자료유형 | 학위논문 |
---|---|
서명/저자사항 | Holistic Optimization of Embedded Computer Vision Systems. |
개인저자 | Buckler, Mark Andrew. |
단체저자명 | Cornell University. Electrical and Computer Engineering. |
발행사항 | [S.l.]: Cornell University., 2019. |
발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2019. |
형태사항 | 148 p. |
기본자료 저록 | Dissertations Abstracts International 81-04B. Dissertation Abstract International |
ISBN | 9781088393147 |
학위논문주기 | Thesis (Ph.D.)--Cornell University, 2019. |
일반주기 |
Source: Dissertations Abstracts International, Volume: 81-04, Section: B.
Advisor: Sampson, Adrian. |
이용제한사항 | This item must not be sold to any third party vendors. |
요약 | Despite strong interest in embedded computer vision, the computational demands of Convolutional Neural Network (CNN) inference far exceed the resources available in embedded devices. Thankfully, the typical embedded device has a number of desirable properties that can be leveraged to significantly reduce the time and energy required for CNN inference. This thesis presents three independent and synergistic methods for optimizing embedded computer vision: 1) Reducing the time and energy needed to capture and preprocess input images by optimizing the image capture pipeline for the needs of CNNs rather than humans. 2) Exploiting temporal redundancy within incoming video streams to perform computationally cheap motion estimation and compensation in lieu of full CNN inference for the majority of frames. 3) Leveraging the sparsity of CNN activations within the frequency domain to significantly reduce the number of operations needed for inference. Collectively these techniques significantly reduce the time and energy needed for computer vision at the edge, enabling a wide variety of exciting new applications. |
일반주제명 | Computer science. Computer engineering. Artificial intelligence. |
언어 | 영어 |
바로가기 |
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |