Abstract
An optimized Back-Propagation network (BP network) based on Genetic Algorithm (GA) was introduced to construct bidirectional reflectance distribution function (BRDF) model. To verify the performance of GA-BP network, two different kinds of space target materials were used for experiment. Based on the experimental data, we used GA to simulate the undetermined parameters of a five-parameter BRDF model, and used GA-BP network and BP network to construct a new BRDF model respectively. The fitting results manifest that the GA-BP network is suitable for construct a new BRDF model and outperforms the five-parameter BRDF model in speed and accuracy under the same condition.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
1 Introduction
BRDF is used to describe how irradiance in a given incident direction affects radiance in a given direction of reflection [1], it has a wide utilization in graphic rendering [2, 3], remote sensing [4, 5], target recognition [6], and other fields [7, 8]. In general, BRDF model can be divided into three categories: theoretical, empirical, and experimental model [9].
An empirical BRDF model named five-parameter model was proposed by Wu [10]. Wu used genetic algorithm to fit the undetermined parameters, the results demonstrate that the model has good agreement with experimental BRDF data, and it is a good choice to analyze reflectance properties of materials [11]. However, each of the different models is only suitable for typical material. To construct a model with wider applicability, we proposed a data-driven model based on GA-BP network.
The Back-Propagation neural network (BP Network) is the most widely used network (about 80%), which embodies the essence of neural network [12]. BP network can judge the error of output value and actual value according to the error formula, and it can modify the connection weight and threshold repeatedly to make the network error reach the expected value, so it has a strong function approximation ability. As long as the reasonable network structure and parameters are chosen, it can approximate any continuous function [13], so BP is a good choice to build BRDF model. However, BP network has its own disadvantages; because of the principle of gradient descent to adjust the weights, the training results can easily fall into local optimum and cannot achieve the desired results [14].
An effective way to solve this problem is to optimize the initial parameters of BP network for the initial parameters which have a great impact on training [15]. The genetic algorithm (GA) is good at finding candidates potentially close to global optimum and generally not disturbed by local minimum value, so it is suitable for solving the problem of training BP network. In the end of 1980s, Whitley [16], Montana [17], and Miller [18] first attempted to use genetic algorithm to train BP neural network. In recent years, a multitude of scholars have studied the combination of genetic algorithm and BP network, which has a wide range of applications, such as model building [19, 20], fault diagnosis [21], and strategy evaluation [22]. Compared to BP network, the GA-BP network algorithm has better convergence and computational accuracy.
To test the performance of GA-BP in BRDF applications, the BRDF data of two different kinds of materials were measured, and the calculation results demonstrate that GA-BP model has good agreement with experimental data and more accurate than BP model.
2 BP network
The BP network includes input layer, hidden layer, and output layer [23]. In general, there is only one input layer and one output layer, but the hidden layer can be one layer or multiple layers [12]. Single hidden layer is able to approximate continuous function at any interval [24] and too much layers will lead to long training time and over fitting, so a three-layer BP network with five neurons in a single hidden layer was employed. After determining the network structure, the BP network calculates the output H of the hidden layer according to the input data, the connection weights between the input layer and the hidden layer, and the threshold value of the hidden layer. The predicted output of BP neural network is calculated according to weights and thresholds of network connection and the output H of the hidden layer [25]. BP neural network used Levenberg–Marquardt as training algorithm, and corrects weight and threshold from the negative gradient direction of network prediction error until satisfactory error values are obtained [26].
In the case of the same network structure, weight value, and interval value, the relationship between the prediction error, mean square error, and node activation function of the output layer is shown in Table 1.
It can be seen that the selection of the hidden layer and output layer activation functions has a great impact on the prediction accuracy of the BP neural network. In this paper, we select logsig function and purelin function as the activation function of the hidden layer and output layer, respectively. The logsig function is:
And the purelin function is:
The structure of BP network is shown in Fig. 1. We chose the scattering angle and incidence angle as input layer, so the node of the input layer is 2. The BRDF value is set as the output data, so the node of the output layer is 1.
BP neural network must train the network before prediction to make the network to have associative memory and prediction ability through training. We choose 80% of the experimental data as training data, 10% as testing data, and 10% as validation data to verify the prediction ability of the BP network. The learning process of BP includes information forward and error backward propagation [27]. The input angle data are transferred from the input layer to the hidden layer and then to the output layer. The errors between network output results and expected value are transferred from the output layer to the hidden layer and the input layer in turn. During this process, the weights and thresholds of each layer are modified one by one. These two processes cooperate with each other, so that the network can get better parameters and achieve the desired results.
3 GA-BP network
BP neural network optimization based on genetic algorithm can be divided into three parts: BP neural network structure determination, genetic algorithm optimization, and BP neural network prediction. The purpose of optimizing BP neural network by genetic algorithm is to get better initial weights and threshold [28, 29]. Each weight and threshold of BP neural network is encoded by genetic algorithm and connected into a real number array as a chromosome in a certain order, and then the selection, crossover, and mutation operations are performed in the initial chromosome group [30]. In this way, the connection and the threshold of BP network can be optimized to make the network fitting effect more stable [31].
3.1 GA operation
Genetic algorithm filters individuals through selection operation, crossover operation, and mutation operation, so that individuals with good fitness are retained and individuals with poor fitness are eliminated [32]. The new population not only inherits the information of the previous generation, but also is superior to the previous generation. This process repeated until the desired results are obtained.
Selection operation refers to the selection of individuals from the old group to the new group with a certain probability [33]. The probability of individuals being selected is related to the fitness value. The prediction error of BP neural network is taken as the fitness value of the individual. It can be calculated from the formula 3:
where \(n\) is the number of output nodes, \(BRDF_{i0}\) is the ith experimental data, and \(BRDF_{ic}\) is the ith calculated data by BP network.
The better the fitness value of individuals, the greater the probability of being selected [34]. The selection strategy of genetic algorithm is based on roulette method and the selection probability of each individual is:
where \(F_{i}\) is the fitness value of individual \(i\), \(k\) is a coefficient, and \(N\) is the number of individual population.
Then, we use real number crossover method. The crossover operation at the j position between kth individual \(a_{k}\) and \(l\) th individual \(a_{l}\) is [35]:
where \(b\) is a random number in the interval [0,1].
Finally, the mutation operation is executed. It refers to the selection of an individual from a population and the selection of a point in the chromosome for mutation to produce a better individual. The operation method of selecting the \(j\) th gene of the first individual for mutation is [35]:
where \(a_{\max }\) and \(a_{\min }\) are the upper and lower bounds of \(a_{ij}\), \(g\) is the current iteration number, \(G_{\max }\) is the largest number of evolutions, and \(r\) is a random number in the interval [0,1].
3.2 GA-BP operation
As shown in Fig. 2, the optimization procedure of the GA-BP model includes the determination of the structure of BP network, the population initialization, and the iterative operation of genetic algorithm. During the iteration, the BP network is used as an objective function of the genetic algorithm and the output of the function is the prediction error of the sample. The weights and thresholds of BP network are selected, mutated, and crossed due to the “natural environment”, and the individual fitness value are calculated after the evolution. After multiple iterations, the fitness of the individual obtained in the genetic algorithm will be greater as the error get smaller, and the "genes" of weights and thresholds will become better and better. Then, the superior varieties (weights and thresholds) will left so as to achieve the training purpose. After the weights and thresholds of BP network are determined by genetic algorithm, the GA-BP network is will be executed to train and fit the BRDF data.
4 Experiments
We measured BRDF of two different materials and built BRDF models by BP algorithm and GA-BP algorithm, respectively. The accuracy and validity of GA-BP model are verified by comparing the results of these two models.
4.1 BRDF measurement
The BRDF experiment system consists of a visible light source, a precise turntable, a photo-detector, and a power meter. Under condition of the same incident angles (10°, 30°, and 45°) with the scattering angles range from − 70° to 70° in five steps, the BRDF values were measured. As shown in Figs. 3 and 4, these two materials have obvious specular reflection.
4.2 Data preprocessing
After obtaining the experimental BRDF data of two kinds of materials, to facilitate the calculation and analysis of BRDF by neural network, spectral integration is needed. Since the measured values are discrete, the BRDF values between 400 and 900 nm are integrated by the following formula:
where \(f_{ri}\) is the BRDF value of the ith wavelength and \(\Delta \lambda\) is the interval of wavelength.
4.3 Five-parameter BRDF model
The equation of five-parameter model is:
where \(\theta_{r}\) and \(\theta_{i}\) are the scattering and incident angles, respectively; \(G\) is a geometric attenuation factor describes a shadowing phenomenon; \(k_{b}\), \(k_{d}\), \(k_{r}\), \(a\), \(b\) are parameters that need to be determined. We used GA to calculate the five undermined parameters.
4.4 GA-BP model
To improve the robustness and accuracy of the network, we use GA to optimize the initial weights and thresholds and locate some better search spaces in the solution space. Figure 5 shows the genetic search performance from an example. With generations, the better solutions are continuously found.
After optimization by genetic algorithm, the optimal weights and thresholds are brought into the network and combined with the experimental data for training. As shown in Fig. 6, the BP network optimized by GA has better training performance than BP network.
Figures 7 and 8 show all the fitting results of sample 1 and sample 2, respectively, and the calculated curves of both BP network and GA-BP network have great agreement with experimental data at incident angles of 10°, 30°, and 45°. In comparison with these three models, the curve of the GA-BP network fits best with experimental data.
Tables 2 and 3 show the comparison of mean square error and time based on BP network and GA-BP network calculation for sample 1 and sample 2, respectively. It is obviously that the mean square error of GA-BP model is significantly lower than the value of BP model and the operation time of GA-BP model is perfectly short.
5 Conclusion
We proposed a method of building data-driven model based on GA-BP neural network and experimental data. To verify the performance of the GA-BP network, the BRDF values of two different space target materials in the spectral range of 400 nm–900 nm were measured, and the relationship between BRDF and wavelength and scattering angle was analyzed. The feasibility and practicability of the method are verified by the good agreement between the calculation data using the GA-BP model and experimental BRDF data. The BRDF model built by GA-BP neural network proposed in this paper has higher calculation accuracy compared to five-parameter model and BP neural network. In addition, the GA-BP model is not limited to typical materials, and it has more extensive applicability and fast speed.
References
F.E. Nicodemus et al., Geometrical considerations and nomenclature for reflectance. NBS Monograph (U S) 160, 1–52 (1977)
D. Meneveaux et al., Rendering rough opaque materials with interfaced lambertian microfacets. IEEE Trans. Vis. Comput. Graph 24(3), 1368–1380 (2018)
B. Raymond, G. Guennebaud, P. Barla, Multi-scale rendering of scratched materials using a structured SV-BRDF model. ACM Trans. Graph 35(4), 1–11 (2016)
Butler, S.D., et al., Experimentally validated modification to Cook-Torrance BRDF model for improved accuracy, in Earth Observing Systems Xxii, J.J. Butler, X. Xiong, and X. Gu, Editors. 2017.
C.K. Gatebe, M.D. King, Airborne spectral BRDF of various surface types (ocean, vegetation, snow, desert, wetlands, cloud decks, smoke layers) for remote sensing applications. Remote Sens. Environ. 179, 131–148 (2016)
Wu, H.P., et al., Study of Space Spectral Characteristics of the BRDF Diffuse Standard Plate in Visible and Infrared Bands, in Aopc 2015: Optical Test, Measurement, and Equipment, S. Han, et al., Editors. 2015.
I.G.E. Renhorn, T. Hallberg, G.D. Boreman, Efficient polarimetric BRDF model. Opt. Express 23(24), 31253–31273 (2015)
I.G.E. Renhorn, G.D. Boreman, Developing a generalized BRDF model from experimental data. Opt. Express 26(13), 17099–17114 (2018)
R. Montes Soldado, C. Ureña Almagro, An Overview of BRDF Models. 1.-Investigación (2012).
Z. Wu et al., Modeling reflectance function from rough surface and algorithms. Acta Opt. Sin. 22(8), 897–901 (2002)
Q. Wang et al., Hybrid artificial bee colony algorithm for parameter optimization of five-parameter bidirectional reflectance distribution function model. Appl. Opt. 56(33), 9165–9170 (2017)
D.E. Rumelhart, G.E. Hinton, R.J. Williams, Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986)
Y.U. Feng, X.U. Xiaozhong, A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network. Appl. Energy 134(134), 102–113 (2014)
D.S. Chen, R.C. Jain, A robust back-propagation learning algorithm for function approximation. IEEE Trans. Neural Netw. 5(3), 467–479 (1994)
Y.Q. Yang, G.J. Wang, Y. Yang, Parameters optimization of polygonal fuzzy neural networks based on GA-BP hybrid algorithm. Int. J. Mach. Learn. Cybern. 5(5), 815–822 (2014)
Whitley, D., Applying genetic algorithms to neural network problems: Darrell Whitley. Department of Computer Science, Colorado State University, Fort Collins, CO 80523 USA. Neural Networks, 1988. 1: pp. 230.
Montana, D.J. Training Feedforward Neural Networks Using Genetic Algorithm. In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI-89). 1989.
Miller, G.F., P.M. Todd, and S.U. Hegde. Designing neural networks using genetic algorithms. 1989.
X.H. Xue et al., Prediction of slope stability based on ga-bp hybrid algorithm. Neural Netw. World 25(2), 189–202 (2015)
Kassa, Y., et al., A GA-BP Hybrid Algorithm Based ANN Model for Wind Power Prediction. 2016 the 4th IEEE International Conference on Smart Energy Grid Engineering. 2016. 158–163.
Sun, H.Q., et al., The module fault diagnosis of power transformer based on GA-BP algorithm. Proceedings of 2005 International Conference on Machine Learning and Cybernetics, Vols 1–9. 2005. 1596–1598.
H. Chen, S. Cai, M. Zheng, Evaluation of china's sustainable development of energy based on GA-BP model. Acta Energiae Solaris Sinica 31(9), 1220–1224 (2010)
F. He, L. Zhang, Mold breakout prediction in slab continuous casting based on combined method of GA-BP neural network and logic rules. Int. J. Adv. Manuf. Technol. 95(9–12), 4081–4089 (2018)
Sarajedini, A. and R. Hecht-Nielson. The best of both worlds: Casasent networks integrate multilayer perceptrons and radial basis functions. in International Joint Conference on Neural Networks. 1992.
X. Wei, H. Yuan, Y. Lang, Prediction method of icing thickness of transmission line based on MEAO. Cluster Comput. 7, 1–9 (2017)
Duan, H., et al., Modeling and optimization of polysaccharide precipitation of traditional Chinese medicine injection. Int. J. Mach. Learn. Cybern. 2016: pp. 1–10.
S.C. Ng, S.H. Leung, A. Luk, Fast convergent generalized back-propagation algorithm with constant learning rate. Neural Process. Lett. 9(1), 13–23 (1999)
C. Liu, J. Ling, L. Kou, Performance comparison between GA-BP neural network and BP neural network. Chin. J. Health Stat. 30(2), 173 (2013)
W. Wang et al., Optimization of thermal performance of the parabolic trough solar collector systems based on GA-BP neural network model. Int. J. Green Energy 14(10), 819–830 (2017)
H. Li et al., The prediction in computer color matching of dentistry based on GA + BP neural network. Comput. Math. Methods Med. 2015, 816719–816719 (2015)
Y.-J. Liang et al., Research on soil moisture inversion method based on GA-BP neural network model. Int. J. Remote Sens. 40(5–6), 2087–2103 (2019)
Lin, Y., Research on partial selecting operation of genetic algorithm (GA) in integrative global optimization. Oil Geophysical Prospecting, 2000.
D. Li et al., Gesture recognition based on BP neural network improved by chaotic genetic algorithm. Int. J. Autom. Comput. 15(3), 267–276 (2018)
K. Deb, An efficient constraint handling method for genetic algorithms. Comput. Methods Appl. Mech. Eng. 186(2–4), 311–338 (2000)
J. Li et al., A modeling approach for energy saving based on GA-BP neural network. J. Electr. Eng. Technol. 11(5), 1289–1298 (2016)
Funding
This study was funded by the 135 Program (No: KJSP-2016-0401-03).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Liu, Y., Dai, J., Zhao, S. et al. A bidirectional reflectance distribution function model of space targets in visible spectrum based on GA-BP network. Appl. Phys. B 126, 114 (2020). https://doi.org/10.1007/s00340-020-07455-y
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00340-020-07455-y