Electronics and Telecommunications Trends (전자통신동향분석)

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Trends in Low-Power On-Device Vision SW Framework Technology

저전력 온디바이스 비전 SW 프레임워크 기술 동향

  • 이문수 (고성능디바이스SW연구실) ;
  • 배수영 (고성능디바이스SW연구실) ;
  • 김정시 (고성능디바이스SW연구실) ;
  • 석종수 (고성능디바이스SW연구실)
  • Published : 2021.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

Many computer vision algorithms are computationally expensive and require a lot of computing resources. Recently, owing to machine learning technology and high-performance embedded systems, vision processing applications, such as object detection, face recognition, and visual inspection, are widely used. However, on-devices need to use their resources to handle powerful vision works with low power consumption in heterogeneous environments. Consequently, global manufacturers are trying to lock many developers into their ecosystem, providing integrated low-power chips and dedicated vision libraries. Khronos Group-an international standard organization-has released the OpenVX standard for high-performance/low-power vision processing in heterogeneous on-device systems. This paper describes vision libraries for the embedded systems and presents the OpenVX standard along with related trends for on-device vision system.

Keywords

References

  1. H. Andrade et al., "Software deployment on heterogeneous platforms: A systematic mapping study," IEEE Trans. Softw. Eng. Aug. 2019. https://doi.org/10.1109/tse.2001.908956
  2. Z. Zheng et al., "HiWayLib: A software framework for enabling high performance communications for heterogeneous pipeline computations," in Proc. ASPLOS, New York, NY, USA, Apr. 2019, pp. 153-166.
  3. S. Aldegheri et al., "Rapid prototyping of embedded vision systems: Embedding computer vision applications into low-power heterogeneous architectures," in Proc. Int. Symp. Rapid Syst. Prototyp. Turin, Italy, Oct. 2018. pp. 63-69.
  4. ML Group, "Speed up your AI designs with dedicated Arm machine learning hardware," Arm Tech Symposia, 2018.
  5. G. Jo et al., "OpenCL framework for ARM processors with NEON support," in Proc. Workshop Program. Models SIMD/Vector Process. Orlando, FL, USA, Feb. 2014. pp. 33-40.
  6. D. Sun et al., "Enabling embedded inference engine with ARM compute library: A case study," arXiv preprint, CoRR, 2017, arXiv:1704.03751
  7. Qualcomm Technologies, Inc, "Qualcomm hexagon DSP: An architecture optimized for mobile multimedia," 2013.
  8. Khronos Group, https://www.khronos.org/
  9. E. Rainey et al., "Addressing system-level optimization with OpenVX graphs," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops, Columbus, OH, USA, Jun. 2014. pp. 644-649.
  10. Khronos Group, OpenVX Specification ver. 1.3, Aug. 2019, https://www.khronos.org/registry/OpenVX/
  11. Nvidia VisionWorks, https://developer.nvidia.com/embedded/visionworks
  12. M. Qasaimeh et al., "Comparing energy efficiency of CPU, GPU and FPGA implementations for vision kernels," in Proc. Int. Conf. Embed. Softw. Syst. Las Vegas, NV, USA, June 2019.