Abstract
The use of smart cameras on highways has increased to monitor traffic variables such as density, speed, and flow of vehicles and to prevent car accidents. Many current systems can become expensive due to the high demand for resources since large amounts of data must be processed. Other systems only store the video and perform the processing offline. In this work, it is presented the development of a system that performs the processing using a heterogeneous architecture based on FPGA to achieve a real-time implementation due to hardware acceleration and low power consumption. The implementation of the model obtained with SSD MobilenetV2 in the Ultra96V2 achieved a rate of 23 FPS only in detection and 18 FPS adding vehicle counting, tracking, and display on a monitor.
Supported by investigation group AE &CC COL0053581.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Zaidi, S.S.A., et al.: A survey of modern deep learning based object detection models. Dig. Signal Process. 126 (2022). https://doi.org/10.1016/j.dsp.2022.103514.226
Yuan, T., et al.: Machine learning for next-generation intelligent transportation systems: a survey. Trans. Emerg. Telecommun. Technol. 33, e4427 (2022). https://doi.org/10.1002/ett.4427
Yang, Z., Pun-Cheng, L.S.: Vehicle detection in intelligent transportation systems and its applications under varying environments: a review. Image Vision Comput. 69, 143–154 (2018). https://doi.org/10.1016/j.imavis.2017.09.008
Khazukov, K., et al.: Real-time monitoring of traffic parameters. J. Big Data 7 (2020). https://doi.org/10.1186/s40537-020-00358-x.158
Butilă, E.V., Boboc, R.G.: Urban traffic monitoring and analysis using unmanned aerial vehicles (uavs): a systematic literature review. Remote Sens. 14 (2022). https://doi.org/10.3390/rs14030620.130
Song, H., Liang, H., Li, H., Dai, Z., Yun, X.: Vision-based vehicle detection and counting system using deep learning in highway scenes. Eur. Transp. Res. Rev. 11(1), 1–16 (2019). https://doi.org/10.1186/s12544-019-0390-4
Gomaa, A., et al.: Faster cnn-based vehicle detection and counting strategy for fixed camera scenes. Multimedia Tools Appl. (2022). https://doi.org/10.1007/s11042-022-12370-9.148
Srivastava, S., et al.: A survey of deep learning techniques for vehicle detection from uav images. J. Syst. Arch. 117 (2021). https://doi.org/10.1016/j.sysarc.2021.102152.206
Tayara, H., et al.: Vehicle detection and counting in high-resolution aerial images using convolutional regression neural network. IEEE Access 6, 2220–2230 (2018). https://doi.org/10.1109/ACCESS.2017.2782260
Wang, J., Gu, S.: FPGA implementation of object detection accelerator based on Vitis-AI. In: 2021 11th International Conference on Information Science and Technology (ICIST), pp. 571–577 (2021). https://doi.org/10.1109/ICIST52614.2021.9440554
Chen, L., et al.: Surrounding vehicle detection using an fpga panoramic camera and deep cnns. IEEE Trans. Intell. Transp. Syst. 21(12), 5110–5122 (2020). https://doi.org/10.1109/TITS.2019.2949005
Li, S., Luo, Y., Sun, K., Yadav, N., Choi, K.K.: A novel fpga accelerator design for real-time and ultra-low power deep convolutional neural networks compared with titan x gpu. IEEE Access 8, 105455–105471 (2020). https://doi.org/10.1109/ACCESS.2020.3000009
Acknowledgment
This study was supported by the Automática, Electrónica y Ciencias Computacionales (AE &CC) Group COL0053581, at the Sistemas de Control y Robótica Laboratory, attached to the Instituto Tecnológico Metropolitano (ITM). The work was developed in project “Sistema de visión artificial inteligente con aceleración por hardware para aplicaciones IoT industriales” with code P20223 co-funded by ITM and FLY NORTH SAS.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Uribe-Rios, J., Castano-Londono, L., Marquez-Viloria, D., Morantes-Guzman, L. (2022). Vehicle Detection and Counting Framework in Aerial Images Based on SoC-FPGA. In: Figueroa-García, J.C., Franco, C., Díaz-Gutierrez, Y., Hernández-Pérez, G. (eds) Applied Computer Sciences in Engineering. WEA 2022. Communications in Computer and Information Science, vol 1685. Springer, Cham. https://doi.org/10.1007/978-3-031-20611-5_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-20611-5_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20610-8
Online ISBN: 978-3-031-20611-5
eBook Packages: Computer ScienceComputer Science (R0)