[-] Show simple item record

dc.contributor.advisorHe, Zhihaieng
dc.contributor.authorZhang, Zhieng
dc.date.issued2018eng
dc.date.submitted2018 Falleng
dc.description.abstractDespite being a core topic for more than several decades, object detection is still receiving increasing attentions due to its irreplaceable importance in a wide variety of applications. Abundant object detectors based on deep neural networks have shown significantly revamped accuracies in recent years. However, it's still the day one for these models to be effectively deployed to real world. In this dissertation, we focus on object detection models which tackle real world problems that are unavailable few years ago. We also aim at making object detectors on the go, which means detectors are not longer required to be run on workstations and cloud services which is latency unfriendly. To achieve these goals, we addressed the problem in two phases: application and deployment. We have done thoughtful research on both areas. Our contribution involves inter-frame information fusing, model knowledge distillation, advanced model flow control for progressive inference, and hardware oriented model design and optimization. More specifically, we proposed a novel cross-frame verification scheme for spatial temporal fused object detection model for sequential images and videos in a proposal and reject favor. To compress model from a learning basis and resolve domain specific training data shortage, we improved the learning algorithm to handle insufficient labeled data by searching for optimal guidance paths from pre-trained models. To further reduce model inference cost, we designed a progressive neural network which run in flexible cost enabled by RNN style decision controller during runtime. We recognize the awkward model deployment problem, especially for object detection models that require excessive customized layers. In response, we propose to use end-to-end neural network which use pure neural network components to substitute traditional post-processing operations. We also applied operator decomposition and graph level and on-device optimization towards real-time object detection on low power edge devices. All these works have achieved state-of-the-art performances and converted to successful applications.eng
dc.description.bibrefIncludes bibliographical references.eng
dc.format.extentxi, 127 pages : illustrationseng
dc.identifier.urihttps://hdl.handle.net/10355/67715
dc.identifier.urihttps://doi.org/10.32469/10355/67715eng
dc.languageEnglisheng
dc.publisherUniversity of Missouri--Columbiaeng
dc.relation.ispartofcommunityUniversity of Missouri--Columbia. Graduate School. Theses and Dissertationseng
dc.rightsOpenAccess.eng
dc.rights.licenseThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 License.eng
dc.titleTowards real-time object detection on edge with deep neural networkseng
dc.typeThesiseng
thesis.degree.disciplineElectrical and computer engineering (MU)eng
thesis.degree.grantorUniversity of Missouri--Columbiaeng
thesis.degree.levelDoctoraleng
thesis.degree.namePh. D.eng


Files in this item

[PDF]

This item appears in the following Collection(s)

[-] Show simple item record