Hybrid CPU-GPU implementation of tracking-learning-detection algorithm

Download

index.pdf

Date

2014

Author

Gürcan, İlker

Metadata

Show full item record

Item Usage Stats

182
views

61
downloads

Tracking objects in a video stream is an important problem in robot learning (learning an object’s visual features from different perspectives as it moves, rotates, scales, and is subjected to some morphological changes such as erosion), defense, public security and many other various domains. In this thesis, we focus on a recently proposed tracking framework called TLD (Tracking-Learning-Detection). While having promising tracking results, the algorithm has high computational cost. The computational cost of the algorithm prevents running it at higher resolutions as well as running multiple instances of the algorithm to track multiple objects on CPU. In this thesis, we analyzed this framework with an aim to optimize it computationally on a CPU-GPU hybrid setting and developed a solution via using GP-GPU (General Purpose GPU) programming using Open-MP and CUDA. Our results show that 2.82 times speed-up at 480x270 resolution can be achieved. The speed-ups are higher at higher resolutions as expected in a massively parallel GPU platform, increasing to 10.25 times speed-up at 1920x1080 resolution. The resulting performance of the algorithm enables the algorithm to track multiple objects at higher frame rates in real-time and improving detection and tracking quality by allowing selection of configuration parameters requiring higher processing power.

Subject Keywords

Computer vision., Robotics., Artificial intelligence., Robots, Graphics processing units.

URI

http://etd.lib.metu.edu.tr/upload/12618126/index.pdf
https://hdl.handle.net/11511/24146

Collections

Graduate School of Informatics, Thesis

Suggestions

OpenMETU
Core

Data-driven image captioning via salient region discovery Kilickaya, Mert; Akkuş, Burak Kerim; Çakıcı, Ruket; Erdem, Aykut; Erdem, Erkut; İKİZLER CİNBİŞ, NAZLI (Institution of Engineering and Technology (IET), 2017-09-01) n the past few years, automatically generating descriptions for images has attracted a lot of attention in computer vision and natural language processing research. Among the existing approaches, data-driven methods have been proven to be highly effective. These methods compare the given image against a large set of training images to determine a set of relevant images, then generate a description using the associated captions. In this study, the authors propose to integrate an object-based semantic image r...
Simple and complex behavior learning using behavior hidden Markov Model and CobART Seyhan, Seyit Sabri; Alpaslan, Ferda Nur; Department of Computer Engineering (2013) In this thesis, behavior learning and generation models are proposed for simple and complex behaviors of robots using unsupervised learning methods. Simple behaviors are modeled by simple-behavior learning model (SBLM) and complex behaviors are modeled by complex-behavior learning model (CBLM) which uses previously learned simple or complex behaviors. Both models have common phases named behavior categorization, behavior modeling, and behavior generation. Sensory data are categorized using correlation based...
Key protected classification for collaborative learning Sariyildiz, Mert Bulent; Cinbiş, Ramazan Gökberk; Ayday, Erman (Elsevier BV, 2020-08-01) © 2020Large-scale datasets play a fundamental role in training deep learning models. However, dataset collection is difficult in domains that involve sensitive information. Collaborative learning techniques provide a privacy-preserving solution, by enabling training over a number of private datasets that are not shared by their owners. However, recently, it has been shown that the existing collaborative learning frameworks are vulnerable to an active adversary that runs a generative adversarial network (GAN...
Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision? KRÜGER, Norbert; JANSSEN, Peter; Kalkan, Sinan; LAPPE, Markus; LEONARDİS, Ales; PİATER, Justus; Rodriguez-Sanchez, Antonio J.; WİSKOTT, Laurenz (Institute of Electrical and Electronics Engineers (IEEE), 2013-08-01) Computational modeling of the primate visual system yields insights of potential relevance to some of the challenges that computer vision is facing, such as object recognition and categorization, motion detection and activity recognition, or vision-based navigation and manipulation. This paper reviews some functional principles and structures that are generally thought to underlie the primate visual cortex, and attempts to extract biological principles that could further advance computer vision research. Or...
Automated classification of remote sensing images using multileveled MobileNetV2 and DWT techniques Karadal, Can Haktan; Kaya, Muhammed Çağrı; Tuncer, Turker; Dogan, Sengul; Acharya, U. Rajendra (2021-12-15) Automated classification of remote sensing images is one of the complex issues in robotics and machine learning fields. Many models have been proposed for remote sensing image classification (RSIC) to obtain high classification performance. The objective of this study are twofold. First, to create a new space object image collection as such a dataset is not currently available. Second, propose a novel RSIC model to yield highest classification performance using our newly created dataset. Our presented autom...

Citation Formats

İ. Gürcan, “Hybrid CPU-GPU implementation of tracking-learning-detection algorithm,” M.S. - Master of Science, Middle East Technical University, 2014.