Embedded development of aI-based computer vision:  Acceleration on intel myriad X VPU

Μηναΐδης, Παναγιώτης; Minaidis, Panagiotis

dc.contributor.author	Μηναΐδης, Παναγιώτης	el
dc.contributor.author	Minaidis, Panagiotis	en
dc.date.accessioned	2022-05-25T08:03:42Z
dc.date.available	2022-05-25T08:03:42Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/55199
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.22897
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/gr/	*
dc.subject	Heterogeneous architectures	en
dc.subject	Embedded systems	en
dc.subject	Myriad X	en
dc.subject	Computer vision	en
dc.subject	Convolutional neural networks	en
dc.subject	Ετερογενείς αρχιτεκτονικές	el
dc.subject	Ενσωματωμένα συστήματα	el
dc.subject	Όραση υπολογιστών	el
dc.subject	Συνελικτικά νευρωνικά δίκτυα	el
dc.title	Embedded development of aI-based computer vision: Acceleration on intel myriad X VPU	en
heal.type	bachelorThesis
heal.classification	Επιστήμη Υπολογιστών	el
heal.classification	Computer Science	en
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2021-11-08
heal.abstract	It is estimated that, by 2022, 82% of the packets transferred through the Internet will contain video data. The real-time processing of these data is a rather attractive prospect, that can lead to the creation of very interesting systems, commercial or otherwise. Convolutional Neural Networks (CNNs) are an important tool in this direction, as their recent rapid growth has resulted in some impressive solutions to classic computer vision problems. On the other hand, traditional embedded systems cannot support the increased requirements of CNNs in computational or memory resources. In this environment, an upcoming class of microprocessors, the Vision Processing Units, are developed. Myriad X is the latest installment in the family of VPUs offered by Intel/Movidius. It is a multicore, heterogeneous computing system, with a dedicated hardware accelerator for deep learning applications, and high performance per unit of power. However, most modern neural networks are developed, based on the performance of much more potent processing systems, and emphasize on accuracy rather than efficiency. This is the basis of many networks that attempt to solve the problem of estimating and tracking the pose of a satellite, more commonly known as the "Lost in Space" problem. In this thesis, we studied several different resampling methods on the input data, in order to determine how they affect the total number of computations and parameters of a CNN, as well as its accuracy. Multiple optimization techniques were utilized, including the exploitation of the on-chip Scratchpad Memory and the SIMD utilities of the Myriad X VPU, so as to avoid creating a bottleneck during this preprocessing stage. The preprocessed data are fed into a CNN, named "UrsoNet", which locates the position of a satellite on the input image and estimates its pose. To measure the power requirements of this application, a custom Power Measurement system is introduced, which can also perform static power management. Finally, a hybrid system is proposed. This system utilizes the CNN for the estimation of the initial pose of the satellite and, consequently, runs a classic, pipelined CV algorithm, that evolves and refines this initial pose in real-time. The results are highly encouraging, since the execution time required for a single inference is reduced up to 5 times, provided that proper preprocessing of the input frames is applied, with no noticeable degradation in accuracy. This allows for real-time execution on Myriad X, on a tight power envelope. Specifically, we achieve 2.12 - 2.22 FPS, depending on the scale on which the preprocessing takes place, with a mean power consumption of less than 2 Watts. The proposed hybrid system operates with an overhead of about 373.3 - 391.3 ms for the initial estimation and then requires approximately 263 - 388 ms to continue tracking the pose of the satellite, resulting in a throughput of 2.58 - 3.80 FPS.	en
heal.advisorName	Σούντρης, Δημήτριος	el
heal.committeeMemberName	Τσανάκας, Παναγιώτης	el
heal.committeeMemberName	Γκούμας, Γεώργιος	el
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών. Τομέας Τεχνολογίας Πληροφορικής και Υπολογιστών. Εργαστήριο Μικροϋπολογιστών και Ψηφιακών Συστημάτων VLSI	el
heal.academicPublisherID	ntua
heal.numberOfPages	143 σ.	el
heal.fullTextAvailability	false