covid
Buscar en
Revista Iberoamericana de Automática e Informática Industrial RIAI
Toda la web
Inicio Revista Iberoamericana de Automática e Informática Industrial RIAI Detección de obstáculos y espacios transitables en entornos urbanos para siste...
Información de la revista
Vol. 9. Núm. 4.
Páginas 462-473 (octubre - diciembre 2012)
Compartir
Compartir
Descargar PDF
Más opciones de artículo
Visitas
4816
Vol. 9. Núm. 4.
Páginas 462-473 (octubre - diciembre 2012)
Open Access
Detección de obstáculos y espacios transitables en entornos urbanos para sistemas de ayuda a la conducción basados en algoritmos de visión estéreo implementados en GPU
Obstacle detection and free spaces in urban environments for advanced driver assistance systems based on stereo vision algorithms implemented in GPU
Visitas
4816
B. Musleh
Autor para correspondencia
bmusleh@ing.uc3m.es

Autor para correspondencia.
, A. de la Escalera, J.M. Armingol
Laboratorio de Sistemas Inteligentes del Departamento de Sistemas y Automática, Universidad Carlos III de Madrid, C/Butarque, 15, 28911 Leganés, Madrid, España
Este artículo ha recibido

Under a Creative Commons license
Información del artículo
Resumen
Texto completo
Bibliografía
Descargar PDF
Estadísticas
Resumen

Tanto los sistemas avanzados de ayuda a la conducción (ADAS) aplicados a la mejora de la seguridad vial, como los sistemas de navegación autónoma de vehículos, demandan sensores y algoritmos cada vez más complejos, capaces de obtener e interpretar información del entorno vial. En concreto, las mayores dificultades surgen a la hora de analizar la información proveniente de los entornos urbanos, debido a la diversidad de elementos con distintas características que existen en áreas urbanas. Estos sistemas requieren, cada vez más, que la interpretación de la información se realice en tiempo real para mejorar la toma de decisiones. Por otra parte, la visión estéreo es ampliamente utilizada en sistemas de modelado, dada la gran cantidad de información que proporciona, pero al mismo tiempo, los algoritmos basados en esta técnica requieren de un elevado tiempo de cómputo que dificulta su implementación en aplicaciones de tiempo real. En este trabajo se presenta un algoritmo basado en visión estéreo para la detección tanto de obstáculos como de espacios transitables en entornos urbanos y que ha sido implementado principalmente en GPU (Unidad de Procesamiento Gráfico) para reducir el tiempo de cómputo y conseguir un funcionamiento en tiempo real.

Palabras clave:
Visión por Computador
Vehículos Autónomos
Algoritmos de Detección
Sistemas de Tiempo Real
Abstract

Both advanced driver assistance systems (ADAS) applied to the improvement of road safety, and autonomous navigation vehicle systems require more and more complex sensors and algorithms capable of obtaining and interpreting the information of the road environment. The greatest difficulties arise in analysing the information of the urban environments, because of the large number of elements which have different characteristics in urban areas. These systems require to interpret the information in real time to improve the decision-making. On the other hand, the stereo vision is usable in modeling systems because of the great amount of information that it provides, but at the same time, the algorithms based on this technique have a high computation time which makes difficult its implementation in real time applications. This paper presents an algorithm based on stereo vision for detecting obstacles and free spaces in urban environments and it has been implemented principally in GPU (Graphic Processing Unit) to reduce the computation time and achieving that it works in real time.

Keywords:
Computer Vision
Autonomous Vehicles
Detection Algorithms
Real time systems
Referencias
[Armingol et al., 2007]
J. Armingol, A. de la Escalera, C. Hilario, J. Collado, J. Carrasco, M. Flores, J. Pastor, F. Rodriguez.
Ivvi: Intelligent vehicle based on visual information.
Robotics and Autonomous Systems, 55 (2007), pp. 904-916
[Bertozzi et al., 2003]
M. Bertozzi, A. Broggi, P. Grisleri, T. Graf, M. Meinecke.
Pedestrian detection in infrared images.
In: Intelligent Vehicles Symposium, 2003. Pro- ceedings. IEEE. IEEE, (2003), pp. 662-667
[Broggi et al., 2008]
Broggi, A., Cappalunga, A., Caraffi, C., Cattani, S., Ghidoni, S., Grisleri, P., Porta, P., Posterli, M., Zani, P., Beck, J., 2008. The passive sensing suite of the terramax autonomous vehicle. In: Intelligent Vehicles Symposium, 2008 IEEE. IEEE, pp. 769-774.
[Broggi et al., 2005]
Broggi, A., Caraffi, C., Fedriga, R., Grisleri, P., 2005. Obstacle detection with stereo vision for off-road vehicle navigation. In: Computer Vision and Pat- tern Recognition-Workshops, 2005. CVPR Workshops. IEEE Computer So- ciety Conference on. IEEE, pp. 65-65.
[Brown et al., 2003]
M. Brown, D. Burschka, G. Hager.
Advances in computational stereo.
Pattern Analysis and Machine Intelligence, IEEE Transactions on, 25 (2003), pp. 993-1008
[Cabani et al., 2006]
Cabani, I., Toulminet, G., Bensrhair, A., 2006. A color stereo vision system for extraction of 3d edges of obstacle. In: Intelligent Transportation Systems Conference, 2006. ITSC’06. IEEE. IEEE, pp. 307-312.
[Dalal and Triggs, 2005]
N. Dalal, B. Triggs.
Histograms of oriented gradients for human detection In: Computer Vision and Pattern Recognition, 2005. CVPR 2005.
IEEE Computer Society Conference on., 1 (2005), pp. 886-893
[Enzweiler and Gavrila, 2009]
M. Enzweiler, D. Gavrila.
Monocular pedestrian detection: Survey and experiments.
Pattern Analysis and Machine Intelligence, IEEE Transactions on, 31 (2009), pp. 2179-2195
[Faugeras et al., 1993]
Faugeras, O., Viéville, T., Theron, E., Vuillemin, J., Hotz, B., Zhang, Z., Moll, L., Bertin, P., Mathieu, H., Fua, P., et al., 1993. Real-time correlation-based stereo: algorithm, implementations and applications.
[Flores et al., 2011]
M. Flores, J. Armingol, A. de la Escalera.
Sistema avanzado de asisten- cia a la conducción para la detección de la somnolencia.
Revista Iberoame- ricana de Automática e Informática Industrial RIAI, 8 (2011), pp. 216-228
[Fusiello et al., 2000]
A. Fusiello, E. Trucco, A. Verri.
A compact algorithm for rectification of stereo pairs.
Machine Vision and Applications, 12 (2000), pp. 16-22
[Gong et al., 2007]
M. Gong, R. Yang, L. Wang, M. Gong.
A performance study on diffe- rent cost aggregation approaches used in real-time stereo matching.
Interna- tional Journal of Computer Vision, 75 (2007), pp. 283-296
[Guo et al., 2009]
Guo, C., Mita, S., McAllester, D., 2009. Drivable road region detection using homography estimation and efficient belief propagation with coordinate des- cent optimization. In: Intelligent Vehicles Symposium, 2009 IEEE. IEEE, pp. 317-323.
[Hautiére et al., 2006]
Hautiére, N., Labayrade, R., Perrollaz, M., Aubert, D., 2006. Road scene analy- sis by stereovision: a robust and quasi-dense approach. In: Control, Automa- tion, Robotics and Vision, 2006. ICARCV’06. 9th International Conference on. IEEE, pp. 1-6.
[Hirschmu¿ ller et al., 2002]
H. Hirschmu¿ ller, P. Innocent, J. Garibaldi.
Real-time correlation-based stereo vision with reduced border errors.
International Journal of Computer Vision, 47 (2002), pp. 229-246
[Hirschmuller and Scharstein, 2007]
Hirschmuller, H., Scharstein, D., 2007. Evaluation of cost functions for stereo matching. In: Computer Vision and Pattern Recognition, 2007. CVPR’07. IEEE Conference on. IEEE, pp. 1-8.
[Hu et al., 2005]
Hu, Z., Lamosa, F., Uchimura, K., 2005. A complete uv-disparity study for stereovision based 3d driving environment analysis. In: 3-D Digital Imaging and Modeling, 2005. 3DIM 2005. Fifth International Conference on. IEEE, pp. 204-211.
[Hu and Uchimura, 2005]
Hu, Z., Uchimura, K., 2005. Uv-disparity: an efficient algorithm for stereovi- sion based scene analysis. In: Intelligent Vehicles Symposium, 2005. Pro- ceedings. IEEE. IEEE, pp. 48-54.
[Kim et al., 2009]
Kim, J., Hwangbo, M., Kanade, T., 2009. Parallel algorithms to a parallel hard- ware: Designing vision algorithms for a gpu. In: Computer Vision Works- hops (ICCV Workshops), 2009 IEEE 12th International Conference on. IEEE, pp. 862-869.
[Labayrade and Aubert, 2003a]
Labayrade, R., Aubert, D., 2003a. In-vehicle obstacles detection and characteri- zation by stereovision. Proc. IEEE In-Vehicle Cognitive Comput. Vis. Syst, 1-3.
[Labayrade and Aubert, 2003b]
Labayrade, R., Aubert, D., 2003b. A single framework for vehicle roll, pitch, yaw estimation and obstacles detection by stereovision. In: Intelligent Vehi- cles Symposium, 2003. Proceedings. IEEE. IEEE, pp. 31-36.
[Labayrade et al., 2002]
Labayrade, R., Aubert, D., Tarel, J., 2002. Real time obstacle detection in ste- reovision on non flat road geometry through v-disparity representation. In: Intelligent Vehicle Symposium, 2002. IEEE. Vol. 2. IEEE, pp. 646-651.
[Lee et al., 2008]
Lee, C., Lim, Y., Kwon, S., Lee, J., 2008. Obstacle localization with a binarized v-disparity map using local maximum frequency values in stereo vision. In: Signals, Circuits and Systems, 2008. SCS 2008. 2nd International Conferen- ce on. IEEE, pp. 1-4.
[Lemonde and Devy, 2004]
V. Lemonde, M. Devy.
Obstacle detection with stereovision.
Mechatro- nics & Robotics (MECHROBa¿04, 3 (2004), pp. 919-924
[Ling et al., 2007]
Ling, B., Zeifman, M., Gibson, D., 2007. Multiple pedestrian detection using ir led stereo camera. In: Proceedings of SPIE. Vol. 6764. p. 67640A.
[Musleh et al., 2010]
B. Musleh, F. García, J. Otamendi, J. Armingol, A. De la Escalera.
Identifying and tracking pedestrians based on sensor fusion and motion sta- bility predictions.
Sensors, 10 (2010), pp. 8028-8053
[Nvidia, 2008]
Nvidia, C., 2008. Programming guide.
[NVIDIA, 2009]
NVIDIA, C., 2009. C programming best practices guide. Cuda Toolkit 2.
[Olmeda et al., 2011]
D. Olmeda, A. de la Escalera, J. Armingol.
Far infrared pedestrian detection and tracking for night driving.
Robotica, 29 (2011), pp. 495-505
[Pérez et al., 2010]
J. Pérez, V. Milanés, J. Alonso, E. Onieva, T. De Pedro.
Adelantamien- to con vehiculos autónomos en carreteras de doble sentido.
Revista Iberoa- mericana de Automática e Informática Industrial RIAI, 7 (2010), pp. 25-33
[Petrovskaya and Thrun, 2009]
A. Petrovskaya, S. Thrun.
Model based vehicle detection and tracking for autonomous urban driving.
Autonomous Robots, 26 (2009), pp. 123-139
[Premebida et al., 2009]
Premebida, C., Ludwig, O., Nunes, U., 2009. Exploiting lidar-based features on pedestrian detection in urban scenarios. In: Intelligent Transportation Sys- tems, 2009. ITSC’09. 12th International IEEE Conference on. IEEE, pp. 1-6.
[Scharstein and Szeliski, 2002]
D. Scharstein, R. Szeliski.
A taxonomy and evaluation of dense two- frame stereo correspondence algorithms.
International journal of computer vision, 47 (2002), pp. 7-42
[Soquet et al., 2007]
Soquet, N., Aubert, D., Perrollaz, M., et al., 2007. Free space estimation for autonomous navigation.
[Stam, 2008]
Stam, J., 2008. Stereo imaging with cuda. OpenVIDIA, january.
[Sun et al., 2006]
Z. Sun, G. Bebis, R. Miller.
Monocular precrash vehicle detection: fea- tures and classifiers.
Image Processing, IEEE Transactions on, 15 (2006), pp. 2019-2034
[Taylor et al., 2004]
Taylor, T., Geva, S., Boles, W., 2004. Monocular vision as a range sensor. Inter- national Conference on Computational Intelligence for Modelling, Control and Automation.
[Thrun, 2003]
S. Thrun.
Learning occupancy grid maps with forward sensor models.
Autonomous robots, 15 (2003), pp. 111-127
[Urmson et al., 2008]
C. Urmson, J. Anhalt, D. Bagnell, C. Baker, R. Bittner, M. Clark, J. Dolan, D. Duggins, T. Galatali, C. Geyer, et al.
Autonomous driving in urban environments: Boss and the urban challenge.
Journal of Field Robotics., 25 (2008), pp. 425-466
[Wang et al., 2006]
Wang, L., Gong, M., Gong, M., Yang, R., 2006. How far can we go with local optimization in real-time stereo matching. In: 3D Data Processing, Visua- lization, and Transmission, Third International Symposium on. IEEE, pp.129-136.
[Xu et al., 2009]
Xu, Y., Zhao, M., Wang, X., Zhang, Y., Peng, Y., Yuan, Y., Liu, H., 2009. A method of stereo obstacle detection based on image symmetrical move. In: Intelligent Vehicles Symposium, 2009 IEEE. IEEE, pp. 36-41.
[Zhao et al., 2009]
Zhao, J., Whitty, M., Katupitiya, J., 2009. Detection of non flat ground surfaces using v disparity images. In: Intelligent Robots and Systems, 2009. IROS. [2009] IEEE/RSJ International Conference on. IEEE, pp. 4584-4589.
Copyright © 2012. Elsevier España, S.L.. Todos los derechos reservados
Descargar PDF
Opciones de artículo