اخبار و اعلانات
آمار
| تعداد نشریات | 38 |
| تعداد شماره‌ها | 1,240 |
| تعداد مقالات | 8,992 |
| تعداد مشاهده مقاله | 7,843,161 |
| تعداد دریافت فایل اصل مقاله | 4,704,907 |
شناسایی سریع مکان و نوع وسیله نقلیه در تصاویر با استفاده از روش یادگیری عمیق | ||
| پدافند الکترونیکی و سایبری | ||
| دوره 10، شماره 2 - شماره پیاپی 38، مهر 1401، صفحه 117-127 اصل مقاله (1.32 M) | ||
| نوع مقاله: مقاله پژوهشی | ||
| نویسندگان | ||
| مجتبی ناصحی1؛ محسن عشوریان* 2؛ حسین امامی2 | ||
| 1دانشجوی دکترا، دانشکده مهندسی برق، دانشگاه آزاد واحد شهر مجلسی، اصفهان، ایران | ||
| 2دانشیار، دانشکده مهندسی برق، واحد شهر مجلسی، دانشگاه آزاد اسلامی، اصفهان، ایران | ||
| تاریخ دریافت: 31 مرداد 1400، تاریخ بازنگری: 29 آبان 1400، تاریخ پذیرش: 18 مرداد 1401 | ||
| چکیده | ||
| امروزه وسایل نقلیه در مقیاس بالا، در قسمت‌های مختلف شهر پراکنده هستند و از این جهت احتیاج به کنترل توسط سامانههای برنامه‌ریزی شده دارند. پیدا کردن خودکار وسایل نقلیه در تصویر و دسته‌بندی نوع آنها پیچیده است، زیرا وسایل نقلیه شکل‌ها، رنگها و مدل‌های بسیار متفاوتی دارند و طراحی‌شان با یکدیگر متفاوت است. از این رو روشهای مختلف آنالیز تصاویر برای حل این مسئله مطرح گردیده است. اما بعضی از چالشها مانند تعدد تصویر در یک صحنه، بهم پیوستگی تصویر وسیله نقلیه و زمینه تصویر، وجود نویز در تصاویر، تلرانس نسبت به تغییرات نور وجود دارد. در سالهای اخیر استفاده از شبکه‌های عصبی عمیق به‌عنوان ابزاری کارآمد در شناسایی با وجود تنوع شرایط محیطی و اجسام مطرح شدهاند. اما چالش استفاده از شبکه‌های عصبی عمیق بار محاسباتی بالای آنهاست. در این مقاله رویکرد جدیدی برای شناسایی نوع وسایل نقلیه استفاده میشود، این رویکرد از ترکیب شبکه عصبی VGG و الگوریتم تفکیک و دنبال کردن تصاویر Yolo استفاده کرده است. این روش باعث بهبود چالشهای روشهای پیشین میگردد و در ضمن باعث کاهش بار محاسباتی میگردد. تصاویر از دو پایگاه داده ImageNet و COCO گرفته شده و از این پایگاهها به‌منظور آموزش و آزمون شبکه عصبی استفاده میگردد. نتایج نشان میدهد که سامانه طراحی شده بسیاری از مشکلات را به خوبی برطرف مینماید. دقت تشخیص در مقایسه با سامانههای قبلی 2 الی 3 درصد افزایش یافته است. از مزایا این رویکرد میتوان به کیفیت بالا در آشکارسازی تصاویر و سرعت قابل قبول در تشخیص نوع وسیله نقلیه اشاره کرد. | ||
| کلیدواژه‌ها | ||
| تشخیص وسایل نقلیه؛ شبکه عصبی عمیق کانولوشن؛ شبکه عصبی VGG | ||
| عنوان مقاله [English] | ||
| Fast Detection of Vehicle Type and Position in Images Based on Deep Neural Network | ||
| نویسندگان [English] | ||
| Mojtaba Nasehi1؛ Mohsen Ashoorian2؛ Hossein Emami2 | ||
| 1PhD student, Faculty of Electrical Engineering, Shahr Majlesi Azad University, Isfahan, Iran | ||
| 2Associate Professor, Faculty of Electrical Engineering, Shahr Majlesi Branch, Islamic Azad University, Isfahan, Iran | ||
| چکیده [English] | ||
| Today, large-scale vehicles are scattered in different parts of the city and therefore need to be controlled by programmed systems. Automatically finding vehicles in the images and categorizing them is complicated because vehicles come in so many different shapes, colors, and models, and their designs are so different. Therefore, different methods of image analysis have been proposed to solve this problem. But there are some challenges such as the multiplicity of images in a scene, the coherence of the image of the vehicle and the image background, the presence of noise in the images and the tolerance to changes in light. In recent years, the use of deep neural networks has been proposed as an effective tool in identification despite the diversity of environmental conditions and objects. But the challenge of using deep neural networks is their high computational load. In this paper, a new approach is used to identify the type of vehicles, which uses a combination of VGG neural network and the Yolo image separation and tracking algorithm. This method improves the challenges of the previous methods and also reduces the computational load. The images are taken from two databases, ImageNet and COCO, and these databases are used to train and test the neural network. The results show that the designed system solves many problems well, including the speed of vehicle detection and the problem of computational load. The detection accuracy has increased by 2 to 3% compared to previous systems and has reached about 98%. The advantages of this approach include high-quality image detection and the use of a YOLO algorithm with an acceptable speed in detecting the type of vehicle. | ||
| کلیدواژه‌ها [English] | ||
| Real-time algorithm, Deep Convolutional Neural Networks (CNN), Neural Networks VGG, Vehicle Detection | ||
| مراجع | ||
|
[1] S. Yamaguchi, "A Car Detection System Using the Neocognitron," IEEE International Joint Conference on, Singapore, 2002. [2] T. Tang, S. Zhou, Z. Deng, H. Zou, and L. Lei, "Vehicle Detection in Aerial Images Based on Region Convolutional Neural Networks and Hard Negative Example Mining," Sensor, 2017. [3] B. D. Stewart, I. Reading, M. S. Thomson, T. D. Binnie, K. W. Dickinson, and C. L. Wan, "Adaptive Lane Finding in Road Traffic Image Analysis," Proceedings of Seventh International Conference on Road Traffic Monitoring and Control, IEEE, London, 1994. [4] W. Enkelmann, "Obstacle Detection by Evaluation of Optical Flow Field from Image Sequences," Proceedings of European Conference on Computer Vision, Antibes, France 427, pp. 134–138, 1990. [5] Y. Park, "Shape-resolving Local Thresholding for Object Detection," Pattern Recognition Letters 22, pp. 883–890, 2001. [6] J. M. Blosseville, C. Krafft, F. Lenoir, V. Motyka, and S. Beucher, "New Traffic Measurements by Image Processing," IFAC Transportation Systems, Tianjin, Proceedings, 1994. [7] Y. Won, J. Nam, and B. H. Lee, "Image Pattern Recognition in Natural Environment Using Morphological Feature Extraction", In: F.J. Ferri (Ed.), SSPR&SPR 2000, Springer, Berlin, pp.806–815, 2001. [8] J. B. Kim, H. S. Park, M. H. Park, and H. J. Kim, "A Real-time Region-based Motion Segmentation Using Adaptive Thresholding and K-means Clustering," In: M. Brooks, D. Corbett, M. Stumptner (Eds.), AI 2001, Springer, Berlin, pp. 213–224, 2001. [9] M. Dubuisson and A. Jain, "Contour Extraction of Moving Objects in Complex Outdoor Scenes", International Journal of Computer Vision, vol. 14, pp. 83–105, 1995. [10] H. Bensedik, A. Azough and M. Meknasssi, "Vehicle Type Classification Using Convolutional Neural Network", IEEE 5th International Congress on Information Science and Technology (CiSt), 2018. [11] Y. Li, B. Song, X. Kang, X. Du, and M. Guizani, "Vehicle-type Detection Based on Compressed Sensing and Deep Learning in Vehicular Networks," Sensors, 2018. [12] A. Techmer, "Real-time Motion Based Vehicle Segmentation in Traffic Lanes", In: B. Radig, S. Florczyk (Eds.), DAGM, Springer, Berlin, pp. 202–207, 2001. [13] M. A. Ali, H. E. Abd El Munim,. A. H. Yousef,and Sh. Hammad, "A Deep Learning Approach for Vehicle Detection," 13th International Conference on Computer Engineering and Systems (ICCES), 2018. [14] A. Giachetti, M. Campani, and V. Torre, (). "The Use of Optical Flow for Road Navigation," IEEE Transactions on Robotics and Automation, vol. 14, no. 1, 2000. [15] X. Li, Z. Q. Liu, and K. M. Leung, "Detection of Vehicles from Traffic Scenes Using Fuzzy Integrals," Pattern Recognition, vol. 35, pp. 967–980, 2002. [16] M. Oliveria and V. Santos, "Automatic Detection of Cars in Real Roads Using Haar-like Features,"[M1] Department of Mechanical Engineering, University of Aveiro, Portugal, 2008. [17] M. Nasehi, M. Ashourian, and P. Moalem, "An Overview of the Type of Vehicle Detection Techniques," Majlesi Journal of Telecommunication Devices, vol. 9, no. 3, 2020. [18] G. D. Sullivan, K. D. Baker, A. D. Worrall, C. I. Attwood, and P. M. Remagnino, () "Model-based Vehicle Detection and Classification Using Orthographic Approximations," Image and Vision Computing, vol. 15, [M2] pp. 649–654, 2004. [19] Z. Zhigang, L. Huan, D. Pengcheng, Z. Guangbing, W. Nan , and Z. Wei-Kun., "Vehicle Target Detection Based on R-FCN," Chinese Control And Decision Conference (CCDC), 2018. [20] X. Wang, W. Zhang, X. Wu, L. Xiao, Y. Qian, and Z. Fang."Real-time Vehicle Type Classification with Deep Convolutional Neural Networks," Journal of Real-Time Image Processing, 2019. [21] Z. Zhang, C. Xu, and W. Feng , "Road Vehicle Detection and Classification Based on Deep Neural Network"7th IEEE International Conference on Software Engineering and Service Science (ICSESS), 2016. [22] Sh. Yu, Y. Wu, W. Li, Z. Song, and W. Zeng,"A Model for Fine-Grained Vehicle Classification Based on Deep Learning", Neurocomputing, , [M3] 2017. [23] L. Suhao,, L. Jinzhao, L. Guoquan, B. Tong, W. Huiqian, and P. Yu, "Vehicle Type Detection Based on Deep Learning in Traffic Scene," Procedia Computer Science, 2018. [24] M. Sheng, Ch. Liu, Q. Zhang, L. Lou, and Y. Zheng, "Vehicle Detection and Classification Using Convolutional Neural Networks," IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS), 2018. [25] A. Murali,, B. B Nair, and S. N. Rao, "Comparative Study of Different CNNs for Vehicle Classification," IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), 2018. [26] H. Moon, R. Chellapa, and A. Rosenfeld, "Performance Analysis of a Simple Vehicle Detection Algorithm", Image and Vision Computing, vol. 20, pp. 1–13, 2003. [27] T. Aach and A. Kaup, "Bayesian algorithms for adaptive change detection in image sequences using Markov random fields", Signal Processing: Image Communication, vol. 7, pp. 147–160, 1995. [28] J. Lan, J. Li, G. Hu, B. Ran, and L. Wang, "Vehicle Speed Measurement Based on Gray Constraint Optical Flow Algorithm," Optic, vol. 125, pp. 289-295, 2014.[M4] [29] J. Li, F. Yang, M. Tomizuka, and C. Choi "Evolvegraph: Multi-agent trajectory Prediction with Dynamic Relational Reasoning," Proceedings of the Neural Information Processing Systems (NeurIPS), Vancouver, BC, Canada. 6–12 December 2022. | ||
|
آمار تعداد مشاهده مقاله: 1,008 تعداد دریافت فایل اصل مقاله: 252 |
||