Based Vehicular Instrumentation. IEEE Transactions on Instrumentation and Measurement 65 (4), 856–873. https://doi.org/10.1109/TIM.2016.2514780

Mesmakhosroshahi, M., Chung, K.-H., Lee, Y., Kim, J., November 2014. Depth gradient based region of interest generation for pedestrian detection. In: IEEE International Conference on SoC Design (ISOCC). pp. 156–157. https://doi.org/10.1109/ISOCC.2014.7087674

Min, K., Son, H., Choe, Y., Kim, Y., June 2013. Real-time pedestrian detection based on a hierarchical two-stage support vector machine. In: IEEE 8th Conference on Industrial Electronics and Applications (ICIEA). pp. 114–119.

Oikawaa, S., Matsuia, Y., Doib, T., Sakuraic, T., February 2016. Relation between vehicle travel velocity and pedestrian injury risk in different age groups for the design of a pedestrian detection system. Safety Science 82, 361–367. https://doi.org/10.1016/j.ssci.2015.10.003

Overett, G., Petersson, L., Brewer, N., Andersson, L., Pettersson, N., 2008. A new pedestrian dataset for supervised learning. URL: https://research.csiro.au/data61/automap-datasets-and-code/

Russell, B. C., Torralba, A., Murphy, K. P., Freeman, W. T., May 2008. Label me, a database and web-based tool for image annotation. International Journal of Computer Vision (1-3). URL: http://labelme.csail.mit.edu/

Shi, J., Tomasi, C., jun 1994. Good features to track. In: Computer Vision and Pattern Recognition, 1994. Proceedings CVPR '94., 1994 IEEE Computer Society Conference on. pp. 593 –600. https://doi.org/10.1109/CVPR.1994.323794

Shou, N., Peng, H., Wang, H., Meng, L.-M., Du, K.-L., Octuber 2012. An rois based pedestrian detection system for single images.

Tetik, Y., Bolat, B., June 2011. Pedestrian detection from still images. In: IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA). pp. 540–544.

Villalón-Sepúlveda, G., Torres-Torriti, M., Flores-Calero, M., May 2017. Traffic Sign Detection System for Locating Road Intersections and Roundabouts: The Chilean Case. Sensors MDPI 17 (6), 138–147. https://doi.org/10.3390/s17061207

Wang, L., Shi, J., Song, G., Shen, I.-f., 2007. Object detection combining recognition and segmentation. URL: https://www.cis.upenn.edu/~jshi/ped_html/

Wang, X., Wang, M., Li, W., December 2014. Scene-Specific Pedestrian Detection for Static Video Surveillance. IEEE Transactions on Pattern Analysis and Machine Intelligence 36, 361–374. https://doi.org/10.1109/TPAMI.2013.124

World Health Organization WHO, 2015. Road traffic injuries.

Yuan, Y., Lin, W., Fang, Y., September 2015. Is pedestrian detection robust for surveillance? In: Image Processing (ICIP), 2015 IEEE International Conference on. pp. 2776 – 2780.

Zhang, C., Chung, K.-H., Kim, J., November 2015a. Region-of-interest reduction using edge and depth images for pedestrian detection in urban areas.

Zhang, X., Hu, H.-M., Jiang, F., Li, B., May 2015b. Pedestrian detection based on hierarchical co-occurrence model for occlusion handling. Neurocomputing 168, 861–870. https://doi.org/10.1016/j.neucom.2015.05.038

Zhang, Z., Tao, W., Sun, K., Hu, W., Yao, L., May 2016. Pedestrian detection aided by fusion of binocular information. Pattern Recognition 60, 227–238. https://doi.org/10.1016/j.patcog.2016.05.006

Zhao, X., Ye, M., Zhu, Y., Zhong, C., Zhou, J., December 2009. Real time roi generation for pedestrian detection.

Abstract Views

177
Metrics Loading ...

Metrics powered by PLOS ALM




Esta revista se publica bajo una Licencia Creative Commons Atribución-NoComercial-SinDerivar 4.0 Internacional

Universitat Politècnica de València

e-ISSN: 1697-7920     ISSN: 1697-7912