Detection Performance from Compressed Measurements
نویسندگان
چکیده
This work uses two performance metrics, target detection and scene reconstruction performance, to compare various estimation techniques that operate on compressed measurements. Specifically we compare the performance of the compressed matched filter, `1-regularized least squares, and complex approximate message passing (CAMP), as well as a sparsified matched filter estimate. We show that the compressed matched filter provides the same or similar detection performance as the other, more computationally expensive techniques, but at the expense of poorer signal reconstruction error. However, by sparsifying the matched filter estimate using a soft-thresholding function, this estimate can achieve high reconstruction performance as well, and at much lower computational cost.
منابع مشابه
Compressed Domain Scene Change Detection Based on Transform Units Distribution in High Efficiency Video Coding Standard
Scene change detection plays an important role in a number of video applications, including video indexing, searching, browsing, semantic features extraction, and, in general, pre-processing and post-processing operations. Several scene change detection methods have been proposed in different coding standards. Most of them use fixed thresholds for the similarity metrics to determine if there wa...
متن کاملA Novel Joint Compressive Single Target Detection and Parameter Estimation in Radar without Signal Reconstruction
In this paper, a detector/estimator is proposed for compressed sensing radars, which does not need to reconstruct the radar signal, and which works directly from compressive measurements. More precisely, through direct processing of the measurements, and without the need for reconstructing the original radar signal, the system performs target detection, and then estimates range, Doppler frequen...
متن کاملThis is the published version :
This paper addresses a major challenge in data mining applications where the full information about the underlying processes, such as sensor networks or large online database, cannot be practically obtained due to physical limitations such as low bandwidth or memory, storage, or computing power. Motivated by the recent theory on direct information sampling called compressed sensing (CS), we pro...
متن کاملTarget Detection Performance Bounds in Compressive Spectral Imaging
This paper describes computationally efficient approaches and associated theoretical performance guarantees for the detection of known spectral targets and spectral anomalies from few projection measurements of spectral images. The proposed approaches accommodate spectra of different signal strengths contaminated by a colored Gaussian background, and perform detection without reconstructing the...
متن کاملA Block-Wise random sampling approach: Compressed sensing problem
The focus of this paper is to consider the compressed sensing problem. It is stated that the compressed sensing theory, under certain conditions, helps relax the Nyquist sampling theory and takes smaller samples. One of the important tasks in this theory is to carefully design measurement matrix (sampling operator). Most existing methods in the literature attempt to optimize a randomly initiali...
متن کامل