Abstract | ||
---|---|---|
Modern descriptors like HOG and SIFT are now commonly used in vision for pattern detection within image and video. From a signal processing perspective, this detection process can be efficiently posed as a correlation/ convolution between a multi-channel image and a multi-channel detector/filter which results in a single channel response map indicating where the pattern (e.g. object) has occurred. In this paper, we propose a novel framework for learning a multi-channel detector/filter efficiently in the frequency domain, both in terms of training time and memory footprint, which we refer to as a multichannel correlation filter. To demonstrate the effectiveness of our strategy, we evaluate it across a number of visual detection/ localization tasks where we: (i) exhibit superior performance to current state of the art correlation filters, and (ii) superior computational and memory efficiencies compared to state of the art spatial detectors. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICCV.2013.381 | Computer Vision |
Keywords | Field | DocType |
computer vision,filtering theory,frequency-domain analysis,learning (artificial intelligence),object detection,HOG descriptor,SIFT descriptor,computational efficiency,computer vision,detection process,frequency domain,memory efficiency,memory footprint,multichannel correlation filters,multichannel detector-filter learning,multichannel image,pattern detection,signal processing perspective,single-channel response map,training time,video,visual detection-localization tasks,correlation filter learning,multi channel features,pattern recognition | Frequency domain,Signal processing,Scale-invariant feature transform,Computer vision,Object detection,Pattern recognition,Convolution,Computer science,Communication channel,Artificial intelligence,Memory footprint,Detector | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1550-5499 |
Citations | PageRank | References |
69 | 2.69 | 13 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hamed Kiani Galoogahi | 1 | 136 | 6.68 |
Terence Sim | 2 | 2562 | 169.42 |
Simon Lucey | 3 | 2034 | 116.77 |