Conference paper
Distributed coding of multiview sparse sources with joint recovery
In support of applications involving multiview sources in distributed object recognition using lightweight cameras, we propose a new method for the distributed coding of sparse sources as visual descriptor histograms extracted from multiview images. The problem is challenging due to the computational and energy constraints at each camera as well as the limitations regarding intercamera communication.
Our approach addresses these challenges by exploiting the sparsity of the visual descriptor histograms as well as their intraand inter-camera correlations. Our method couples distributed source coding of the sparse sources with a new joint recovery algorithm that incorporates multiple side information signals, where prior knowledge (low quality) of all the sparse sources is initially sent to exploit their correlations.
Experimental evaluation using the histograms of shift-invariant feature transform (SIFT) descriptors extracted from multiview images shows that our method leads to bit-rate saving of up to 43% compared to the state-of-the-art distributed compressed sensing method with independent encoding of the sources.
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2016 |
Pages: | 1-5 |
Proceedings: | 32nd Picture Coding Symposium |
ISBN: | 1509059660 , 1509059679 , 9781509059669 and 9781509059676 |
ISSN: | 24727822 |
Types: | Conference paper |
DOI: | 10.1109/PCS.2016.7906382 |
ORCIDs: | Forchhammer, Søren |
Cameras Decoding Distributed source coding Histograms Object recognition SIFT descriptors Silicon Source coding bit-rate saving cameras compressed sensing with side information computational constraint distributed object recognition energy constraint feature extraction image coding intercamera correlation intracamera correlation joint recovery algorithm lightweight camera multiview image multiview sparse source distributed coding object recognition shift-invariant feature transform descriptors source coding transforms visual descriptor histogram