Small target detection in compressed domain for parallel compressive imaging system
(2.University of Chinese Academy of Sciences, Beijing, China 200083)
(3.University of Chinese Academy of Sciences, Beijing ,China 100049)
【Abstract】A small target detection algorithm working at a compressed domain was proposed for parallel compressive imaging systems to reduce the computational complexity by eliminating the process of image reconstruction. A mathematical model of the parallel compressive imaging system was used to capture measuring values of background and current frames. Then, the background measurements were updated according to a compressive sensing-mixture of Gaussians model (CS-MoG) to obtain the measurement values of the foreground. The cosine similarities between the measurements of current frame and the compressed target-location templates were calculated. And the local threshold and target area in the compressed domain were adopted to screen candidate targets. Finally, the effects of down-sampling rate, number of measurements, projection error and noise on the detection results were studied by simulation experiments. Experimental results show that large down-sampling rate and noise would decrease the detection performance, but the number of measurements to detection results has limited contribution. When 2 or 3 measurements are set, the operation time could be controlled while ensuring the detection performance. It suggests that the noise in the system should be controlled strictly because the noise affects the detection ability greatly. Furthermore, the proposed algorithm can achieve real-time target detection without any image reconstruction.
【Keywords】 small target detection; compressive sensing; background modeling; template matching; parallel compressive imaging system;
(Translated by caizhijian)
DUARTE M F, DAVENPORT M A, TAKHARD, et al. Single-pixel imaging via compressive sampling[J]. IEEE Signal Processing Magazine, 2008, 25(2), 83–91.
BARANIUK R G. Compressive sensing[J]. IEEESignal Processing Magazine, 2007, 24(4), 121–124.
SHEPARD R H, FERNANDEZCULL C, RASKARR, et al. Optical design and characterization of an advanced computational imaging system[J]. Proc. SPIE, 2014, 9216, 92160A.
KERVICHE R, ZHU N, ASHOK A. Information optimal scalable compressive imaging system[C]. Computational Imaging and Sensing Conference(Optical Society of America), 2014.
MAHALANOBIS A, SHILLING R, MURPHY R, et al. Recent results of medium wave infrared compressive sensing[J]. Applied Optics, 2014, 53(34), 8060–8070.
WANG J, GUPTA M, SANKARANARAYANANA C. LiSensA scalable architecture for video compressive sensing[C]. Proceedings of IEEE International Conference on Computational Photography, 2015, 1–9.
DUMAS J P, LODHI M A, BAJWA W U, et al. Computational imaging with a highly parallel image planecoded architecture: challenges and solutions[J]. Opt. Express, 2016, 24, 6145–6155.
CHEN Q, WANG Y. A small target detection method in infrared image sequences based on compressive sensing and background subtraction[C]. IEEE Int. Conf. Signal Process, Communication, Compute, 2013.
XIU X Y, LIU Y X, ZHOU G H. On detection technique of small moving objects in remote sensing image based on compressive sensing[J]. Computer Applications and Software, 2014, 31(5): 219–222. (in Chinese)
QIN SH H, CHEN D Y, HUANG X, et al. A compressive signal detection Scheme based on sparsity[J]. International Journal of Signal Processing, Image Processing and Pattern Recognition, 2014, 7(2): 121–130.
LI L, LI H, LI T, et al. Infrared small target detection in compressive domain[J]. Electron Letters, 2014, 50(7): 510–512.
LI A D, LIN Z P, AN W, et al. Infrared small target detection in compressive domain based on selfadaptive parameter configuration[J]. Chinese Journal of Lasers, 2015, 42(10): 221–228. (in Chinese)
MU ZH Y, WEI ZH H, HE X, et al. Adaptive clutter suppression of infrared images by using sparse representation[J]. Opt. Precision Eng. , 2013, 21(7): 1850–1857. (in Chinese)
HE Y J, LI M, ZHANG J L, et al. Clutter suppression of infrared image based on threecomponent lowrank matrix decomposition[J]. Opt. Precision Eng. , 2015, 23(7): 2069–2078. (in Chinese)
XIE L J, HUANG J J, HUANG J X, et al. Infrared small target detection with compressive measurements[C]. Proceedings of the 14th China Conference of Stereology and Image Analysis. Chinese Society for Stereology, 2015, 5. (in Chinese)
SHEN Y, HU W, YANG M R, et al. Realtime and robust compressive background subtraction for embedded camera networks[J]. IEEE Transactions on Mobile Computing, 2016, 152, 406–418.
ZANG Q, KLETTE R. Parameter analysis for mixture of Gaussians[R]. CITR Technical Report188, Auckland University, 2006.
RIVEST J F, FORTIN R. Detection of dim targets in digital infrared imagery by morphological image processing[J]. Optical Engineering, 1996, 35: 1886–1893.
GAO C, MENG D, YANG Y, et al. Infrared patchimage model for small target detection in a single image[J]. IEEE Transactions on Image Processing, 2013, 22(12): 4996–5009.