IEEE Trans Image Process - Efficient minimum error bounded particle resampling L1 tracker with occlusion detection.

Tópicos

{ error(1145) method(1030) estim(1020) }
{ problem(2511) optim(1539) algorithm(950) }
{ motion(1329) object(1292) video(1091) }
{ first(2504) two(1366) second(1323) }
{ estim(2440) model(1874) function(577) }
{ detect(2391) sensit(1101) algorithm(908) }
{ use(976) code(926) identifi(902) }
{ framework(1458) process(801) describ(734) }
{ control(1307) perform(991) simul(935) }
{ age(1611) year(1155) adult(843) }
{ algorithm(1844) comput(1787) effici(935) }
{ method(1219) similar(1157) match(930) }
{ imag(2830) propos(1344) filter(1198) }
{ learn(2355) train(1041) set(1003) }
{ clinic(1479) use(1117) guidelin(835) }
{ howev(809) still(633) remain(590) }
{ perform(1367) use(1326) method(1137) }
{ activ(1138) subject(705) human(624) }
{ chang(1828) time(1643) increas(1301) }
{ extract(1171) text(1153) clinic(932) }
{ general(901) number(790) one(736) }
{ perform(999) metric(946) measur(919) }
{ cost(1906) reduc(1198) effect(832) }
{ patient(1821) servic(1111) care(1106) }
{ high(1669) rate(1365) level(1280) }
{ use(1733) differ(960) four(931) }
{ result(1111) use(1088) new(759) }
{ process(1125) use(805) approach(778) }
{ can(774) often(719) complex(702) }
{ inform(2794) health(2639) internet(1427) }
{ imag(2675) segment(2577) method(1081) }
{ method(984) reconstruct(947) comput(926) }
{ import(1318) role(1303) understand(862) }
{ model(2341) predict(2261) use(1141) }
{ blood(1257) pressur(1144) flow(957) }
{ spatial(1525) area(1432) region(1030) }
{ group(2977) signific(1463) compar(1072) }
{ sampl(1606) size(1419) use(1276) }
{ analysi(2126) use(1163) compon(1037) }
{ implement(1333) system(1263) develop(1122) }
{ activ(1452) weight(1219) physic(1104) }
{ model(3404) distribut(989) bayesian(671) }
{ imag(1947) propos(1133) code(1026) }
{ data(1737) use(1416) pattern(1282) }
{ system(1976) rule(880) can(841) }
{ measur(2081) correl(1212) valu(896) }
{ imag(1057) registr(996) error(939) }
{ bind(1733) structur(1185) ligand(1036) }
{ sequenc(1873) structur(1644) protein(1328) }
{ featur(3375) classif(2383) classifi(1994) }
{ network(2748) neural(1063) input(814) }
{ patient(2315) diseas(1263) diabet(1191) }
{ take(945) account(800) differ(722) }
{ studi(2440) review(1878) systemat(933) }
{ assess(1506) score(1403) qualiti(1306) }
{ treatment(1704) effect(941) patient(846) }
{ surgeri(1148) surgic(1085) robot(1054) }
{ concept(1167) ontolog(924) domain(897) }
{ method(1557) propos(1049) approach(1037) }
{ data(1714) softwar(1251) tool(1186) }
{ design(1359) user(1324) use(1319) }
{ model(2220) cell(1177) simul(1124) }
{ care(1570) inform(1187) nurs(1089) }
{ search(2224) databas(1162) retriev(909) }
{ featur(1941) imag(1645) propos(1176) }
{ case(1353) use(1143) diagnosi(1136) }
{ data(3963) clinic(1234) research(1004) }
{ studi(1410) differ(1259) use(1210) }
{ risk(3053) factor(974) diseas(938) }
{ research(1085) discuss(1038) issu(1018) }
{ system(1050) medic(1026) inform(1018) }
{ visual(1396) interact(850) tool(830) }
{ compound(1573) activ(1297) structur(1058) }
{ studi(1119) effect(1106) posit(819) }
{ record(1888) medic(1808) patient(1693) }
{ health(3367) inform(1360) care(1135) }
{ model(3480) simul(1196) paramet(876) }
{ monitor(1329) mobil(1314) devic(1160) }
{ ehr(2073) health(1662) electron(1139) }
{ state(1844) use(1261) util(961) }
{ research(1218) medic(880) student(794) }
{ patient(2837) hospit(1953) medic(668) }
{ model(2656) set(1616) predict(1553) }
{ data(2317) use(1299) case(1017) }
{ medic(1828) order(1363) alert(1069) }
{ signal(2180) analysi(812) frequenc(800) }
{ gene(2352) biolog(1181) express(1162) }
{ data(3008) multipl(1320) sourc(1022) }
{ intervent(3218) particip(2042) group(1664) }
{ time(1939) patient(1703) rate(768) }
{ use(2086) technolog(871) perceiv(783) }
{ can(981) present(881) function(850) }
{ health(1844) social(1437) communiti(874) }
{ structur(1116) can(940) graph(676) }
{ cancer(2502) breast(956) screen(824) }
{ drug(1928) target(777) effect(648) }
{ survey(1388) particip(1329) question(1065) }
{ decis(3086) make(1611) patient(1517) }
{ method(1969) cluster(1462) data(1082) }
{ method(2212) result(1239) propos(1039) }

Resumo

Recently, sparse representation has been applied to visual tracking to find the target with the minimum reconstruction error from a target template subspace. Though effective, these L1 trackers require high computational costs due to numerous calculations for l1 minimization. In addition, the inherent occlusion insensitivity of the l1 minimization has not been fully characterized. In this paper, we propose an efficient L1 tracker, named bounded particle resampling (BPR)-L1 tracker, with a minimum error bound and occlusion detection. First, the minimum error bound is calculated from a linear least squares equation and serves as a guide for particle resampling in a particle filter (PF) framework. Most of the insignificant samples are removed before solving the computationally expensive l1 minimization in a two-step testing. The first step, named t testing, compares the sample observation likelihood to an ordered set of thresholds to remove insignificant samples without loss of resampling precision. The second step, named max testing, identifies the largest sample probability relative to the target to further remove insignificant samples without altering the tracking result of the current frame. Though sacrificing minimal precision during resampling, max testing achieves significant speed up on top of t testing. The BPR-L1 technique can also be beneficial to other trackers that have minimum error bounds in a PF framework, especially for trackers based on sparse representations. After the error-bound calculation, BPR-L1 performs occlusion detection by investigating the trivial coefficients in the l1 minimization. These coefficients, by design, contain rich information about image corruptions, including occlusion. Detected occlusions are then used to enhance the template updating. For evaluation, we conduct experiments on three video applications: biometrics (head movement, hand holding object, singers on stage), pedestrians (urban travel, hallway monitoring), and cars in traffic (wide area motion imagery, ground-mounted perspectives). The proposed BPR-L1 method demonstrates an excellent performance as compared with nine state-of-the-art trackers on eleven challenging benchmark sequences.

Resumo Limpo

recent spars represent appli visual track find target minimum reconstruct error target templat subspac though effect l tracker requir high comput cost due numer calcul l minim addit inher occlus insensit l minim fulli character paper propos effici l tracker name bound particl resampl bprl tracker minimum error bound occlus detect first minimum error bound calcul linear least squar equat serv guid particl resampl particl filter pf framework insignific sampl remov solv comput expens l minim twostep test first step name t test compar sampl observ likelihood order set threshold remov insignific sampl without loss resampl precis second step name max test identifi largest sampl probabl relat target remov insignific sampl without alter track result current frame though sacrif minim precis resampl max test achiev signific speed top t test bprl techniqu can also benefici tracker minimum error bound pf framework especi tracker base spars represent errorbound calcul bprl perform occlus detect investig trivial coeffici l minim coeffici design contain rich inform imag corrupt includ occlus detect occlus use enhanc templat updat evalu conduct experi three video applic biometr head movement hand hold object singer stage pedestrian urban travel hallway monitor car traffic wide area motion imageri groundmount perspect propos bprl method demonstr excel perform compar nine stateoftheart tracker eleven challeng benchmark sequenc

Resumos Similares

IEEE J Biomed Health Inform - A bicluster-based Bayesian principal component analysis method for microarray missing value estimation. ( 0,713526516197447 )
Neural Comput - Density-difference estimation. ( 0,704429541895427 )
IEEE Trans Image Process - Optimal transition probability of reversible data hiding for general distortion metrics and its applications. ( 0,67893742397956 )
IEEE Trans Image Process - Sparse demixing of hyperspectral images. ( 0,677028387678404 )
Lifetime Data Anal - The weighted log-rank class under truncated binomial design: saddlepoint p-values and confidence intervals. ( 0,669652874630438 )
IEEE Trans Image Process - Feature adaptive co-segmentation by complexity awareness. ( 0,664051982018291 )
Med Biol Eng Comput - A Kalman filter-based approach to reduce the effects of geometric errors and the measurement noise in the inverse ECG problem. ( 0,650952855745576 )
IEEE Trans Image Process - Efficient registration of nonrigid 3-D bodies. ( 0,65025316723155 )
Med Biol Eng Comput - Automatic video detection of body movement during sleep based on optical flow in pediatric patients with epilepsy. ( 0,648020089249838 )
IEEE Trans Image Process - Sub-hexagonal phase correlation for motion estimation. ( 0,647341028883556 )
J. Comput. Biol. - Maximal acyclic agreement forests. ( 0,647049308168375 )
IEEE Trans Neural Netw Learn Syst - An incremental design of radial basis function networks. ( 0,645055314803976 )
Med Biol Eng Comput - Binary optimization for source localization in the inverse problem of ECG. ( 0,6363391052613 )
Int J Health Geogr - Determining optimal neighborhood size for ecological studies using leave-one-out cross validation. ( 0,63134504161818 )
Comput Math Methods Med - Nonnegative mixed-norm convex optimization for mitotic cell detection in phase contrast microscopy. ( 0,626056086787658 )
Med Biol Eng Comput - An adaptive gyroscope-based algorithm for temporal gait analysis. ( 0,625599025821431 )
IEEE Trans Image Process - Parameter estimation for blind and non-blind deblurring using residual whiteness measures. ( 0,623292028755035 )
IEEE Trans Pattern Anal Mach Intell - Robust Text Detection in Natural Scene Images. ( 0,620971089597417 )
J. Comput. Biol. - Threshold group testing on inhibitor model. ( 0,616290006060757 )
Int J Comput Assist Radiol Surg - A morphological study of anatomical plates for acetabular posterior column. ( 0,612676116171684 )
Comput. Biol. Med. - Three penalized EM-type algorithms for PET image reconstruction. ( 0,612047371851659 )
Med Decis Making - An efficient method for computing single-parameter partial expected value of perfect information. ( 0,611602564314445 )
J. Comput. Biol. - Fast and accurate detection of multiple quantitative trait Loci. ( 0,610193820256897 )
Int J Comput Assist Radiol Surg - Mesh-based method for measuring intracranial volume in patients with craniosynostosis. ( 0,60856280797031 )
IEEE Trans Image Process - Multi-frame super-resolution reconstruction of small moving objects. ( 0,606677008725356 )
Comput Methods Programs Biomed - Novel mathematical algorithm for pupillometric data analysis. ( 0,606657237157384 )
IEEE Trans Pattern Anal Mach Intell - Tracking-Learning-Detection. ( 0,606181427336171 )
Comput. Biol. Med. - Noninvasive identification of two lesions with local repolarization changes using two dipoles in inverse solution simulation study. ( 0,605190532574836 )
IEEE Trans Image Process - Missing intensity interpolation using a kernel PCA-based POCS algorithm and its applications. ( 0,603327388161663 )
Methods Inf Med - Individual Thresholding of Voxel-based Functional Connectivity Maps. Estimation of Random Errors by Means of Surrogate Time Series. ( 0,602795580803649 )
IEEE Trans Image Process - Robust albedo estimation from a facial image with cast shadow under general unknown lighting. ( 0,602764877894908 )
IEEE Trans Image Process - Online sparse Gaussian process regression and its applications. ( 0,602381673618998 )
IEEE Trans Image Process - t-Tests, F-tests and Otsu's methods for image thresholding. ( 0,601578947624194 )
Int J Comput Assist Radiol Surg - Optimized order estimation for autoregressive models to predict respiratory motion. ( 0,601578947624194 )
Telemed J E Health - A new chest compression depth feedback algorithm for high-quality CPR based on smartphone. ( 0,592464753026537 )
Comput Math Methods Med - Application of multivariate modeling for radiation injury assessment: a proof of concept. ( 0,59073879942423 )
Comput. Biol. Med. - Real time identification of active regions in muscles from high density surface electromyogram. ( 0,589682126714959 )
Med Biol Eng Comput - Efficient and robust estimation of blood oxygenation levels in single cerebral veins. ( 0,588831687847483 )
Artif Intell Med - Modified tabu search approach for variable selection in quantitative structure-activity relationship studies of toxicity of aromatic compounds. ( 0,588150336653256 )
IEEE Trans Image Process - Camera-pose estimation via projective Newton optimization on the manifold. ( 0,585305902271795 )
Int J Comput Assist Radiol Surg - Three-dimensional prediction of free-flap volume in autologous breast reconstruction by CT angiography imaging. ( 0,585145231190359 )
Neural Comput - Energy complexity of recurrent neural networks. ( 0,58432564018787 )
Neural Comput - Improved integral equation solution for the first passage time of leaky integrate-and-fire neurons. ( 0,583657238187947 )
IEEE Trans Image Process - Approximate least trimmed sum of squares fitting and applications in image analysis. ( 0,582916872470902 )
IEEE Trans Pattern Anal Mach Intell - Monotonicity and Error Type Differentiability in Performance Measures for Target Detection and Tracking in Video. ( 0,581265649615629 )
IEEE Trans Image Process - Optimized regression for efficient function evaluation. ( 0,580702791837479 )
Comput. Biol. Med. - Real time estimation of generation, extinction and flow of muscle fibre action potentials in high density surface EMG. ( 0,577782736486584 )
J Biomed Inform - Using genetic algorithm in reconstructing single individual haplotype with minimum error correction. ( 0,576561598870361 )
Int J Comput Assist Radiol Surg - A low-cost tracked C-arm (TC-arm) upgrade system for versatile quantitative intraoperative imaging. ( 0,575654657612268 )
Int J Comput Assist Radiol Surg - Improved human observer performance in digital reconstructed radiograph verification in head and neck cancer radiotherapy. ( 0,575178027822927 )
IEEE Trans Image Process - Real-time affine global motion estimation using phase correlation and its application for digital image stabilization. ( 0,573356689092518 )
J Clin Monit Comput - Effect of concurrent oxygen therapy on accuracy of forecasting imminent postoperative desaturation. ( 0,570706183477884 )
Int J Comput Assist Radiol Surg - Wireless mobile technology to improve workflow and feasibility of MR-guided percutaneous interventions. ( 0,568533644925113 )
Comput Math Methods Med - Investigation of attenuation correction for small-animal single photon emission computed tomography. ( 0,567300166585676 )
Int J Comput Assist Radiol Surg - Intraoperative detection and localization of cylindrical implants in cone-beam CT image data. ( 0,566346170459124 )
J. Comput. Biol. - Nonadaptive algorithms for threshold group testing with inhibitors and error-tolerance. ( 0,565083464001054 )
Comput Methods Programs Biomed - HELOW: a program for testing extreme homogeneity in meta-analysis. ( 0,563755717475675 )
Int J Comput Assist Radiol Surg - Needle deflection estimation: prostate brachytherapy phantom experiments. ( 0,56267200298521 )
IEEE Trans Image Process - Nonlocal sparse and low-rank regularization for optical flow estimation. ( 0,561079927747078 )
IEEE Trans Image Process - Nonlocal means with dimensionality reduction and SURE-based parameter selection. ( 0,55981930194853 )
Res Synth Methods - Robust variance estimation in meta-regression with binary dependent effects. ( 0,559030877961977 )
IEEE Trans Vis Comput Graph - Truthful Color Reproduction in Spatial Augmented Reality Applications. ( 0,558785348348642 )
IEEE Trans Neural Netw Learn Syst - The Connection Between Bayesian Estimation of a Gaussian Random Field and RKHS. ( 0,558775697971263 )
J Integr Bioinform - Comparison of different algorithms for simultaneous estimation of multiple parameters in kinetic metabolic models. ( 0,55850930988668 )
IEEE Trans Neural Netw Learn Syst - Retargeted Least Squares Regression Algorithm. ( 0,558262181508566 )
Methods Inf Med - Analysis of Fluorescence Lifetime Imaging Microscopy (FLIM) data. Based on a fully automated Laguerre deconvolution method. ( 0,557354992175911 )
IEEE Trans Pattern Anal Mach Intell - Biologically Inspired Object Tracking Using Center-Surround Saliency Mechanisms. ( 0,556974045857343 )
Comput Methods Programs Biomed - Bayesian sample-size determination for two independent Poisson rates. ( 0,555529615843607 )
J. Comput. Biol. - Border length minimization problem on a square array. ( 0,554699270901621 )
Comput Methods Programs Biomed - A Gauss-Newton approach to joint image registration and intensity correction. ( 0,554522338436714 )
Comput. Biol. Med. - Missing value imputation in DNA microarrays based on conjugate gradient method. ( 0,553303405588012 )
Med Biol Eng Comput - A robust method for online heart sound localization in respiratory sound based on temporal fuzzy c-means. ( 0,552781661933336 )
J Clin Monit Comput - Reliable real-time calculation of heart-rate complexity in critically ill patients using multiple noisy waveform sources. ( 0,550878557844265 )
Med Biol Eng Comput - Effect of layer heterogeneity on the biomechanical properties of ascending thoracic aortic aneurysms. ( 0,550396382441315 )
Med Biol Eng Comput - Predicting 3D pose in partially overlapped X-ray images of knee prostheses using model-based Roentgen stereophotogrammetric analysis (RSA). ( 0,550389678516867 )
Artif Intell Med - Identification of sympathetic and parasympathetic nerves function in cardiovascular regulation using ANFIS approximation. ( 0,549153915607459 )
IEEE Trans Image Process - Spatially adapted total variation model to remove multiplicative noise. ( 0,546540896505667 )
IEEE Trans Pattern Anal Mach Intell - Variational Light Field Analysis for Disparity Estimation and Super-Resolution. ( 0,545067027072798 )
IEEE Trans Image Process - Adaptive multiple-frame image super-resolution based on U-curve. ( 0,54503022359876 )
Med Decis Making - Estimating health state utility values for joint health conditions: a conceptual review and critique of the current evidence. ( 0,54242427881878 )
IEEE Trans Image Process - Multi-Wiener SURE-LET deconvolution. ( 0,541300103415829 )
Comput Math Methods Med - The failure of R0. ( 0,541239198209742 )
IEEE Trans Vis Comput Graph - Poisson Coordinates. ( 0,540331804530755 )
Spat Spatiotemporal Epidemiol - Error propagation models to examine the effects of geocoding quality on spatial analysis of individual-level datasets. ( 0,538203914021951 )
IEEE Trans Image Process - This is SPIRAL-TAP: Sparse Poisson Intensity Reconstruction ALgorithms--theory and practice. ( 0,537944205183289 )
Lifetime Data Anal - On collapsibility and confounding bias in Cox and Aalen regression models. ( 0,537699254279632 )
Brief. Bioinformatics - Letter to the editor: Stability of Random Forest importance measures. ( 0,537050925779751 )
IEEE Trans Image Process - Robust principal component analysis based on maximum correntropy criterion. ( 0,536488740538291 )
Comput. Biol. Med. - Preoperative implant selection for two stage breast reconstruction with 3D imaging. ( 0,535998277829661 )
Comput Methods Programs Biomed - Adaptive network based on fuzzy inference system for equilibrated urea concentration prediction. ( 0,535569337374395 )
J Chem Inf Model - Benchmarking study of parameter variation when using signature fingerprints together with support vector machines. ( 0,53550453635087 )
IEEE Trans Image Process - Vision-based pose estimation from points with unknown correspondences. ( 0,534956070687956 )
IEEE Trans Pattern Anal Mach Intell - Robust Visual Tracking Using Local Sparse Appearance Model and K-Selection. ( 0,532646924232975 )
IEEE Trans Neural Netw Learn Syst - Sparse multivariate gaussian mixture regression. ( 0,532628101173337 )
Med Biol Eng Comput - Inertial sensors in estimating walking speed and inclination: an evaluation of sensor error models. ( 0,532428243482112 )
Neural Comput - A general likelihood framework for characterizing the time course of neural activity. ( 0,530747877984571 )
Comput. Biol. Med. - An optimized Nash nonlinear grey Bernoulli model based on particle swarm optimization and its application in prediction for the incidence of Hepatitis B in Xinjiang, China. ( 0,53030706958949 )
Comput. Biol. Med. - The L1/2 regularization approach for survival analysis in the accelerated failure time model. ( 0,529925739244596 )
IEEE Trans Pattern Anal Mach Intell - On-line Video Event Detection by Constraint Flow. ( 0,529095528976264 )
IEEE Trans Image Process - An augmented Lagrangian method for total variation video restoration. ( 0,528740850628236 )