Deep Learning RetinaNet based Car Detection for Smart Transportation Network

IRMA AMELIA DEWI, LISA KRISTIANA, ARSYAD RAMADHAN DARLIS, REZA FADILAH DWIPUTRA

Sari


ABSTRAK

Deteksi objek yang merupakan salah satu bagian utama dari sistem Smart Transportasion Network (STN) diajukan pada penelitian ini. Penelitian ini menggunakan salah satu model STN yaitu Infrastructure-to-Vehicle (I2V), dimana sistem ini bekerja dengan mendeteksi kendaraan mobil menggunakan model arsitektur RetinaNet dengan backbone Resnet101 dan FPN (Feature Pyramid Network), kemudian hasil deteksi mentrigger VLC transmitter yang terpasang di lampu penerangan jalan mengirimkan sinyal informasi menuju VLC receiver yang dipasang di mobil. Pada tahap proses training, jumlah dataset mobil yang digunakan adalah sekitar 1600 image dan 400 validation image serta pengulangan proses sebanyak 100 epoch. Berdasarkan 50 kali pengujian pada image test, diperoleh nilai precision mencapai 86%, nilai recall mencapai 85% dan f1-score mencapai 84%.

Kata kunci: Object detection, RetinaNet, Resnet101, STN, VLC, I2V

 

ABSTRACT

Object detection is one of the main part in Smart Transportation Network (STN) system proposed in this research. This research used one of the STN models, namely Infrastructure-to-Vehicle (I2V), a system works by detecting car using RetinaNet architecture model with ResNet 101 and FPN (Feature Pyramid Network) as backbone, then the detection result triggers VLC transmitter set up on the street lighting to transmit information signal to the VLC receiver which set up in the car. At the training process stage, the number of car datasets is approximately 1600 images, 400 validation images and repetition of processes about 100 epochs. Based on the 50 times testing process on a image test, it is obtained 86% of a precision value, by reaching 85% of recall value, and 84% of f1-score.

Keywords: Object detection, RetinaNet, Resnet101, STN, VLC, I2V


Kata Kunci


Object detection; RetinaNet; Resnet101; STN; VLC; I2V

Teks Lengkap:

PDF

Referensi


Arcos-Garcia, A., Alvarez-Garcia, J., & Soria-Morillo, L. (2018). Evaluation of Deep Neural Networks for traffic sign detection systems. Elsevier, (pp. 332-344).

Biswasa, D., Su, H., Wang, C., Stevanovic, A., & Wang, W. (2018). An automatic traffic density estimation using Single Shot Detection (SSD). Elsevier Ltd.

Dai, J., Li, Y., He, K., & Sun, J. (2016). R-FCN: Object Detection via Region-based Fully Convolutional Networks. arXiv:1605.06409v2 [cs.CV].

Darlis, A. R., Cahyadi, W. A., & Chung, Y.-H. (2018). Shore-To-Undersea Visible Light Communication. Wireless Personal Communications, 99(2), 681–694.

Darlis, A. R., Lidyawati, L., & Jambola, L. (2018). Color Filter Identification For Bidirectional Visible Light Communication. Elkomika: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika, 6(2), 303.

Darlis, A. R., Lidyawati, L., & Nataliana, D. (2013). Implementasi Visible Light Communication (VLC) Pada Sistem Komunikasi. Elkomika: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika, 1(1),13 – 25.

Darlis, A. R., Lidyawati, L., Nataliana, D., & Wulandari, N. (2014). Implementasi Sistem Komunikasi Video menggunakan Visible Light Communication (VLC). Jurnal Reka Elkomika, 2(3), 160 – 173.

Ding, X., Lin, Z., He, F., Wang, Y., & Huang, Y. (2018). A Deeply- Recursive Convolutional Network for Crowd Counting. arXiv:1805.05633v1.

Foley, D., & O'Reilly, R. (2015). An Evaluation of Convolutional Neural Network Models for Object Detection in Images on Low-End Devices. CEUR Workshop Proceedings, Vol-2259. Paris.

He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition. CVPR, pg.770-778.

Hoang, T. M., Nguyen, P. H., Truong, N. Q., Lee, Y. W., & Park, K. R. (2019). Deep RetinaNet-Based Detection and Classification of Road Markings by Visible Light Camera Sensors. MDPI-Sensors, 19, 281.

Hsu, S.-C., Huang, C.-L., & Chuang, C.-H. (2018). Vehicle Detection using Simplified Fast RCNN. Chiang Mai: IEEE.

Kristiana, L., Schmitt, C., & Stiller, B. (2017a). Evaluation of inter-vehicle connectivity in threedimensional cases. Wireless Days, 2017. Porto, Portugal: IEEE.

Kristiana, L., Schmitt, C., & Stiller, B. (2017b). Application of an enhanced V2VUNet in a complex three-dimensional inter-vehicular communication scenario. IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob). Bandung, Indonesia: IEEE.

Kristiana, L., Schmitt, C., & Stiller, B. (2017c). The evaluation of a predictive forwarding scheme in three-dimensional vehicular communication scenarios. International Conference on Selected Topics in Mobile and Wireless Networking (MoWNeT). Avignon, France: IEEE.

Kristiana, L., Schmitt, C., & Stiller, B. (2017d). The Evaluation of the V2VUNet Concept to Improve Inter-vehicle Communications. IFIP International Conference on Autonomous Infrastructure, Management and Security. Springer.

Lin, T.-Y., Dollar, P., & Girshick, R. (2017). Feature Pyramid Networks for Object Detection. arXiv:1612.03144v2 [cs.CV].

Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Doll´ar, P. (2018). Focal Loss for Dense Object Detection. arXiv:1708.02002v2.

Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, Alex, C.-Y., & Berg, A. (2016). SSD: Single Shot MultiBox Detector. Springer.

loffe, S., & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv:1502.03167v3 [cs.LG].

Milton, M. A. (2018). Towards Pedestrian Detection Using RetinaNet in ECCV 2018 Wider Pedestrian Detection Challenge. arXiv:1902.01031, 225-228. Diambil kembali dari arXiv.org.

Munir, R. (2004). Konvolusi dan Transformasi Fourier. Dalam Pengolahan Citra Digital (pp.61). Bandung: Informatika.

Nguyen, K., Ross, A., Fookes, C., & Sridharan, S. (2017). Iris Recognition With Off-the-Shelf CNN Features: A Deep Learning Perspective. 6.

Redmon, J., & Farhadi, A. (2017). YOLO9000: Better, Faster, Stronger. Honolulu: IEEE.

Ren, S., He, K., Girshick, R., & Sun, J. (2016). Faster R-CNN: Towards Real-Time Object Detection. arXiv:1506.01497.

Szeliski, R. (2011). Computer vision algorithms and applications. (pp. 10–17). London: Spinger.

Tang, S., & Yuan, Y. (2015). Object Detection based on Convolutional Neural Network. Stanford University. California.

Udacity. (2018). Self Driving Car. Mountain View: Github.

Wang, Y., Wang, C., Zhang, H., Dong, Y., & Wei, S. (2019). Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 Imagery. MDPI-Remote Sensing, 11.




DOI: https://doi.org/10.26760/elkomika.v7i3.570

Refbacks

  • Saat ini tidak ada refbacks.


_______________________________________________________________________________________________________________________

ISSN (cetak) : 2338-8323   |  ISSN (elektronik) : 2459-9638    

diterbitkan oleh :

Teknik Elektro Institut Teknologi Nasional Bandung

Alamat : Gedung 20 Jl. PHH. Mustofa 23 Bandung 40124

Kontak : Tel. 7272215 (ext. 206)  Fax. 7202892

Surat Elektronik jte.itenas@itenas.ac.id

_________________________________________________________________________________________________________________________

Terindeks 

index copernicus

________________________________________________________________________________________________________________________

Statistik Pengunjung 

Free counters!

 Web
Analytics Made Easy - StatCounter

Lihat Statistik Jurnal

Jurnal ini terlisensi oleh Creative Commons Attribution-ShareAlike 4.0 International License.

Creative Commons License