Skip to main content
main-content

Tipp

Weitere Kapitel dieses Buchs durch Wischen aufrufen

2018 | OriginalPaper | Buchkapitel

Shallow Convolutional Neural Network and Viterbi Algorithm for Dim Line Tracking

verfasst von: Przemyslaw Mazurek

Erschienen in: Computer Vision and Graphics

Verlag: Springer International Publishing

share
TEILEN

Abstract

The estimation of line is important in numerous practical applications. The most difficult case if the line is dim, even hidden in background noise. The application of Track–Before–Detect algorithms allows the tracking of such line. Additional preprocessing using shallow neural network trained for the detection of line features is proposed in this paper. Four variant of data fusion from neural network are compared. Direct output of neural network that works as a classifier gives best results for Mean Absolute Error (MAE) metric. Similar results are obtained if output of neural network is used as a mask for input image. Monte Carlo test are used for unbiased results. Test shows improvement of MAE about two times. The application of binary output from neural network is wrong solution and the error is largest. The influence of the number of convolutional layer neurons is not significant in this test.
Literatur
1.
Zurück zum Zitat Bar-Shalom, Y.: Multitarget-Multisensor Tracking: Applications and Advances, vol. II. Artech House, Norwood (1992) Bar-Shalom, Y.: Multitarget-Multisensor Tracking: Applications and Advances, vol. II. Artech House, Norwood (1992)
2.
Zurück zum Zitat Bertsekas, D.: Dynamic Programming and Optimal Control, vol. I. Athena Scientific, Belmont (1995) MATH Bertsekas, D.: Dynamic Programming and Optimal Control, vol. I. Athena Scientific, Belmont (1995) MATH
3.
Zurück zum Zitat Blackman, S.: Multiple-Target Tracking with Radar Applications. Artech House, Norwood (1986) Blackman, S.: Multiple-Target Tracking with Radar Applications. Artech House, Norwood (1986)
4.
Zurück zum Zitat Blackman, S., Popoli, R.: Design and Analysis of Modern Tracking Systems. Artech House, Norwood (1999) MATH Blackman, S., Popoli, R.: Design and Analysis of Modern Tracking Systems. Artech House, Norwood (1999) MATH
6.
Zurück zum Zitat Chen, Z., Ellis, T.: Automatic lane detection from vehicle motion trajectories. In: Workshop on Vehicle Retrieval in Surveillance (VRS) in conjunction with 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 466–471 (2013) Chen, Z., Ellis, T.: Automatic lane detection from vehicle motion trajectories. In: Workshop on Vehicle Retrieval in Surveillance (VRS) in conjunction with 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 466–471 (2013)
7.
Zurück zum Zitat Deans, S.R.: The Radon Transform and Some of Its Applications. Wiley, New York (1983) MATH Deans, S.R.: The Radon Transform and Some of Its Applications. Wiley, New York (1983) MATH
8.
Zurück zum Zitat Dupois, J.F., Parizeau, M.: Evolving a vision-based line-following robot controller. In: Proceedings of the 3rd Canadian Conference on Computer and Robot Vision (CRV 2006), p. 75 (2006) Dupois, J.F., Parizeau, M.: Evolving a vision-based line-following robot controller. In: Proceedings of the 3rd Canadian Conference on Computer and Robot Vision (CRV 2006), p. 75 (2006)
9.
Zurück zum Zitat Golightly, I., Jones, D.: Visual control of an unmanned aerial vehicle for power line inspection. In: 12th International Conference on Advanced Robotics, ICAR 2005, pp. 288–295, July 2005 Golightly, I., Jones, D.: Visual control of an unmanned aerial vehicle for power line inspection. In: 12th International Conference on Advanced Robotics, ICAR 2005, pp. 288–295, July 2005
10.
Zurück zum Zitat LeCun, Y., Kavukcuoglu, K., Farabet, C.: Convolutional networks and applications in vision. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems, pp. 253–256, May 2010 LeCun, Y., Kavukcuoglu, K., Farabet, C.: Convolutional networks and applications in vision. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems, pp. 253–256, May 2010
11.
Zurück zum Zitat Matczak, G., Mazurek, P.: History dependent Viterbi algorithm for navigation purposes of line following robot. Image Process. Commun. 20(4), 5–11 (2016) CrossRef Matczak, G., Mazurek, P.: History dependent Viterbi algorithm for navigation purposes of line following robot. Image Process. Commun. 20(4), 5–11 (2016) CrossRef
13.
Zurück zum Zitat Mazurek, P.: Line estimation using the Viterbi algorithm and track-before-detect approach for line following mobile robots. In: 2014 19th International Conference on Methods and Models in Automation and Robotics (MMAR), pp. 788–793, September 2014 Mazurek, P.: Line estimation using the Viterbi algorithm and track-before-detect approach for line following mobile robots. In: 2014 19th International Conference on Methods and Models in Automation and Robotics (MMAR), pp. 788–793, September 2014
15.
Zurück zum Zitat Scott, T.A., Nilanjan, R.: Biomedical Image Analysis: Tracking. Morgan & Claypool, San Rafael (2005) Scott, T.A., Nilanjan, R.: Biomedical Image Analysis: Tracking. Morgan & Claypool, San Rafael (2005)
16.
Zurück zum Zitat Stone, L., Barlow, C., Corwin, T.: Bayesian Multiple Target Tracking. Artech House, Norwood (1999) MATH Stone, L., Barlow, C., Corwin, T.: Bayesian Multiple Target Tracking. Artech House, Norwood (1999) MATH
17.
Zurück zum Zitat Viterbi, A.: Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Trans. Inf. Theory 13(2), 260–269 (1967) CrossRef Viterbi, A.: Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Trans. Inf. Theory 13(2), 260–269 (1967) CrossRef
Metadaten
Titel
Shallow Convolutional Neural Network and Viterbi Algorithm for Dim Line Tracking
verfasst von
Przemyslaw Mazurek
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-030-00692-1_33

Premium Partner