ABSTRACT
Image processing pipelines involved in detecting markers from real-time video employ contour detection algorithms. Field Programmable Gate Arrays (FPGA) can provide greater computing power due to parallel processing and pipelining of the different stages in these algorithms. However, FPGA implementation of different contour detection methods remains challenging due to resource limitation and timing constraints. In this work a novel approach for a complete pipeline has been presented based on FPGA. The method used for the detection of fiducial markers from real-time video streams is based on a single-scan approach. Implementation of such pipeline into reconfigurable technology is specially challenging compared to software-oriented implementation as pointers, dynamic structures, efficient use of resources, etc. need to be considered. A driver is the need to fit the design into low-cost reconfigurable devices. To help face the related challenges of a hardware implementation High Level Synthesis (HLS) technology has been adopted, which implies reengineering of the reference algorithms. The results show a successful detection of markers over a dataset acquired in a controlled indoor environment with different resolutions at different distances. The proposal has been prototyped and tested on a Zedboard with Xilinx Zynq®-7000 SoC.
- Schoun, B., Oagaz, H., Choi, M.H. 2021. Corner-based square fiducial marker detection for hand-manipulated AR objects. In Proceedings of the IEEE International Conference on Intelligent Reality (ICIR). IEEE. doi: 10.1109/ICIR51845.2021.00014Google ScholarCross Ref
- Oliveira J. A., Piardi, L., Giometti, E. B., Leitao, P. 2021. Improving the mobile robots indoor localization system by combining SLAM with fiducial markers. In: 2021 Latin American Robotic Symposium (LARS), 2021 Brazilian Symposium on Robotics (SBR). IEEE. doi: 10.1109/LARS/SBR/WRE54079.2021.9605456Google Scholar
- Annusewicz, A., Zwierzchowski, J. 2020. Marker detection algorithm for the navigation of a mobile robot. In Proceedings of the 27th International Conference - Mixed Design of Integrated Circuits and Systems 2020, Poland, pp. 223-226. IEEE Xplore. doi: 10.23919/mixdes49814.2020.9155658Google ScholarCross Ref
- Liu, Y., Schofield, H., Shan, J. 2021. Navigation of a self-driving vehicle using one fiducial marker. In: 2021 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. IEEE. doi: 10.1109/MFI52462.2021.9591194Google ScholarCross Ref
- Attard, L., Debono, C.J., Valentino, G., Castro, M., Tambutti, M.L.B. 2018. An RGB-D video-based wire detection tool to aid robotic arms during machine alignment measurement. In: Proceedings of the IST 2018 - IEEE International Conference on Imaging Systems and Techniques. IEEE. doi: 10.1109/IST.2018.8577199Google ScholarDigital Library
- Khazetdinov, A., Zakiev, A., Tsoy, T., Svinin, M., Magid, E. 2021. Embedded ArUco: a novel approach for high precision UAV landing. In: 2021 International Siberian Conference on Control and Communications (SIBCON). IEEE.Google ScholarCross Ref
- Zhang, X., Jiang, J., Fang, Y 2019. Enhanced fiducial marker based precise landing for quadrotors. In Proceedings of the 2019 IEEE-ASME International Conference on Advanced Intelligent Mechatronics, Hong Kong, China. IEEE. doi: 10.1109/AIM.2019.8868532Google ScholarDigital Library
- Acuna, R., Li, Z., Volker, W. 2018. MOMA: Visual Mobile Marker Odometry. In: 2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN), France, IEEE. doi: 10.1109/IPIN.2018.8533685Google Scholar
- Truong, V.T., Lao, J.S., Huang, C.C. 2020. Multi-camera marker-based real-time head pose estimation system. In: 2020 International Conference on Multimedia Analysis and Pattern Recognition, MAPR. IEEE. doi: 10.1109/MAPR49794.2020.9237775Google ScholarCross Ref
- Romero-Ramirez, F. J., Muñoz-Salinas, R., Medina-Carnicer, R. 2019. Fractal Markers: a new approach for long-range marker pose estimation under occlusion. IEEE Access, vol. 7, IEEE. doi: 10.1109/ACCESS.2019.2951204Google Scholar
- Wang, Y., Ji, Y. Liu, D. Tamura, Y. 2020. ACMarker: acoustic camera-based fiducial marker system in underwater environment. In: IEEE Robotics and Automation Letters, vol. 5 (6), pp. 5018-5025. IEEE. doi: 10.1109/LRA.2020.3005375Google ScholarCross Ref
- Romero-Ramirez, F. J., Muñoz-Salinas, R., Medina-Carnicer, R. 2018.Speeded up detection of squared fiducial markers.In: Image and Vision Computing, vol. 76, pp. 38–47, Aug. 2018. doi: 10.1016/j.imavis.2018.05.004Google ScholarCross Ref
- Garrido-Jurado, S., Muñoz-Salinas, R., Madrid-Cuevas, F. J., Marin-Jimenez, M. J. 2014. Automatic generation and detection of highly reliable fiducial markers under occlusion. In: Pattern Recognition, vol. 47 (6), pp. 2280–2292. Elsevier. doi: https://doi.org/10.1016/j.patcog.2014.01.005Google ScholarDigital Library
- Hajjami, J., Caracotte, J., Caron, G., Napoleon, T. 2020. ArUcOmni: detection of highly reliable fiducial markers in panoramic images. In: 2020 IEEE-CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE. doi:10.1109/CVPRW50498.2020.00325Google ScholarCross Ref
- He, L., Ren, X., Gao, Q., Zhao, X., Yao, B., Chao, Y. 2017. The connected-component labeling problem: A review of state-of-the-art algorithms. In: Journal of Pattern Recognition, Vol. 70, pp. 25–43. Elsevier. doi:10.1016/j.patcog.2017.04.018Google ScholarDigital Library
- Cabaret, L., Lacassagne, L., Oudni, L. 2015. A review of world's fastest connected component labeling algorithms: Speed and energy estimation. In: Conference on Design and Architectures for Signal and Image Processing (DASIP). IEEE. doi:10.1109/DASIP.2014.7115641Google Scholar
- Benkrid, K., Sukhsawas, S., Crookes, D. 2003. An FPGA-based image connected component labeler. In: Lecture Notes in Computer Science, vol. 2778, pp. 1012-1015. Springer. doi: 10.1007/978-3-540-45234-8_108Google Scholar
- Jablonski, M., Gorgon, M. 2004. Handel-C implementation of classical component labelling algorithm. In: Euromicro Symposium on Digital System Design,DSD, IEEE. doi: 10.1109/DSD.2004.1333301Google ScholarCross Ref
- Appiah, K., Hunter, A., Dickinson, P., Owens, J. 2008. A run-length based connected component algorithm for FPGA implementation. In Proceedings of the 2008 International Conference on Field-Programmable Technology, ICFPT 2008, pp. 177-184. IEEE. doi: 10.1109/FPT.2008.4762381Google ScholarCross Ref
- Zhou, H., Dou, R., Cheng, L., Liu, J., Wu, N. 2022. A provisional labels-reduced, real-time connected component labeling algorithm for edge hardware. In: IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 69 (6), pp. 2997-3001. IEEE. doi:10.1109/tcsii.2022.3152783Google ScholarCross Ref
- Schwenk, K., Huber, F. 2015. Connected component labeling algorithm for very complex and high-resolution images on an FPGA platform. In Proceedings of the SPIE High-Performance Computing in Remote Sensing, vol. 964603, pp. 964603-02, SPIE. doi:10.1117/12.2194101Google Scholar
- Appiah, K., Hunter, A., Dickinson, Meng, H. 2010. Accelerated hardware video object segmentation: From foreground detection to connected components labeling. In: Computer Vision and Image Understanding, vol. 114, pp. 1282–1291. Elsevier. doi: 10.1016/j.cviu.2010.03.021Google ScholarDigital Library
- Zhao, C., Gao, W., Nie, Fe. 2020.A memory-efficient hardware architecture for connected component labeling in embedded system. In: IEEE Transactions on Circuits and Systems for Video Technology, vol. 30 (9), IEEE. doi: 10.1109/TCSVT.2019.2937189Google ScholarDigital Library
- Bailey, D. G., Klaiber, M. J. 2019.Zig-zag based single-pass connected components analysis. In: Journal of Imaging, vol. 5 (4). MDPI. doi: 10.3390/jimaging5040045Google ScholarCross Ref
- Tang, J.W., Shaikh-Husin, N., Sheikh, U. U., Marsono, M. N. 2018. A linked list run-length-based single-pass connected component analysis for real-time embedded hardware, In: ACM Journal of Real-Time Image Processing, vol. 15 (1), pp. 197-215. Springer. doi: 10.1007/s11554-016-0590-2Google ScholarDigital Library
- Klaiber, M. J. Bailey, D. G. Baroud, Y. O. Simon, S. 2016. A resource-efficient hardware architecture for connected component analysis, In: IEEE Transactions on Circuits and Systems for Video Technology, vol. 26 (7), pp. 1334-1349. IEEE. doi: 10.1109/TCSVT.2015.2450371Google ScholarDigital Library
- Zhao, F., Zhang L. H., Zhi, Y. Z.. 2013. Real-time single-pass connected components analysis algorithm, In: EURASIP Journal on Image and Video Processing, vol. 2013, pp. 1-10. Springer. doi: 10.1186/1687-5281-2013-21Google Scholar
- Bailey, D. G. 2010. Chain coding streamed images through crack run-length encoding, In: 25th International Conference Image and Vision Computing New Zealand, IEEE. doi: 10.1109/IVCNZ.2010.6148812Google ScholarCross Ref
- Johnston, C.T. Bailey, D. G. 2008. FPGA implementation of a single pass connected components algorithm, In: Proceedings - 4th IEEE International Symposium on Electronic Design, Test and Applications, DELTA 2008, pp. 228-231. IEEE. doi: 10.1109/DELTA.2008.21Google ScholarCross Ref
- Trein, J., Schwarzbacher, A. Th., Hoppe, B., Noffz, K.-H., Trenschel, T. 2007. Development of a FPGA based real-time blob analysis circuit. In: Irish Signals and Systems Conference (ISSC), Derry, UK (2007), pp. 121–126.Google Scholar
Recommendations
Model-Based Design of Flexible and Efficient LDPC Decoders on FPGA Devices
AbstractAdvances in digital communication advocate for the use of hardware LDPC decoders in applications requiring reliable and fast information transfer. Hand-coded RTL architectures provide the highest performances but slower the path to IP design. By ...
SIFT Keypoint Descriptor Matching Algorithm: A Fully Pipelined Accelerator on FPGA(Abstract Only)
FPGA '18: Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate ArraysScale Invariant Feature Transform (SIFT) algorithm is one of the classical feature extraction algorithms that is well known in Computer Vision. It consists of two stages: keypoint descriptor extraction and descriptor matching. SIFT descriptor matching ...
Real-time embedded systems powered by FPGA dynamic partial self-reconfiguration: a case study oriented to biometric recognition applications
This work aims to pave the way for an efficient open system architecture applied to embedded electronic applications to manage the processing of computationally complex algorithms at real-time and low-cost. The target is to define a standard ...
Comments