Pedestrian Detection and Tracking Using Deformable Part Models and Kalman Filtering

Abstract： Pedestrian detection techniques are important and challenging especially for complex real world scenes. They can be used for ensuring pedestrian safety, ADASs （advance driver assistance systems） and safety surveillance systems. In this paper, we propose a novel approach for multi-person tracking-by-detection using deformable part models in Kalman filtering framework. The Kalman filter is used to keep track of each person and a unique label is assigned to each tracked individual. Based on this approach, people can enter and leave the scene randomly. We test and demonstrate our results on Caltech Pedestrian benchmark, which is two orders of magnitude larger than any other existing datasets and consists of pedestrians varying widely in appearance, pose and scale. Complex situations such as people occluded by each other are handled gracefully and individual persons can be tracked correctly after a group of people split. Experiments confirm the real-time performance and robustness of our system, working in complex scenes. Our tracking model gives a tracking accuracy of 72.8% and a tracking precision of 82.3%. We can further reduce false positives by 2.8%, using Kalman filtering.     

An efficient implicit regularized Lagrangian twin support vector regression

Twin support vector regression (TSVR) and Lagrangian TSVR (LTSVR) satisfy only empirical risk minimization principle. Moreover, the matrices in their formulations are always positive semi-definite. To overcome these problems, we propose an efficient implicit Lagrangian formulation for the dual regularized twin support vector regression, called IRLTSVR for short. By introducing a regularization term to each objective function, the optimization problems in our IRLTSVR are positive definite and implement the structural risk minimization principle. Moreover, the 1-norm of the vector of slack variable is replaced with 2-norm to make the objective functions strongly convex. Our IRLTSVR solves two systems of linear equations instead of solving two quadratic programming problems (QPPs) in TSVR and one large QPP in SVR, which makes the learning speed of IRLTSVR faster than TSVR and SVR. Particularly, we compare three implementations of IRLTSVR with existing approaches. Computational results on several synthetic and real-world benchmark datasets clearly indicate the effectiveness and applicability of the IRLTSVR in comparison to SVR, TSVR and LTSVR.     

Performance Analysis of Ferroelectric GAA MOSFET with Metal Grain Work Function Variability

Silicon - This work represents a unique GAA MOSFET with metal work-function variations (WFVs) and ferroelectric material as dielectric. A random distribution of metal grain (TiN) with grain size...     

Investigation on DC/RF Performance of LG = 19 nm Heterogeneous Integrated Ga0.15In0.85As/InAs/Ga0.15In0.85As Composite Channel InP HEMT on Silicon Substrate for Future Beyond 5G and Quantum Computing Applications

Silicon - The RF/DC performances of LG = 19 nm heterogeneous integrated Ga0.15In0.85As/InAs/Ga0.15In0.85As composite channel based InP HEMT (high electron mobility transistor)...     

Oxidation of Cr(III) in tannery sludge to Cr(VI): field observations and theoretical assessment

Sludge, soil and leachate samples collected from a chromium-contaminated tannery waste dumping site in Kanpur, India, were found to contain considerable amounts of Cr(VI), despite the fresh tannery sludge containing little or no Cr(VI). Literature reports suggested that dry Cr(III) precipitates could be converted to Cr(VI) when heated in the presence of oxygen. Also, Cr(III) in aqueous phase could be oxidized through interaction with manganese dioxide (MnO2) surface to Cr(VI). Measurement of manganese in the sludge samples collected from the site showed concentrations up to 0.6 mg/g. Based on equilibrium calculations, it was determined that both dry phase Cr(III) oxidation by atmospheric oxygen and aqueous phase Cr(III) oxidation by MnO2 surface were thermodynamically feasible. It was further suggested that in aqueous phase, manganese may act effectively as an electron transporter between Cr(III) and dissolved oxygen during Cr(III) oxidation, leading to regeneration of MnO2 solid phase. Further, as dissolved Cr(III) is oxidized, dissolution of Cr(OH3) will take place to maintain the equilibrium between the dissolved and solid phases of Cr(III). In the pH range of 3-10, and at oxygen partial pressure (P(O2)) of 10(-6) atm or higher, equilibrium conditions stipulate nearly complete conversion of Cr(III) to Cr(VI). At P(O2) of 10(-20) atm or lower, very little Cr(VI) is expected to be present under equilibrium conditions. In the intermediate P(O2) regions, incomplete dissolution of the Cr(OH3) solid phase and only partial conversion of chromium from +3 to the +6 oxidation state is expected, especially at lower pH values.     

Seismic response of precast reinforced concrete wall subjected to cyclic in-plane and constant out-of-plane loading

This paper provides insight into the seismic behavior of a full-scale precast reinforced concrete wall under in-plane cyclic loading combined with out-of-plane loading replicated by sand backfill to simulate the actual condition of basement walls. The tested wall exhibited flexural cracks, owing to the high aspect ratio and considerable out-of-plane movement due to lateral pressure from the backfill. The wall performed satisfactorily by exhibiting competent seismic parameters and deformation characteristics governed by its ductile response in the nonlinear phase during the test with smaller residual drift. Numerical analysis was conducted to validate experimental findings, which complied with each other. The numerical model was used to conduct parametric studies to study the effect of backfill density and aspect ratio on seismic response of the proposed precast wall system. The in-plane capacity of walls reduced, while deformation characteristics were unaffected by the increase in backfill density. An increase in aspect ratio leads to a reduction in in-plane capacity and an increase in drift. Curves between the ratio of in-plane yield capacity and design shear load of walls are proposed for the backfill density, which may be adopted to determine the in-plane yield capacity of the basement walls based on their design shear.     

Cardiovascular effects produced by microinjection of angiotensins and angiotensin antagonists into the ventrolateral medulla of freely moving rats

In this study we determined the cardiovascular effects produced by microinjection of angiotensin peptides [Angiotensin-(1-7) and Angiotensin II] and angiotensin antagonists (losartan, L-158,809, CGP 42112A. Sar1-Thr8-Ang II, A-779) into the rostral ventrolateral medulla of freely moving rats. Microinjection of angiotensins (12.5-50 pmol) produced pressor responses associated to variable changes in heart rate, usually tachycardia. Unexpectedly, microinjection of both AT1 and AT2 ligands produced pressor effects at doses that did not change blood pressure in anesthetized rats. Conversely, microinjection of Sar1-Thr8-Ang II and the selective Ang-(1-7) antagonist, A-779, produced a small but significant decrease in MAP an HR. These findings suggest that angiotensins can influence the tonic activity of vasomotor neurons at the RVLM. As previously observed in anesthetized rats, our results further suggest a role for endogenous Ang-(1-7) at the RVLM. The pressor activity of the ligands for AT1 and AT2 angiotensin receptor subtypes at the RVLM, remains to be clarified.     

Hydrothermally stable mesoporous aluminosilicates with moderate acidity via degradation-assembly process and improved catalytic properties

Mesoporous aluminosilicates with hydrothermal stability and moderate acidity are synthesized via assembly of microporous zeolite precursors obtained by the degradation of zeolite NaY, denoted as “degradation-assembly” (DA) technique. By controlling the degradation degree of matrix NaY, precursors with larger spatial volume and stronger rigidity will be obtained. The characterization results showed that the walls of the mesophase in MDA (mesoporous aluminosilicate obtained by “DA” method) composed of the preformed zeolite Y building units and the moderate acidity was inherited from the introduced precursors. It was suggested that the more mature assembly units accounted for the increased acidity of MDA with more Al species retained in the framework of mesophases. The resulting aluminosilicates with simultaneously moderate acidity and hydrothermal stability showed superior catalytic properties when used in heavy oil catalytic cracking catalysts.     

An Adaptive Non Reference Anchor Array Framework for Audio Retrieval in Teleconferencing Environment

In this paper, an adaptive framework for audio retrieval in live teleconferencing environments with multiple participants is proposed. The framework uses a non reference anchor array (NRA) to capture the interfering speech sources, in addition to the primary array that captures the speech source of interest (SOI). A linearly constrained-minimum variance (LC-MV) beamformer is used herein such that the signal coming from the look direction is preserved while interferences coming from the non look direction are nulled. Additionally, the reverberant component of the speech acquired by this framework is removed by a novel method that uses the linear prediction (LP) residual cepstrum. This method does not require the computation of the acoustic impulse response (AIR) of the teleconferencing room and hence is computationally efficient. The NRA framework is therefore able to remove correlated noise coming from the direction of the SOI and also dereverberating the noise free signal. The performance of the proposed framework is evaluated by conducting experiments on clean speech acquisition from distant microphone arrays. Experiments on distant speech recognition are also conducted using the TIMIT and MONC databases. Experimental results obtained from the proposed framework indicate a reasonable improvement over correlation, subspace and standard minimum variance beamforming methods. The application of the framework in audio retrieval in a live teleconferencing environment with multiple participants is also discussed.