Traffic surveillance: vehicle detection and pose estimation based on deep learning

• Autorzy: Fadhil, Fajer , Abdulghani, Mohammed Moath , Salih, Anmar , Ghazal, Mohammed Tala

Warianty tytułu

PL

Nadzór drogowy: wykrywanie pojazdów i szacowanie pozycji w oparciu o głębokie uczenie się

• Języki publikacji: EN

Abstrakty

EN

Video-based traffic surveillance analysis is an important area of research with numerous applications in intelligent transportation systems. Due to camera positioning, background crowd, and vehicle orientation fluctuations, urban situations are more complex than highways. This paper provides a state-of-the-art technique for vehicle detection and orientation estimation based on the convolutional neural network CNN for detecting and determining the orientation of a vehicle from a given image to reduce traffic accidents. Different CNN model architectures have been examined to reach this approach's goal, which results in a small and fast model that is compatible with limited-resources hardware. A large-scale dataset of vehicles has been used to train the model. The dataset includes different types and views of cars; the taken images are high quality with diverse backgrounds and light conditions. To train the model, the dataset has been divided into five classes according to view: Front, Rear, Side, Front-side, and Rear-side, to fit the requirement of this work. The system achieves a high accuracy result.

PL

Analiza monitoringu ruchu oparta na wideo jest ważnym obszarem badań z licznymi zastosowaniami w inteligentnych systemach transportowych. Ze względu na ustawienie kamery, tłum w tle i wahania orientacji pojazdu sytuacje w mieście są bardziej złożone niż na autostradach. W artykule przedstawiono najnowocześniejszą technikę wykrywania pojazdów i szacowania orientacji w oparciu o konwolucyjną sieć neuronową CNN do wykrywania i określania orientacji pojazdu na podstawie danego obrazu w celu zmniejszenia liczby wypadków drogowych. Zbadano różne architektury modeli CNN, aby osiągnąć cel tego podejścia, co skutkuje małym i szybkim modelem, który jest kompatybilny ze sprzętem o ograniczonych zasobach. Do trenowania modelu wykorzystano wielkoskalowy zbiór danych pojazdów. Zbiór danych zawiera różne typy i widoki samochodów; wykonane zdjęcia są wysokiej jakości z różnym tłem i warunkami oświetleniowymi. Aby wytrenować model, zestaw danych został podzielony na pięć klas według widoku: przód, tył, bok, przód i tył, aby spełnić wymagania tej pracy. System osiąga wysoką dokładność wyniku.

Słowa kluczowe

PL

nadzór drogowy; sieć neuronowa; głębokie uczenie się

EN

vehicle; convolutional neural network; orientation estimation; surveillance system

• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2023
• Tom: R. 99, nr 2
• Strony: 131--134
• Opis fizyczny: Bibliogr. 25 poz., rys., tab.

Twórcy

autor

Fadhil, Fajer

• Mosul University, Iraq,

autor

Abdulghani, Mohammed Moath

• Mosul University, Iraq,

autor

Salih, Anmar

• Northern Technical University, Iraq,

autor

Ghazal, Mohammed Tala

• Northern Technical University, Iraq,

Bibliografia

• [1] X. Liu, W. Liu, T. Mei, and H. Ma. Provid: Progressive and multimodal vehicle reidentification for large-scale urbansurveillance. IEEE Transactions on Multimedia, 20(3):645–658, 2018.
• [2] S. Sivaraman, and M.M. Trivedi, “Looking at vehicles on the road: A survey of vision-based vehicle detection, tracking, andbehavior analysis,” IEEE Transactions on Intelligent Transportation Systems, vol. 14, no. 4, pp. 1773-1795, 2013.
• [3] Szypuła, Ernest. Using deep learning to recognize the sign alphabet. Diss. Instytut Elektrotechniki Teoretycznej i Systemów Informacyjno-Pomiarowych, 2021.
• [4] Kim, J. U., & Kang, H. B., “A new 3D object pose detection method using LIDAR shape set. Sensors," 18(3), 882, 2018.
• [5] S. Agarwal, A. Awan, and D. Roth, “Learning to detect objects in images via a sparse, part-based representation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.26, no. 11, pp. 1475-1490, 2004.
• [6] N. Dalal, and B. Triggs, “Histograms of oriented gradients for human detection,” in proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, Jun. 2005, pp. 886-893.
• [7] D.G. Lowe, “Object recognition from local scale-invariant features”, in proc. IEEE 7th international conference on Computer vision, Jan. 1999, vol. 2, pp. 1150-1157.
• [8] P. Viola, and M. Jones, “Rapid object detection using a boostedcascade of simple features,” in proc. of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001, vol. 1, pp. I-511.
• [9] N. J. T. Abdullah, M. Ghazal, and N. Waisi, “Pedestrian age estimation based on deep learning," vol. 22, no. 3, 2021.
• [10] M. Ghazal, R. Albasrawi, N. Waisi, and M. Al Hammoshi,"Smart Meeting Attendance Checking Based on A multi-biometric Recognition System," PRZEGLĄD ELEKTROTECHNICZNY, vol. 2022, no. 3, pp. 93-96, 2022
• [11] C. Wang, Y. Fang, H. Zhao, C. Guo, S. Mita, and H. Zha, “Probabilistic Inference for Occluded and Multiview On-road Vehicle Detection,” IEEE Trans. Intell. Transp. Syst., vol. 17,no. 1, pp. 215–229, Jan. 2016.
• [12] T. Wu, B. Li, and S. C. Zhu, “Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation,” IEEE Trans. Pattern Anal. Mach. Intell.,vol. PP, no. 99, p. 1, 2015.
• [13] H. He, Z. Shao, and J. Tan, “Recognition of Car Makes and Models From a Single Traffic-Camera Image,” IEEE Trans. Intell. Transp. Syst., vol. 16, no. 6, pp. 3182–3192, Dec. 2015.
• [14] K. H. Lee, J. N. Hwang, and S. I. Chen, “Model-Based Vehicle Localization Based on 3-D Constrained Multiple-Kernel Tracking,” IEEE Trans. Circuits Syst. Video Technol., vol. 25, no. 1, pp. 38–50, Jan. 2015.
• [15] Y. Tang, C. Zhang, R. Gu, P. Li, and B. Yang, “Vehicle detection and recognition for intelligent traffic surveillance system,” Multimed. Tools Appl., pp. 1–16, 2015.
• [16] Joseph Redmon and Ali Farhadi. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767, 2018.
• [17] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
• [18] Alejandro Newell, Kaiyu Yang, and Jia Deng. Stacked hourglass networks for human pose estimation. In European Conference on Computer Vision, pages 483–499. Springer, 2016.
• [19] Adrian Bulat and Georgios Tzimiropoulos. Human pose estimation via convolutional part heatmap regression. In European Conference on Computer Vision, pages 717–732. Springer, 2016.
• [20] S. Tulsiani and J. Malik, “Viewpoints and Keypoints,” in Proc. 2015 IEEE Conf. on Comput. Vision and Pattern Recognition (CVPR), Boston, USA, 2015, pp. 1510-1519.
• [21] Z. Wang, L. Tang, X. Liu, Z. Yao, S. Yi, J. Shao, J. Yan, S. Wang, H. Li, and X. Wang. Orientation invariant feature embedding and spatial temporal regularization for vehicle reidentification. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 379–387, 2017.
• [22] Yang, L., Luo, P., Loy, C. C., and Tang, X. 2015. A largescale car dataset for fine-grained categorization and verification. In Proceedings of CVPR
• [23] Kuhn, Daniel M., and Viviane P. Moreira. “BRCars: a Dataset for Fine-Grained Classification of Car Images,” 2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI). IEEE, 2021, p. 231-238.
• [24] Ponimatkin, G., Labbé, Y., Russell, B., Aubry, M., & Sivic, J. “Focal Length and Object Pose Estimation via Render and Compare,” 2022 In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, p. 3825-3834.
• [25] Sang, J.; Guo, P.; Xiang, Z.; Luo, H.; Chen, X. Vehicle detection based on faster-RCNN. J. Chongqing Univ. (Nat. Sci. Ed.) 2017, 40, 32–36.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).

Identyfikatory

DOI

10.15199/48.2023.02.22