Abstract
Process mining has shown that it provides valuable insights in terms of uncovering bottlenecks and inefficiencies in processes or identifying tasks for automation. However, process mining techniques expect structured input data that is at a high (business) level of abstraction. Recently, the benefits of process mining for unstructured data which is at a much lower level of abstraction have been demonstrated, e.g., for IoT data or time series data. It can be expected that the demand for methods efficiently processing these kinds of data for process mining will continuously increase. Hence, in this paper, we present an approach that allows the translation of video data into higher-level, discrete event data, thus enabling existing process mining techniques to work on data tracked in videos. Particularly, we used a combination of object tracking, spatio-temporal action detection, and techniques for raising the abstraction level of events. The evaluation results show that meaningful event logs can be extracted from an unlabeled video dataset, validating both the implementation and the feasibility of our approach.
We thank Jan Bosselmann for his support with the implementation, and the Institute of Agricultural Engineering at Kiel University for providing a dataset and use case. This project has received funding from the State of Schleswig-Holstein under the Datencampus project grant no. 220 21 016.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
van der Aalst, W., et al.: Process mining manifesto. In: Daniel, F., Barkaoui, K., Dustdar, S. (eds.) BPM 2011. LNBIP, vol. 99, pp. 169–194. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-28108-2_19
Bergamini, L., et al.: Extracting accurate long-term behavior changes from a large pig dataset. In: VISAPP 2021, vol. 4, pp. 524–533. SCITEPRESS, Online Streaming (2021). https://doi.org/10.5220/0010288405240533
Berti, A., van Zelst, S.J., van der Aalst, W.: Process Mining for Python (PM4Py): bridging the gap between process- and data science (2019). https://doi.org/10.48550/arXiv.1905.06169
Cao, J., Weng, X., Khirodkar, R., Pang, J., Kitani, K.: Observation-centric sort: rethinking sort for robust multi-object tracking. arXiv preprint (2022). https://doi.org/10.48550/arXiv.2203.14360
Chen, C., Zhu, W., Norton, T.: Behaviour recognition of pigs and cattle: journey from computer vision to deep learning. Comput. Electron. Agric. 187, 106255 (2021). https://doi.org/10.1016/j.compag.2021.106255
Diamantini, C., Genga, L., Potena, D.: Behavioral process mining for unstructured processes. J. Intell. Inf. Syst. 47(1), 5–32 (2016). https://doi.org/10.1007/s10844-016-0394-7
Diba, K., Batoulis, K., Weidlich, M., Weske, M.: Extraction, correlation, and abstraction of event data for process mining. WIREs Data Min. Knowl. Discov. 10(3), e1346 (2020). https://doi.org/10.1002/widm.1346
Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: ICCV 2019, pp. 6201–6210. Seoul, Korea (South) (2019). https://doi.org/10.1109/ICCV.2019.00630
Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: CVPR 2018, pp. 6047–6056 (2018). https://doi.org/10.1109/CVPR.2018.00633
Janssen, D., Mannhardt, F., Koschmider, A., van Zelst, S.J.: Process model discovery from sensor event data. In: Leemans, S., Leopold, H. (eds.) ICPM 2020. LNBIP, vol. 406, pp. 69–81. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-72693-5_6
Knoch, S., Ponpathirkoottam, S., Schwartz, T.: Video-to-Model: unsupervised trace extraction from videos for process discovery and conformance checking in manual assembly. In: Fahland, D., Ghidini, C., Becker, J., Dumas, M. (eds.) BPM 2020. LNCS, vol. 12168, pp. 291–308. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58666-9_17
Koschmider, A., Mannhardt, F., Heuser, T.: On the contextualization of event-activity mappings. In: Daniel, F., Sheng, Q.Z., Motahari, H. (eds.) BPM 2018. LNBIP, vol. 342, pp. 445–457. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11641-5_35
Koschmider, A., Oppelt, N., Hundsdörfer, M.: Confidence-driven communication of process mining on time series. Informatik Spektrum 45(4), 223–228 (2022). https://doi.org/10.1007/s00287-022-01470-3
Kratsch, W., König, F., Röglinger, M.: Shedding light on blind spots - developing a reference architecture to leverage video data for process mining. Decis. Support Syst. 158, 113794 (2022). https://doi.org/10.1016/j.dss.2022.113794
Leemans, S.J.J., Fahland, D., van der Aalst, W.M.P.: Discovering block-structured process models from event logs containing infrequent behaviour. In: Lohmann, N., Song, M., Wohed, P. (eds.) BPM 2013. LNBIP, vol. 171, pp. 66–78. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-06257-0_6
Lepsien, A.: Quantifying uncertainty for explainable process mining. In: Proceedings of the 13th International Workshop on Enterprise Modeling and Information Systems Architectures (EMISA 2023). CEUR Workshop Proceedings, vol. 3397. CEUR-WS.org, Stockholm, Sweden (May 2023). https://ceur-ws.org/Vol-3397/
Lepsien, A., Bosselmann, J., Melfsen, A., Koschmider, A.: Process mining on video data. In: Manner, J., Lübke, D., Haarmann, S., Kolb, S., Herzberg, N., Kopp, O. (eds.) ZEUS 2022. CEUR Workshop Proceedings, vol. 3113, pp. 56–62. CEUR-WS.org, Bamberg, Germany (2022). https://ceur-ws.org/Vol-3113/paper9.pdf
Lepsien, A., Koschmider, A., Kratsch, W.: Video process mining evaluation data (2023). https://doi.org/10.5281/zenodo.7763839
Luo, W., Xing, J., Milan, A., Zhang, X., Liu, W., Kim, T.K.: Multiple object tracking: a literature review. Artif. Intell. 293, 103448 (2021). https://doi.org/10.1016/j.artint.2020.103448
Mannhardt, F., Koschmider, A., Baracaldo, N., Weidlich, M., Michael, J.: Privacy-preserving process mining. Bus. Inf. Syst. Eng. 61(5), 595–614 (2019). https://doi.org/10.1007/s12599-019-00613-3
MMAction2 Contributors: openmmlab’s next generation video understanding toolbox oand benchmark. https://github.com/open-mmlab/mmaction2 (2020)
Nannoni, E., Aarnink, A.J.A., Vermeer, H.M., Reimert, I., Fels, M., Bracke, M.B.M.: Soiling of Pig Pens: a review of eliminative behaviour. Animals 10(11), 2025 (2020). https://doi.org/10.3390/ani10112025
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Pegoraro, M., Uysal, M.S., van der Aalst, W.M.P.: Efficient construction of behavior graphs for uncertain event data. In: Abramowicz, W., Klein, G. (eds.) BIS 2020. LNBIP, vol. 389, pp. 76–88. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-53337-3_6
Rebmann, A., Emrich, A., Fettke, P.: Enabling the discovery of manual processes using a multi-modal activity recognition approach. In: Di Francescomarino, C., Dijkman, R., Zdun, U. (eds.) BPM 2019. LNBIP, vol. 362, pp. 130–141. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-37453-2_12
Shermin, T., Teng, S.W., Murshed, M., Lu, G., Sohel, F., Paul, M.: Enhanced transfer learning with imagenet trained classification layer. In: Lee, C., Su, Z., Sugimoto, A. (eds.) PSIVT 2019. LNCS, vol. 11854, pp. 142–155. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-34879-3_12
Wada, K.: LabelMe: image polygonal annotation with Python (2023). https://doi.org/10.5281/zenodo.5711226, https://github.com/wkentaro/labelme
Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors (2022). https://doi.org/10.48550/arXiv.2207.02696
Weijters, A., van Der Aalst, W.M., De Medeiros, A.A.: Process mining with the heuristics miner-algorithm. TU Eindhoven, Tech. Rep. WP 166(July 2017), 1–34 (2006)
Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2. https://github.com/facebookresearch/detectron2 (2019)
Zandkarimi, F., Rehse, J.R., Soudmand, P., Hoehle, H.: A generic framework for trace clustering in process mining. In: ICPM 2020, pp. 177–184. IEEE, Padua, Italy (2020). https://doi.org/10.1109/ICPM49681.2020.00034
van Zelst, S.J., Mannhardt, F., de Leoni, M., Koschmider, A.: Event abstraction in process mining: literature review and taxonomy. Granular Comput. 6(3), 719–736 (2020). https://doi.org/10.1007/s41066-020-00226-2
Zhang, Y., et al.: ByteTrack: multi-object tracking by associating every detection box. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, pp. 1–21. LNCS, Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20047-2_1
Zisgen, Y., Janssen, D., Koschmider, A.: Generating synthetic sensor event logs for process mining. In: De Weerdt, J., Polyvyanyy, A. (eds.) CAiSE Forum 2022. LNBIP, vol. 452, pp. 130–137. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-07481-3_15
Zoric, M., Johansson, S.E., Wallgren, P.: Behaviour of fattening pigs fed with liquid feed and dry feed. Porc. Health Manag. 1(1), 14 (2015). https://doi.org/10.1186/s40813-015-0009-7
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
Lepsien, A., Koschmider, A., Kratsch, W. (2023). Analytics Pipeline for Process Mining on Video Data. In: Di Francescomarino, C., Burattin, A., Janiesch, C., Sadiq, S. (eds) Business Process Management Forum. BPM 2023. Lecture Notes in Business Information Processing, vol 490. Springer, Cham. https://doi.org/10.1007/978-3-031-41623-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-41623-1_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-41622-4
Online ISBN: 978-3-031-41623-1
eBook Packages: Computer ScienceComputer Science (R0)