Journal of Industrial and Systems Engineering

Journal of Industrial and Systems Engineering

An integrated framework for detection of car accident damage using deep neural networks model: a real-life case study

Document Type : Research Paper

Authors
Hossein Mohammadi Dolat-Abadi 1
Fatemeh Sarami 2
1 Assistant Professor, Industrial engineering, Farabi College, University of Tehran
2 Department of Engineering, Farabi College, University of Tehran, Iran
Abstract
In this study, in the insurance industry, an integrated framework based on the Convolutional Neural Networks method is proposed to estimate the amount of car damage after the accident. This paper aims to analyze the performance of deep convolutional network methods in recognizing and classifying six different damage including surface damage, deep damage, car side mirror damage, glass damage, tire damage, and light damage. Regarding the case study, the required data for this research is obtained from the customers of an insurance company in 2021 and 2022 in Iran. This statistical population is a cross-section of all the pictures of accidental cars in the country and includes 20,000 pictures of people's cars after the accident, of which 4,100 pictures were selected and extracted as the target data of the research from the database of third-party insurance companies. The performance of models based on algorithms such as ConvNeXtBase, ConvNeXtXLarge, ResNet-50, ResNet-101, EfficienetNetB7, EfficienetNetV2L, and EfficientNetV2B0 has been evaluated under criteria including accuracy sensitivity, specificity, precision, and F- score criteria to compare all types of heuristic algorithms. The results of this research show that the performance speed of the models largely depends on the characteristics of the pre-trained models and the accuracy of the models is based on algorithms such as AlexNet, VGG-19, ResNet-50 have been obtained in the range of 0.59 to 0.91, which indicates the acceptable performance of these algorithms based on deep convolutional networks in detecting and evaluating car damage after accidents.
Keywords
Deep learning
Convolutional neural network
Car accident damage
Insurance industry
Subjects
Bandi H, Joshi S, Bhagat S, Deshpande A, editors. Assessing Car Damage with Convolutional Neural Networks. 2021 International Conference on Communication information and Computing Technology (ICCICT); 2021 25-27 June 2021.
Crognale M, De Iuliis M, Rinaldi C, Gattulli VJEE, Vibration E. Damage detection with image processing: A comparative study. 2023;22(2):333-45.
Dorafshan S, Thomas RJ, Maguire M. Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete. Construction and Building Materials. 2018;186:1031-
Dwivedi M, Malik HS, Omkar S, Monis EB, Khanna B, Samal SR, et al., editors. Deep learning-based car damage classification and detection. Advances in artificial intelligence and data engineering: Select proceedings of AIDE 2019; 2021: Springer.
Eom H, Choi H. Alpha-pooling for convolutional neural networks. arXiv preprint arXiv:181103436. 2018.
Gao Y, Mosalam KM. Deep transfer learning for image‐based structural damage recognition. Computer‐Aided Civil and Infrastructure Engineering. 2018;33(9):748-6
Han J, Pei J, Tong H. Data mining: concepts and techniques: Morgan kaufmann; 2022.
Kaboodkhani M, Bayesteh H, Hamidia MJEFA. Energy-based damage assessment of RC frames with non-seismic beam-column joint detailing using crack image processing techniques. 2024;155:107723.
Kim H, Kim H, Hong YW, Byun H. Detecting construction equipment using a region-based fully convolutional network and transfer learning. Journal of computing in Civil Engineering. 2018;32(2):04017082.
Kyu PM, Woraratpanya K. Car Damage Detection and Classification. Proceedings of the 11th International Conference on Advances in Information Technology; <conf-loc>, <city>Bangkok</city>, <country>Thailand</country>, </conf-loc>: Association for Computing Machinery; 2020. p. Article 46.
Li B, Wang KC, Zhang A, Yang E, Wang G. Automatic classification of pavement crack using deep convolutional neural network. International Journal of Pavement Engineering. 2020;21(4):457-63.
Maiano L, Montuschi A, Caserio M, Ferri E, Kieffer F, Germanò C, et al. A deep-learning–based antifraud system for car-insurance claims. Expert Systems with Applications. 2023:120644 %@ 0957-4174.
Marnani AB, Teymourzadeh E, Bahadori M, Ravangard R, Pour JSJIJoCRoIM, Health P. Challenges of a large health insurance organization in Iran: A Qualitative Study. 2012;4(6):1050-62.
Medjdoubi A, Meddeber M, Yahyaoui K. Smart City Surveillance: Edge Technology Face Recognition Robot Deep Learning Based %J International Journal of Engineering. 2024;37(1):25-36.
Mohammadzadeh M, Navabakhsh M, Hafezalkotob A. Performance Evaluating Energy, Economic and Environmental Performance with an Integrated Approach of Data Envelopment Analysis and Game Theory %J International Journal of Engineering. 2024;37(5):959-73.
Mohan A, Poobal S. Crack detection using image processing: A critical review and analysis. alexandria engineering journal. 2018;57(2):787-98.
Naderpour H, Abbasi M, Kontoni D-PN, Mirrashid M, Ezami N, Savvides A-AJB. Integrating image processing and machine learning for the non-destructive assessment of RC beams damage. 2024;14(1):214.
Nisha M, Baptista C, Nikhil A, Behl P, editors. Damage Detection on Historical Structure Using Image Processing. International Conference on Machine Learning, Deep Learning and Computational Intelligence for Wireless Communication; 2023: Springer.
Nozari, H., & Szmelter-Jarosz, A. (2022). IoT-based supply chain for smart business. ISNet.
Nozari, H., Tavakkoli-Moghaddam, R., & Dolgui, A. (2024, September). Analysis of Critical Success Factors of Sustainable and Resilient Aioe-based Supply Chain in Industry 5.0. In IFIP International Conference on Advances in Production Management Systems (pp. 76-90). Cham: Springer Nature Switzerland.
Prykaziuk N, Erastov V, Lobova O. PERSPECTIVES OF IMAGE RECOGNITION UTILIZATION IN INSURANCE. MODERN APPROACHES TO KNOWLEDGE MANAGEMENT DEVELOPMENT. 2020:335.
Qaddour J, Siddiqa SA. Automatic damaged vehicle estimator using enhanced deep learning algorithm. Intelligent Systems with Applications. 2023;18:200192.
Ramavath S, Suryawanshi SR. Optimal Prediction of Shear Properties in Beam-Column Joints Using Machine Learning Approach %J International Journal of Engineering. 2024;37(1):67-82.
Ranjbar S, Moghaddasnezhad F, ZAKERI H. Pavement cracks detection and classification using deep convolutional networks. Amirkabir Journal of Civil Engineering. 2020;52(9):2255-78.
Riantini R, Subiyanto L, Adianto. Easolas-LSA: an expert system for determining number of life-saving appliances based on requirement of International Convention for The Safety of Life At Sea. WMU Journal of Maritime Affairs. 2019;18(3):495-507.
Sajitha I, Sambandam RK, John SP, editors. Review on Image Processing-Based Building Damage Assessment Techniques. Doctoral Symposium on Computational Intelligence; 2023: Springer.
Singh R, Ayyar MP, Pavan TVS, Gosain S, Shah RR, editors. Automating car insurance claims using deep learning techniques. 2019 IEEE Fifth International Conference on Multimedia Big Data (BigMM); 2019: IEEE.
Tian Y, Zhang X, Chen H, Wang Y, Wu HJS. A bridge damage visualization technique based on image processing technology and the ifc standard. 2023;15(11):8769.
Tong Z, Gao J, Han Z, Wang Z. Recognition of asphalt pavement crack length using deep convolutional neural networks. Road Materials and Pavement Design. 2018;19(6):1334-49.
Tong Z, Gao J, Zhang H. Innovation for evaluating aggregate angularity based upon 3D convolutional neural network. Construction and Building Materials. 2017;155:919-29.
Vidal R, Bruna J, Giryes R, Soatto S. Mathematics of deep learning. arXiv preprint arXiv:171204741. 2017.
Wiatowski T, Bölcskei H. A mathematical theory of deep convolutional neural networks for feature extraction. IEEE Transactions on Information Theory. 2017;64(3):1845-66.
Wu Z, Yang Y, Zuo Y, Meng X, Wang W, Lei WJAG. Damage evolution characteristics of 3D reconstructed bedding-containing shale based on CT technology and digital image processing. 2024;72(4):2503-19.
Zhang K, Cheng H, editors. A novel pavement crack detection approach using pre-selection based on transfer learning. Image and Graphics: 9th International Conference, ICIG 2017, Shanghai, China, September 13-15, 2017, Revised Selected Papers, Part I 9; 2017: Springer.

  • Receive Date 02 September 2024
  • Revise Date 11 November 2024
  • Accept Date 07 December 2024