Rethinking Image Compression for the Object Detection Task

Simple item page
dc.contributor.advisorVeeraraghavan, Ashoken_US
dc.contributor.committeeMemberBaraniuk, Richarden_US
dc.contributor.committeeMemberShrivastava, Anshumalien_US
dc.creatorBarua, Souptiken_US
dc.date.accessioned2016-01-06T20:30:30Zen_US
dc.date.available2016-01-06T20:30:30Zen_US
dc.date.created2015-12en_US
dc.date.issued2015-12-03en_US
dc.date.submittedDecember 2015en_US
dc.date.updated2016-01-06T20:30:30Zen_US
dc.description.abstractTraditionally, image compression algorithms, such as JPEG, have been designed for human viewers' satisfaction. Increasingly however, more and more images are being viewed by computers, for performing computer vision tasks such as object detection. Image compression and object detection have largely been independent areas of research so far. However, several applications such as surveillance and medical imaging impose severe bandwidth and power restrictions. These constraints make the quality and/or size of the compressed image a critical factor in object detection performance. My works presents three compressed image representations that enable fast and accurate object detection. The first representation is a saliency guided wavelet representation which modifies traditional wavelet compression using the knowledge of saliency to improve both compression and detection performance compared to JPEG images. The second representation, called event stream representation, comes directly from the new DVS sensor which has ultra-low bandwidth and power requirements. We show, for the first time, high speed video reconstruction, and direct detection, on the event data. We achieve detection performance comparable to that on conventional JPEG images. Finally, we explore an abstract compressed representation called patch-wise binary representation, which represents an image (patch-wise) as a collection of short binary strings. We demonstrate two ways of generating these binary strings, called hashing and feature binarization, which enable 10x faster detection. We show promising detection and reconstruction results for both these approaches.en_US
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationBarua, Souptik. "Rethinking Image Compression for the Object Detection Task." (2015) Master’s Thesis, Rice University. <a href="https://hdl.handle.net/1911/87714">https://hdl.handle.net/1911/87714</a>.en_US
dc.identifier.urihttps://hdl.handle.net/1911/87714en_US
dc.language.isoengen_US
dc.rightsCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.en_US
dc.subjectImage compressionen_US
dc.subjectobject detectionen_US
dc.subjectwaveleten_US
dc.subjectDVS sensoren_US
dc.subjectvideo reconstructionen_US
dc.subjecthashingen_US
dc.subjectfeature binarizationen_US
dc.titleRethinking Image Compression for the Object Detection Tasken_US
dc.typeThesisen_US
dc.type.materialTexten_US
thesis.degree.departmentElectrical and Computer Engineeringen_US
thesis.degree.disciplineEngineeringen_US
thesis.degree.grantorRice Universityen_US
thesis.degree.levelMastersen_US
thesis.degree.nameMaster of Scienceen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
BARUA-DOCUMENT-2015.pdf
Size:
4.03 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.84 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.61 KB
Format:
Plain Text
Description:
Download
Collections
Rice University Theses and Dissertations
ECE Theses and Dissertations