People detection on 2D laser range nder datausing deep learning and machine learning

• Autores: José Antonio Abrego González, Eugenio Aguirre Molina , Miguel García Silvente
• Localización: Proceedings of the XXIV Workshop of Physical Agents: September 5-6, 2024 / coord. por Miguel Cazorla Quevedo , Francisco Gómez Donoso , Félix Escalona Moncholi , 2024, ISBN 978-84-09-63822-2, págs. 235-249
• Idioma: español
• Enlaces
  • Texto completo
• Resumen

  • This work presents a machine learning based study on people detection using 2D Laser Range Finders (LRFs) combined with deep learning methodologies, aimed at enhancing mobile robot capabilities in various environmental conditions. The study introduces a novel integration of a monocular camera with an LRF on a mobile robot to improve the accuracy and eciency of detecting and tracking people. By employing deep learning models such as CenterNet, the system leverages both image and 2D range data to facilitate automatic labeling of datasets, crucial for training robust classication algorithms. In order to achieve the best classier, two experimental studies are introduced in this work.

    The former is carried out in a simulated environment and the latter in real-world, oce-like environments. In simulations, various machine learning models are trained and evaluated, showing signicant results in distinguishing human legs from other objects. The transition to realworld testing underscores the challenges and adaptations necessary to achieve high accuracy and reliability in dynamic settings. The XGBoost model emerged as the most eective classier in our study, achieving the highest scores in accuracy, precision, recall, and F1-score, outperforming other methods across these key metrics. This work aims to advance the eld of 2D LRF based people detection and also proposes a solution for real-time applications, balancing precision and computational eciency.

    Experimental results from both simulated and real-world environments demonstrate the system's eectiveness.

• Referencias bibliográficas
  • Aguirre, E., García-Silvente, M.: Using a deep learning model on images to obtain a 2d laser people detector for a mobile robot. International...
  • Aguirre Molina, E., García Silvente, M., Pascual, D.: A multisensor based approach using supervised learning and particle ltering for people...
  • Ahmed, I., Ahmad, M., Rodrigues, J., Jeon, G.: Edge computing-based person detection system for top view surveillance: Using CenterNet with...
  • Benedek, C.: 3D people surveillance on range data sequences of a rotating lidar. Pattern Recognition Letters 50, 149 158 (2014). https://doi.org/10.1016/j.patrec. 2014.04.010
  • Cai, Z., Vasconcelos, N.: Cascade R-CNN: Delving into high quality object detection. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern...
  • Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part a nity elds. In: 2017 IEEE Conference on Computer...
  • Chen, Y., Song, B., Zeng, Y., Du, X., Guizani, M.: A deep learning-based approach for fault diagnosis of current-carrying ring in catenary...
  • Dai, J., Li, Y., He, K., Sun, J.: R-FCN: Object detection via region-based fully convolutional networks. In: Lee, D., Sugiyama, M., Luxburg,...
  • Girshick, R.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV). pp. 1440 1448 (2015). https://doi.org/10.1109/ICCV.2015.169
  • Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014...
  • He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV). pp. 2980 2988...
  • Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., Fischer, I., Wojna, Z., Song, Y., Guadarrama, S., Murphy, K.: Speed/accuracy...
  • Intelligence, S.S.: Sick sensor intelligence, LMS200 (2002), http://www.mysick.com
  • Kim, J.J., On, B.W., Lee, I.: High-quality train data generation for deep learningbased web page classi cation models. IEEE Access 9, 85240...
  • Lafuente-Arroyo, S., Martin-Martin, P., Iglesias-Iglesias, C., Maldonado-Bascon, S., Acevedo-Rodriguez, F.J.: RGB camera-based fallen person...
  • Leigh, A., Pineau, J., Olmedo, N., Zhang, H.: Person tracking and following with 2d laser scanners. In: 2015 IEEE International Conference...
  • Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft COCO: Common objects in context....
  • Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: SSD: Single shot multibox detector. In: European conference...
  • Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: Cortes, C., Lawrence,...
  • Rubagotti, M., Tusseyeva, I., Baltabayeva, S., Summers, D., Sandygulova, A.: Perceived safety in physical human-robot interaction-a survey....
  • S. Mohamed, I., Capitanelli, A., Mastrogiovanni, F., Rovetta, S., Zaccaria, R.: Detection, localisation and tracking of pallets using machine...
  • Sharif, M.H.: Laser-based algorithms meeting privacy in surveillance: A survey. IEEE Access 9, 92394 92419 (2021). https://doi.org/10.1109/ACCESS.2021. 3092687
  • Sun, Y., Li, Z., Wang, L., Zuo, J., Xu, L., Li, M.: Automatic detection of vehicle targets based on centernet model. In: 2021 IEEE International...
  • Taubin, G.: Estimation of planar curves, surfaces and nonplanar space curves de- ned by implicit equations, with applications to edge and...
  • Vijayakumar, A., Vairavasundaram, S.: Yolo-based object detection models: A review and its applications. Multimedia Tools and Applications...
  • Yuan, L., Mao, J., Zheng, H.: Ear detection based on CenterNet. In: 2020 IEEE 2nd International Conference on Civil Aviation Safety and Information...
  • Zhou, X., Wang, D., Krähenbühl, P.: Objects as points. In: arXiv preprint arXiv:1904.07850 (2019)
  • Zhou, X., Wang, D., Krähenbühl, P.: Objects as points (2019). https://doi.org/10. 48550/arXiv.1904.07850