C⁴ : A Real-time Object Detection Framework

dc.contributor.author Wu, Jianxin
dc.contributor.author Liu, Nini
dc.contributor.author Geyer, Christopher
dc.contributor.author Rehg, James M.
dc.contributor.corporatename Georgia Institute of Technology. College of Computing en_US
dc.contributor.corporatename Georgia Institute of Technology. School of Interactive Computing en_US
dc.contributor.corporatename Georgia Institute of Technology. Center for Robotics and Intelligent Machines en_US
dc.contributor.corporatename Nanjing University en_US
dc.contributor.corporatename Nanyang Technological University. School of Computer Engineering en_US
dc.contributor.corporatename iRobot Corporation en_US
dc.date.accessioned 2014-04-25T13:58:53Z
dc.date.available 2014-04-25T13:58:53Z
dc.date.issued 2013-10
dc.description ©2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. en_US
dc.description DOI: 10.1109/TIP.2013.2270111
dc.description.abstract A real-time and accurate object detection framework, C⁴, is proposed in this paper. C⁴ achieves 20 fps speed and state-of-the-art detection accuracy, using only one processing thread without resorting to special hardwares like GPU. Real-time accurate object detection is made possible by two contributions. First, we conjecture (with supporting experiments) that contour is what we should capture and signs of comparisons among neighboring pixels are the key information to capture contour cues. Second, we show that the CENTRIST visual descriptor is suitable for contour based object detection, because it encodes the sign information and can implicitly represent the global contour. When CENTRIST and linear classifier are used, we propose a computational method that does not need to explicitly generate feature vectors. It involves no image preprocessing or feature vector normalization, and only requires O(1) steps to test an image patch. C⁴ is also friendly to further hardware acceleration. It has been applied to detect objects such as pedestrians, faces, and cars on benchmark datasets. It has comparable detection accuracy with state-of-the-art methods, and has a clear advantage in detection speed. en_US
dc.embargo.terms null en_US
dc.identifier.citation Wu, J.; Liu, N; Geyer, C.; & Rehg, J.M. (2013). : A Real-Time Object Detection Framework.” IEEE Transactions on Image Processing, Vol. 22, no.10, (October 2013), pp.4096-4107.
dc.identifier.doi 10.1109/TIP.2013.2270111
dc.identifier.uri http://hdl.handle.net/1853/51637
dc.language.iso en_US en_US
dc.publisher Georgia Institute of Technology en_US
dc.subject CENTRIST en_US
dc.subject Object detection en_US
dc.subject Real-time en_US
dc.title C⁴ : A Real-time Object Detection Framework en_US
dc.type Text
dc.type.genre Article
dspace.entity.type Publication
local.contributor.author Rehg, James M.
local.contributor.corporatename Institute for Robotics and Intelligent Machines (IRIM)
relation.isAuthorOfPublication af5b46ec-ffe2-4ce4-8722-1373c9b74a37
relation.isOrgUnitOfPublication 66259949-abfd-45c2-9dcc-5a6f2c013bcf
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
791.35 KB
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
3.13 KB
Item-specific license agreed upon to submission