Abstract
Quality measurement of vehicle ambient lighting during series production can be influenced by subjective perceptions of light homogeneity. In consequence, the labels correspond to the decisions whether the lights appear homogeneous or not. In this article we demonstrate how images of ambient lighting were trained by Deep Belief Networks using the learning rules “backpropagation” (BP) and “enforcing-rule supervised” (ERS). In addition, the effect of the contrastive divergence pre-training is analyzed on the accuracy of the trained networks. The results are promising for decision support in the production process to minimize the influence of subjectivity by human evaluators.
Supported by MENTOR GmbH & Co. Präzisions-Bauteile KG.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Schellinger, S., Franzke, D., Klinger, K., Lemmer, U.: Advantages of ambient interior lighting for drivers contrast vision. In: Proceedings of SPIE 6198, Photonics in the Automobile II, 61980J (2006)
Flannagan, M.J., Devonshire, J.M.: Effects of automotive interior lighting on driver vision. Leukos 9(1), 9–23 (2012)
Winklbauer, M., Bayersdorfer, B., Lang, J.: Evocative lighting design for premium interiors. ATZ Worldw 117, 32–35 (2015)
Caberletti, L., Elfmann, K., Kummel, M., Schierz, C.: Influence of ambient lighting in a vehicle interior on the driver’s perceptions. Lighting Res. Technol. 42(3), 297–311 (2010)
Luo, W., Luo, X.: User experience research on automotive interior lighting design. In: Ahram, T., Falcão, C. (eds.) AHFE 2017. AISC, vol. 607, pp. 240–246. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-60492-3_23
Nandyala, S., Gayathri, K., Sharath, D.H., Manalikandy, M.: Human Emotion Based Interior Lighting Control. No. 2018–01-1042, SAE Technical Paper (2018)
Weirich, C., Lin, Y., Khanh, T.Q.: Evidence for human-centric in-vehicle lighting: part 1. Appl. Sci. 12, 552 (2022)
Kim, T., Kim, Y., Jeon, H., Choi, C.-S., Suk, H.-J.: Emotional response to in-car dynamic lighting. Int. J. Autom. Technol. 22(4), 1035–1043 (2021). https://doi.org/10.1007/s12239-021-0093-4
Hassib, M., Braun, M., Pfleging, B., Alt, F.: Detecting and influencing driver emotions using psycho-physiological sensors and ambient light. In: Lamas, D., Loizides, F., Nacke, L., Petrie, H., Winckler, M., Zaphiris, P. (eds.) INTERACT 2019. LNCS, vol. 11746, pp. 721–742. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-29381-9_43
Bohrmann, D., Bruder, A., Bengler, K.: Effects of dynamic visual stimuli on the development of carsickness in real driving. IEEE Trans. Intell. Transp. Syst. 23(5), 4833–4842 (2022)
Shelton, B., Nesbitt, K., Thorpe, A., Eidels, A.: Assessing the cognitive load associated with ambient displays. Pers. Ubiquit. Comput. 26(1), 185–204 (2022)
Blankenbach, K., Hertlein, F., Hoffmann, S.: Advances in automotive interior lighting concerning new LED approach and optical performance. J. Soc. Inf. Display. 28, 655–667 (2020)
Fotios, S., Robbins, C.J., Uttley, J.: A comparison of approaches for investigating the impact of ambient light on road traffic collisions. Lighting Res. Technol. 53(3), 249–261 (2020)
Fotios, S., Robbins, C.J.: Effect of ambient light on the number of motorized vehicles, cyclists, and pedestrians. Transp. Res. Record 03611981211044469 (2021)
Blankenbach, K., Brezing, L., Reichel, S.: Evaluation of luminance vs. brightness for automotive RGB LED light guides in autonomous cars. In: Proceedings of SPIE 11874, Illumination Optics VI, p. 1187406 (2021)
FakhrHosseini, S., Ko, S., Alvarez, I., Jeon, M.: Driver emotions in automated vehicles. In: Riener, A., Jeon, M., Alvarez, I. (eds.) User Experience Design in the Era of Automated Driving. SCI, vol. 980, pp. 85–97. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-77726-5_4
Mangla, A., Gulati, D., Jhamb, N., Vashist, D.: Design analysis of dimmer light for autonomous vehicles. In: Khosla, A., Aggarwal, M. (eds.) Smart Structures in Energy Infrastructure. SIC, pp. 145–152. Springer, Singapore (2022). https://doi.org/10.1007/978-981-16-4744-4_15
Stylidis, K., Woxlin, A., Siljefalk, L., Heimersson, E., Söderberg, R.: Understanding light. A study on the perceived quality of car exterior lighting and interior illumination. Procedia CIRP 93, 1340–1345 (2020)
Fernandez, V., Chavez, J., Kemper, G.: Device to evaluate cleanliness of fiber optic connectors using image processing and neural networks. Int. J. Electr. Comput. Eng. (IJECE) 11(4), 3093–3105 (2021)
Lin, H., Li, B., Wang, X., Shu, Y., Niu, S.: Automated defect inspection of LED chip using deep convolutional neural network. J. Intell. Manuf. 30(6), 2525–2534 (2019)
Fu, Y., Downey, A.R.J., Yuan, L., Zhang, T., Pratt, A., Balogun, Y.: Machine learning algorithms for defect detection in metal laser-based additive manufacturing: A review. J. Manuf. Process. 75, 693–710 (2022)
Liu, Y., Zhou, H., Tsung, F., Zhang, S.: Real-time quality monitoring and diagnosis for manufacturing process profiles based on deep belief networks. Comput. Ind. Eng. 136, 494–503 (2019)
Huang, X., Zhang, X., Xiong, Y., Liu, H., Zhang, Y.: A novel intelligent fault diagnosis approach for early cracks of turbine blades via improved deep belief network using three-dimensional blade tip clearance. IEEE Access 9, 13039–13051 (2021)
Bengio, Y., Lamblin, P., Popovici, D., Larochelle. H.: Greedy layer-wise training of deep networks, Technical Report 1282 (2006)
Klüver, C., Klüver, J.: New learning rules for three-layered feed-forward neural networks based on a general learning schema. In: Madani K. (ed.) Proceedings of ANNIIP: International Workshop on Artificial Neural Networks and Intelligent Information Processing. Portugal: Scitepress, 2014, pp. 27–36 (2014)
Hinton, G.E.: training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771–1800 (2002)
Jahani, A.: Forest landscape aesthetic quality model (FLAQM): a comparative study on landscape modelling using regression analysis and artificial neural networks. J. Forest Sci. 65, 61–69 (2019)
Thiemermann, S., Braun, G., Klüver, C.: Homogeneity testing of LED light guides by neural networks. In Klüver, C, Klüver, J. (eds.): New algorithms for practical problems: variations on artificial intelligence and artificial life, pp. 325–339. Wiesbaden: Springer Fachmedien Wiesbaden (2021). (in German)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Braun, G., Brokamp, M., Klüver, C. (2023). Training Subjective Perception Biased Images of Vehicle Ambient Lights with Deep Belief Networks Using Backpropagation- and Enforcing-Rules Supervised. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2022. Lecture Notes in Computer Science(), vol 13588. Springer, Cham. https://doi.org/10.1007/978-3-031-23492-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-23492-7_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23491-0
Online ISBN: 978-3-031-23492-7
eBook Packages: Computer ScienceComputer Science (R0)