Research Article
BibTex RIS Cite

Object Detection with YOLOv7 Model on Smart Mobile Devices

Year 2023, Volume: 26 Issue: 3, 1207 - 1214, 01.10.2023

Batuhan Karadağ Ali Arı

https://doi.org/10.2339/politeknik.1296541
Cited By: 2

Abstract

The YOLOv7 model, which is one of the current object detection algorithms based on deep learning, achieved an average accuracy of 51.2% in the Microsoft COCO dataset, proving that it is ahead of other object detection methods. YOLO has been a preferred model for object detection problems in the commercial field since it was first introduced, due to its speed and accuracy. Generally, high-capacity hardware is needed to run deep learning-based systems. In this study, it is aimed to detect objects in smart mobile devices without using a graphic processor unit by activating the YOLOv7 model on the server in order to be able to detect objects in smart mobile devices, which have become one of the important tools of trade today. With the study, the YOLOv7 object detection algorithm has been successfully run on mobile devices with iOS operating system. In this way, an image taken on mobile devices or already in the gallery after any image is transferred to the server, it is ensured that the objects in the image are detected effectively in terms of accuracy and speed.

Keywords

YOLOv7 Object Detection Mobile Object Detection Mobile YOLOv7

References

  • [1] Cai Y., Li H., Yuan G., Niu W., Li Y., Tang X., Ren B. Ve Wang Y., ”YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design”, arXiv:2009.05697, (2020).
  • [2] Arı A., “Multipath feature fusion for hyperspectral image classification based on hybrid 3D/2D CNN and squeeze-excitation network”, Earth Science Informatics, 16:175–191, (2023).
  • [3] Tao J., Wang H., Zhang X., Li X. and Yang H., "An object detection system based on YOLO in traffic scene", 2017 6th International Conference on Computer Science and Network Technology (ICCSNT), Dalian, China, 2017, pp. 315-319, (2017).
  • [4] Dersuneli M. , Gündüz T. ve Kutlu Y. , "Bul-Tak Oyuncağı Şekillerinin Klasik Görüntü İşleme ve Derin Öğrenme Yöntemleri ile Tespiti", Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, c. 10, sayı. 4, ss. 1290-1303, Ara. 2021, (2021).
  • [5] Liu C., Tao T., Liang J., Li K. and Chen Y., "Object Detection Based on YOLO Network," 2018 IEEE 4th Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China, 2018, pp. 799-803, (2018).
  • [6] Girshick R., Donahue J., Darrell T. and Malik J., "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation", 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014, pp. 580-587, (2014).
  • [7] Girshick R., "Fast R-CNN," 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015, pp. 1440-1448, (2015).
  • [8] Ren S, He K, Girshick R ve Sun J. “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks”, IEEE Trans Pattern Anal Mach Intell, 2017 Jun;39(6):1137-1149, (2017).
  • [9] Liu W., Anguelov D., Erhan D., Szegedy C., Reed S., Fu C.Y. ve Berg A. C., “SSD: Single Shot MultiBox Detector” , arXiv:1512.02325, (2015).
  • [10] Redmon J., Divvala S., Girshick R. ve Farhadi A., “You Only Look Once: Unified, Real-Time Object Detection”, arXiv:1506.02640, (2015).
  • [11] Redmon J. ve Farhadi A., “YOLO9000: Better, Faster, Stronger”, arXiv:1612.08242, (2015).
  • [12] Redmon J. ve Farhadi A., “YOLOv3: An Incremental Improvement”, arXiv:1804.02767, (2018).
  • [13] Er, Ö. ve Bilge, H. Ş., "Bir Küçük Nesne Tespit Zorluğu Olarak Hava Görüntülerinden Araç Tespiti", Veri Bilimi 4 (2021) : 73-83, (2021).
  • [14] Sultana F., Sufian A. ve Dutta P., “A Review of Object Detection Models Based on Convolutional Neural Network”, arXiv:1905.01614, (2020).
  • [15] Wang C., Bochkovskiy A. ve Liao H.M., “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors”, arXiv:2207.02696, (2022).
  • [16] Donuk K., Arı A., Özdemir M.F. ve Hanbay D., “Deep Feature Selection for Facial Emotion Recognition Based on BPSO and SVM”, Politeknik Dergisi, 26(1) : 131-142, (2023).
  • [17] Karadağ B., Arı A. ve Karadağ M., “Derin Öğrenme Modellerinin Sinirsel Stil Aktarımı Performanslarının Karşılaştırılması”, Politeknik Dergisi, 24(4) : 1611-1622, (2021).
  • [18] Korkmaz Ş., Alkan M., “Derin öğrenme algoritmalarını kullanarak deepfake video tespiti”, Politeknik Dergisi, *(*): *, (*).
  • [19] Wang Y., Wang H. ve Xin Z., "Efficient Detection Model of Steel Strip Surface Defects Based on YOLO-V7", in IEEE Access, vol. 10, pp. 133936-133944, (2022).
  • [20] Jiang, K., Xie, T., Yan, R., Wen, X., Li, D., Jiang, H., Jiang, N., Feng, L., Duan, X. ve Wang, J., “An Attention Mechanism-Improved YOLOv7 Object Detection Algorithm for Hemp Duck Count Estimation”, Agriculture 2022, 12(10), 1659, (2022).
  • [21] Hossain J., “YOLOv7 explanation and implementation from scratch”, https://www.kaggle.com/code/jobayerhossain/yolov7-explanation-and-implementation-from-scratch ,(2022), Erişim Tarihi: 16.04.2023.
  • [22] Eği, Y., "YOLO V7 and Computer Vision-Based Mask-Wearing Warning System for Congested Public Areas", Journal of the Institute of Science and Technology 13, 22-32, (2023).
  • [23] Hussain M., Al-Aqrabi H., Munawar M., Hill R., Alsboui T, “Domain Feature Mapping with YOLOv7 for Automated Edge-Based Pallet Racking Inspections”, Sensors, 22(18), 6927, (2022).
  • [24] Huang G., Liu Z., Maaten L. ve Weinberger K, “Densely Connected Convolutional Networks”, arXiv:1608.06993, (2016).
  • [25] Lee Y., Hwang J., Lee S., Bae Y. ve Park J., “An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection”, arXiv:1904.09730, (2019).
  • [26] “PyTorch”, https://pytorch.org , (2016), Erişim Tarihi: 02.02.2023.
  • [27] “TensorFlow”, https://www.tensorflow.org/?hl=tr , (2015), Erişim Tarihi: 08.03.2023.
  • [28] Chau S.C., “Journey putting YOLO v7 model into TensorFlow Lite (Object Detection API) model running on Android”, https://medium.com/geekculture/journey-putting-yolo-v7-model-into-tensorflow-lite-object-detection-api-model-running-on-android-e3f746a02fc4, (2022), Erişim Tarihi: 16.03.2023.
  • [29] Kukil ve Rath S., “YOLOv7 Object Detection Paper Explanation & Inference”, https://learnopencv.com/yolov7-object-detection-paper-explanation-and-inference/ , (2022), Erişim Tarihi: 20.03.2023.
  • [30] Roboflow, “What is YOLOv7?”, https://roboflow.com/model/yolov7, (2022), Erişim Tarihi: 20.03.2023.
  • [31] Görsel 1, https://www.travelandleisure.com/thmb/Cp3v7EPYiVhuAwOO8yxYv4qUjY0=/750x0/filters:no_upscale():max_bytes(150000):strip_icc()/safari-truck-giraffes-micato-safaris-SAFARIGUIDETIPS0721-2549bb165aa34dc193cb8b6f3958654b.jpg ,Erişim Tarihi: 08.05.2023.
  • [32] Görsel 2, https://hackernoon.com/hn-images/1*anJ8xj06Q-xr6XosDF1Etw.jpeg, Erişim Tarihi: 08.05.2023.
  • [33] Görsel 3, https://www.rcp-vision.com/wp-content/uploads/2020/06/800px-Lex_Av_E_92_St_06.jpg, Erişim Tarihi: 08.05.2023.
  • [34] Görsel 4, https://hips.hearstapps.com/hmg-prod/images/kitchen-paint-colors-blue-1672376788.jpg?resize=480:*, Erişim Tarihi: 08.05.2023.

Akıllı Mobil Cihazlarda YOLOv7 Modeli ile Nesne Tespiti

Year 2023, Volume: 26 Issue: 3, 1207 - 1214, 01.10.2023

Batuhan Karadağ Ali Arı

https://doi.org/10.2339/politeknik.1296541
Cited By: 2

Abstract

Derin öğrenmeye dayalı güncel nesne tespit algoritmalarından biri olan YOLOv7 modelinin Microsoft COCO verisetinde aldığı %51.2’lik ortalama kesinlik başarısı, diğer nesne tespit yöntemlerinin ilerisinde olduğunu kanıtlamıştır. YOLO ilk sunulduğu dönemden itibaren, hız ve doğruluk açısından etkili olması sebebiyle ticari alandaki nesne tespit problemlerinde tercih edilen bir model olmuştur. Genellikle derin öğrenmeye dayalı sistemlerin çalıştırılabilmesi için yüksek kapasitede donanımlara ihtiyaç duyulmaktadır. Bu çalışmada, günümüzde ticaretin önemli araçlarından biri haline gelen akıllı mobil cihazlarda nesne tespiti yapılabilmesi için YOLOv7 modelinin sunucuda aktif edilmesi ile akıllı mobil cihazlarda grafik işlemci birimi kullanılmadan nesne tespiti yapılabilmesi amaçlanmıştır. Yapılan çalışma ile YOLOv7 nesne tespit algoritması, iOS işletim sistemine sahip mobil cihazlarda başarı ile çalıştırılmıştır. Bu sayede mobil cihazlarda çekilen bir görüntü veya halihazırda galeride bulunan herhangi bir görüntü sunucuya aktarıldıktan sonra, doğruluk ve hız açısından etkili bir şekilde görüntü içerisinde bulunan nesnelerin tespitinin gerçekleştirilmesi sağlanmıştır.

Keywords

YOLOv7 Nesne Tespiti Mobil Nesne Tespiti Mobil YOLOv7

References

  • [1] Cai Y., Li H., Yuan G., Niu W., Li Y., Tang X., Ren B. Ve Wang Y., ”YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design”, arXiv:2009.05697, (2020).
  • [2] Arı A., “Multipath feature fusion for hyperspectral image classification based on hybrid 3D/2D CNN and squeeze-excitation network”, Earth Science Informatics, 16:175–191, (2023).
  • [3] Tao J., Wang H., Zhang X., Li X. and Yang H., "An object detection system based on YOLO in traffic scene", 2017 6th International Conference on Computer Science and Network Technology (ICCSNT), Dalian, China, 2017, pp. 315-319, (2017).
  • [4] Dersuneli M. , Gündüz T. ve Kutlu Y. , "Bul-Tak Oyuncağı Şekillerinin Klasik Görüntü İşleme ve Derin Öğrenme Yöntemleri ile Tespiti", Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, c. 10, sayı. 4, ss. 1290-1303, Ara. 2021, (2021).
  • [5] Liu C., Tao T., Liang J., Li K. and Chen Y., "Object Detection Based on YOLO Network," 2018 IEEE 4th Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China, 2018, pp. 799-803, (2018).
  • [6] Girshick R., Donahue J., Darrell T. and Malik J., "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation", 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014, pp. 580-587, (2014).
  • [7] Girshick R., "Fast R-CNN," 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015, pp. 1440-1448, (2015).
  • [8] Ren S, He K, Girshick R ve Sun J. “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks”, IEEE Trans Pattern Anal Mach Intell, 2017 Jun;39(6):1137-1149, (2017).
  • [9] Liu W., Anguelov D., Erhan D., Szegedy C., Reed S., Fu C.Y. ve Berg A. C., “SSD: Single Shot MultiBox Detector” , arXiv:1512.02325, (2015).
  • [10] Redmon J., Divvala S., Girshick R. ve Farhadi A., “You Only Look Once: Unified, Real-Time Object Detection”, arXiv:1506.02640, (2015).
  • [11] Redmon J. ve Farhadi A., “YOLO9000: Better, Faster, Stronger”, arXiv:1612.08242, (2015).
  • [12] Redmon J. ve Farhadi A., “YOLOv3: An Incremental Improvement”, arXiv:1804.02767, (2018).
  • [13] Er, Ö. ve Bilge, H. Ş., "Bir Küçük Nesne Tespit Zorluğu Olarak Hava Görüntülerinden Araç Tespiti", Veri Bilimi 4 (2021) : 73-83, (2021).
  • [14] Sultana F., Sufian A. ve Dutta P., “A Review of Object Detection Models Based on Convolutional Neural Network”, arXiv:1905.01614, (2020).
  • [15] Wang C., Bochkovskiy A. ve Liao H.M., “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors”, arXiv:2207.02696, (2022).
  • [16] Donuk K., Arı A., Özdemir M.F. ve Hanbay D., “Deep Feature Selection for Facial Emotion Recognition Based on BPSO and SVM”, Politeknik Dergisi, 26(1) : 131-142, (2023).
  • [17] Karadağ B., Arı A. ve Karadağ M., “Derin Öğrenme Modellerinin Sinirsel Stil Aktarımı Performanslarının Karşılaştırılması”, Politeknik Dergisi, 24(4) : 1611-1622, (2021).
  • [18] Korkmaz Ş., Alkan M., “Derin öğrenme algoritmalarını kullanarak deepfake video tespiti”, Politeknik Dergisi, *(*): *, (*).
  • [19] Wang Y., Wang H. ve Xin Z., "Efficient Detection Model of Steel Strip Surface Defects Based on YOLO-V7", in IEEE Access, vol. 10, pp. 133936-133944, (2022).
  • [20] Jiang, K., Xie, T., Yan, R., Wen, X., Li, D., Jiang, H., Jiang, N., Feng, L., Duan, X. ve Wang, J., “An Attention Mechanism-Improved YOLOv7 Object Detection Algorithm for Hemp Duck Count Estimation”, Agriculture 2022, 12(10), 1659, (2022).
  • [21] Hossain J., “YOLOv7 explanation and implementation from scratch”, https://www.kaggle.com/code/jobayerhossain/yolov7-explanation-and-implementation-from-scratch ,(2022), Erişim Tarihi: 16.04.2023.
  • [22] Eği, Y., "YOLO V7 and Computer Vision-Based Mask-Wearing Warning System for Congested Public Areas", Journal of the Institute of Science and Technology 13, 22-32, (2023).
  • [23] Hussain M., Al-Aqrabi H., Munawar M., Hill R., Alsboui T, “Domain Feature Mapping with YOLOv7 for Automated Edge-Based Pallet Racking Inspections”, Sensors, 22(18), 6927, (2022).
  • [24] Huang G., Liu Z., Maaten L. ve Weinberger K, “Densely Connected Convolutional Networks”, arXiv:1608.06993, (2016).
  • [25] Lee Y., Hwang J., Lee S., Bae Y. ve Park J., “An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection”, arXiv:1904.09730, (2019).
  • [26] “PyTorch”, https://pytorch.org , (2016), Erişim Tarihi: 02.02.2023.
  • [27] “TensorFlow”, https://www.tensorflow.org/?hl=tr , (2015), Erişim Tarihi: 08.03.2023.
  • [28] Chau S.C., “Journey putting YOLO v7 model into TensorFlow Lite (Object Detection API) model running on Android”, https://medium.com/geekculture/journey-putting-yolo-v7-model-into-tensorflow-lite-object-detection-api-model-running-on-android-e3f746a02fc4, (2022), Erişim Tarihi: 16.03.2023.
  • [29] Kukil ve Rath S., “YOLOv7 Object Detection Paper Explanation & Inference”, https://learnopencv.com/yolov7-object-detection-paper-explanation-and-inference/ , (2022), Erişim Tarihi: 20.03.2023.
  • [30] Roboflow, “What is YOLOv7?”, https://roboflow.com/model/yolov7, (2022), Erişim Tarihi: 20.03.2023.
  • [31] Görsel 1, https://www.travelandleisure.com/thmb/Cp3v7EPYiVhuAwOO8yxYv4qUjY0=/750x0/filters:no_upscale():max_bytes(150000):strip_icc()/safari-truck-giraffes-micato-safaris-SAFARIGUIDETIPS0721-2549bb165aa34dc193cb8b6f3958654b.jpg ,Erişim Tarihi: 08.05.2023.
  • [32] Görsel 2, https://hackernoon.com/hn-images/1*anJ8xj06Q-xr6XosDF1Etw.jpeg, Erişim Tarihi: 08.05.2023.
  • [33] Görsel 3, https://www.rcp-vision.com/wp-content/uploads/2020/06/800px-Lex_Av_E_92_St_06.jpg, Erişim Tarihi: 08.05.2023.
  • [34] Görsel 4, https://hips.hearstapps.com/hmg-prod/images/kitchen-paint-colors-blue-1672376788.jpg?resize=480:*, Erişim Tarihi: 08.05.2023.
There are 34 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Research Article
Authors

Batuhan Karadağ 0000-0002-4661-6607

Ali Arı 0000-0002-5071-6790

Early Pub Date June 6, 2023
Publication Date October 1, 2023
Submission Date May 12, 2023
Published in Issue Year 2023 Volume: 26 Issue: 3

Cite

APA Karadağ, B., & Arı, A. (2023). Akıllı Mobil Cihazlarda YOLOv7 Modeli ile Nesne Tespiti. Politeknik Dergisi, 26(3), 1207-1214. https://doi.org/10.2339/politeknik.1296541
AMA Karadağ B, Arı A. Akıllı Mobil Cihazlarda YOLOv7 Modeli ile Nesne Tespiti. Politeknik Dergisi. October 2023;26(3):1207-1214. doi:10.2339/politeknik.1296541
Chicago Karadağ, Batuhan, and Ali Arı. “Akıllı Mobil Cihazlarda YOLOv7 Modeli Ile Nesne Tespiti”. Politeknik Dergisi 26, no. 3 (October 2023): 1207-14. https://doi.org/10.2339/politeknik.1296541.
EndNote Karadağ B, Arı A (October 1, 2023) Akıllı Mobil Cihazlarda YOLOv7 Modeli ile Nesne Tespiti. Politeknik Dergisi 26 3 1207–1214.
IEEE B. Karadağ and A. Arı, “Akıllı Mobil Cihazlarda YOLOv7 Modeli ile Nesne Tespiti”, Politeknik Dergisi, vol. 26, no. 3, pp. 1207–1214, 2023, doi: 10.2339/politeknik.1296541.
ISNAD Karadağ, Batuhan - Arı, Ali. “Akıllı Mobil Cihazlarda YOLOv7 Modeli Ile Nesne Tespiti”. Politeknik Dergisi 26/3 (October 2023), 1207-1214. https://doi.org/10.2339/politeknik.1296541.
JAMA Karadağ B, Arı A. Akıllı Mobil Cihazlarda YOLOv7 Modeli ile Nesne Tespiti. Politeknik Dergisi. 2023;26:1207–1214.
MLA Karadağ, Batuhan and Ali Arı. “Akıllı Mobil Cihazlarda YOLOv7 Modeli Ile Nesne Tespiti”. Politeknik Dergisi, vol. 26, no. 3, 2023, pp. 1207-14, doi:10.2339/politeknik.1296541.
Vancouver Karadağ B, Arı A. Akıllı Mobil Cihazlarda YOLOv7 Modeli ile Nesne Tespiti. Politeknik Dergisi. 2023;26(3):1207-14.

Cited By

Real-Time Scalable System For Face Tracking In Multi-Camera
Journal of Polytechnic
https://doi.org/10.2339/politeknik.1332952
Heatmap creation with YOLO-Deep SORT system customized for in-store customer behavior analysis
Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering
https://doi.org/10.33769/aupse.1378578

 download This work is licensed under Creative Commons Attribution-ShareAlike 4.0 International.