Resource-efficient Reconfigurable Computer-on-Module for Embedded Vision Applications
D. Klimeck, H.G. Meyer, J. Hagemeyer, M. Porrmann, U. Ruckert, in: Institute of Electrical and Electronics Engineers (Ed.), 2018 IEEE 29th International Conference on Application-Specific Systems, Architectures and Processors (ASAP), IEEE, 2018, pp. 1–4.
Download (ext.)
Konferenzbeitrag
| Veröffentlicht
| Englisch
Autor*in
Klimeck, Daniel;
Meyer, Hanno Gerd ;
Hagemeyer, Jens;
Porrmann, Mario;
Ruckert, Ulrich
herausgebende Körperschaft
Institute of Electrical and Electronics Engineers
Abstract
The paper proposes a novel architecture for a highly customisable FPGA-SoC-based Computer-on-Module (CoM) targeting embedded vision applications. Apart from a Xilinx Zynq SoC, the module integrates an Adapteva Epiphany floating point accelerator in a Toradex Apalis compliant form factor. The CoM has been successfully integrated into two robot platforms to enhance their vision processing capabilities. For evaluation, visually-guided collision avoidance and navigation has been implemented, mimicking the behaviour of insects. The hardware/software partitioning is presented together with a comparison to an HLS-based solution for the given application. The proposed stream-based FPGA implementation achieves a speedup of 721 and an increase in energy efficiency by a factor of 800 compared to an OpenCV-based implementation on one of the embedded ARM processors of the Zynq SoC.
Erscheinungsjahr
Titel des Konferenzbandes
2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP)
Seite
1-4
Konferenz
2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP)
Konferenzort
Milan
Konferenzdatum
2018-07-10 – 2018-07-12
FH-PUB-ID
Zitieren
Klimeck, Daniel ; Meyer, Hanno Gerd ; Hagemeyer, Jens ; Porrmann, Mario ; Ruckert, Ulrich: Resource-efficient Reconfigurable Computer-on-Module for Embedded Vision Applications. In: Institute of Electrical and Electronics Engineers (Hrsg.): 2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP) : IEEE, 2018, S. 1–4
Klimeck D, Meyer HG, Hagemeyer J, Porrmann M, Ruckert U. Resource-efficient Reconfigurable Computer-on-Module for Embedded Vision Applications. In: Institute of Electrical and Electronics Engineers, ed. 2018 IEEE 29th International Conference on Application-Specific Systems, Architectures and Processors (ASAP). IEEE; 2018:1-4. doi:10.1109/ASAP.2018.8445091
Klimeck, D., Meyer, H. G., Hagemeyer, J., Porrmann, M., & Ruckert, U. (2018). Resource-efficient Reconfigurable Computer-on-Module for Embedded Vision Applications. In Institute of Electrical and Electronics Engineers (Ed.), 2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP) (pp. 1–4). Milan: IEEE. https://doi.org/10.1109/ASAP.2018.8445091
@inproceedings{Klimeck_Meyer_Hagemeyer_Porrmann_Ruckert_2018, title={Resource-efficient Reconfigurable Computer-on-Module for Embedded Vision Applications}, DOI={10.1109/ASAP.2018.8445091}, booktitle={2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP)}, publisher={IEEE}, author={Klimeck, Daniel and Meyer, Hanno Gerd and Hagemeyer, Jens and Porrmann, Mario and Ruckert, Ulrich}, editor={Institute of Electrical and Electronics EngineersEditor}, year={2018}, pages={1–4} }
Klimeck, Daniel, Hanno Gerd Meyer, Jens Hagemeyer, Mario Porrmann, and Ulrich Ruckert. “Resource-Efficient Reconfigurable Computer-on-Module for Embedded Vision Applications.” In 2018 IEEE 29th International Conference on Application-Specific Systems, Architectures and Processors (ASAP), edited by Institute of Electrical and Electronics Engineers, 1–4. IEEE, 2018. https://doi.org/10.1109/ASAP.2018.8445091.
D. Klimeck, H. G. Meyer, J. Hagemeyer, M. Porrmann, and U. Ruckert, “Resource-efficient Reconfigurable Computer-on-Module for Embedded Vision Applications,” in 2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP), Milan, 2018, pp. 1–4.
Klimeck, Daniel, et al. “Resource-Efficient Reconfigurable Computer-on-Module for Embedded Vision Applications.” 2018 IEEE 29th International Conference on Application-Specific Systems, Architectures and Processors (ASAP), edited by Institute of Electrical and Electronics Engineers, IEEE, 2018, pp. 1–4, doi:10.1109/ASAP.2018.8445091.