Abstract
We present a detection method that is able to detect a learned target and is valid for both static and moving cameras. As an application, we detect pedestrians, but could be anything if there is a large set of images of it. The data set is fed into a number of deep convolutional networks, and then, two of these models are set in cascade in order to filter the cutouts of a multi-resolution window that scans the frames in a video sequence. We demonstrate that the excellent performance of deep convolutional networks is very difficult to match when dealing with real problems, and yet we obtain competitive results.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Squartini S, Hussain A, Piazza F (2003) Preprocessing based solution for the vanishing gradient problem in recurrent neural networks. In: Proc. of the 2003 int. symp. on circuits and systems, vol 5, pp 713–716
Lowe DG (1999) Object recognition from local scale-invariant features
Bay H, Ess A, Tuytelaars T, Gool LV (2008) Speeded-up robust features (SURF). Comput Vis Image Underst 110(3):346–359
Hough PVC (1959) Machine analysis of bubble chamber pictures. In: Proceedings 2nd International conference on high-energy Accelerators (HEACC 59), pp 554–558
Ballard DH, Ballard DH (1981) Generalizing the Hough transform to detect arbitrary shapes. Pattern Recogn 13:111–122
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Int. conf. on computer vision & pattern recognition, vol 2, pp 886–893
Ojala T, Pietikainen M, Harwood D (1994) Performance evaluation of texture measures with classification based on Kullback discrimination of distributions. In: Proceedings of 12th International conference on pattern recognition, vol 1, pp 582–585
Campmany V, Silva S, Moure JC, Espinosa T, Vazquez D, Lopez A (2016) GPU-based pedestrian detection for autonomous driving. In: GPU technology conference
Bouwmans T (2014) Traditional and recent approaches in background modeling for foreground detection: an overview. Comput Sci Rev 11–12:31–66
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ (eds) Proceedings of the 25th International Conference on Neural Information Processing Systems (NIPS'12), Curran Associates Inc., USA, p 1097–1105
Strigl D, Kofler K, Podlipnig S (2010) Performance and scalability of GPU-based convolutional neural networks. In: 18th Euromicro conference on parallel, distributed and network-based processing, pp 317–324
Liu Q, Huang Z, Hu F (2015) Accelerating convolution-based detection model on GPU. in: Int. conf. on estimation, detection and information fusion (ICEDIF), pp 61–66
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444
Hosang J, Omran M, Benenson R, Schiele B (2015) Taking a deeper look at pedestrians. In: IEEE conference on computer vision and pattern recognition (CVPR), Boston, pp 4073–4082
Tian Y, Luo P, Wang X, Tang X (2015) Deep learning strong parts for pedestrian detection. In: IEEE int. conf. on computer vision (ICCV), pp 1904–1912
Ghodrati A, Diba A, Pedersoli M, Tuytelaars T, Gool LV (2015) Deep proposal: hunting objects by cascading deep convolutional layers. In: Proc. of the IEEE int. conf. on computer vision
Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on multimedia, MM’14. ACM, New York, pp 675–678
Hadwiger M, Theußl T, Hauser H, Gröller E (2001) Hardware-accelerated high-quality filtering on PC hardware. In: Proc. of workshop on vision, modeling and visualization (VMV), pp 105–112
Novosad J (2005) Advanced high-quality filtering, vol. GPU gems 2: programming techniques for high-performance graphics and general-purpose computation. Chapter 27
Breitenstein M, Reichlin F, Leibe B, Koller-Meier E, Gool LV (2009) Robust tracking-by-detection using a detector confidence particle filter. In: IEEE 12th int. conf. on computer vision, pp 1515–1522
Yang J, Vela PA, Shi Z, Teizer J (2009) Probabilistic multiple people tracking through complex situations. In: Performance evaluation of tracking and surveillance workshop at CVPR 2009, Miami, pp 79–86
Leibe B, Schindler K, Cornelis N, Gool LV (2008) Coupled object detection and tracking from static cameras and moving vehicles. IEEE Trans Pattern Anal Mach Intell 30(10):1683–1698
Bernardin K, Stiefelhagen R (2008) Evaluating multiple object tracking performance: the CLEAR MOT metrics. J Image Video Process 2008:246309. doi:10.1155/2008/246309
Acknowledgements
This research has been supported by the Spanish Government research funding TIN-2015-69542-C2-1-R (MINECO/FEDER) and the Banco de Santander funding grant for the Computer Vision and Image Processing (CVIP) Excellence research group.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Cuesta-Infante, A., García, F.J., Pantrigo, J.J. et al. Pedestrian detection with LeNet-like convolutional networks. Neural Comput & Applic 32, 13175–13181 (2020). https://doi.org/10.1007/s00521-017-3197-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-017-3197-z