Type classification, color estimation, and specific target detection of moving targets on public streets

This paper describes a vision system that recognizes moving targets such as vehicles and pedestrians on public streets. This system can: (1) classify targets {vehicle, pedestrian, others} and, for vehicles, discriminate vehicle types and (2) estimate the main colors of targets. According to the input images to the system, the categories of targets are set as {mule (golf cart for workers), sedan, van, truck, pedestrian (single or plural), and other (such as noise)}. Their colors are set as six color groups {red, orange, yellow; green; blue, light blue; white, silver, gray; dark blue, dark gray, black; dark red, dark orange}. In this experiment, we collected images of targets from 9: 00 a.m. to 5: 00 p.m. on sunny and cloudy days as system training samples. The recognition ratio was 91.1% under the condition that both the recognition results of type and color agreed with the operators judgment. In addition, the system can detect predefined specific targets such as delivery vans, post office vans, and police cars by combining recognition results for type and color. The recognition ratio for specific targets was 92.9%. For the classification and estimation of targets, we employed a statistical linear discrimination method (linear discriminant analysis, LDA) and a nonlinear decision rule (weighted K-nearest neighbor rule, K-NN).Received: 11 March 2004, Accepted: 11 August 2004, Published online: 20 December 2004 Correspondence to: Osamu Hasegawa     

A new algorithm for non-linear mapping with applications to dimension and cluster analyses

In this paper, a new non-linear mapping method suitable for dimension and cluster analysis is proposed. In order to obtain a flexible and powerful method, the non-metric multidimensional scaling of Kruskal type is extended by introducing the concept of k-nearest neighbor. Some simulation results supporting the efficiency of our new method are given along with a detailed discussion.     

Fabrication of electrochemically stable fluorinated nano-carbon film compared with other fluorinated carbon materials

We fabricated electrochemically stable fluorinated nano-carbon film that had an sp² and sp³ hybrid nanocrystalline structure formed using the electron cyclotron resonance (ECR) sputtering method. This fluorinated ECR (F-ECR) nano-carbon film prepared with a short CF₄ plasma treatment has a high fluorine content (F/C:0.20) and a low oxygen content (O/C:0.02) on its surface and retains its original morphology. This F-ECR nano-carbon is capable of a lower capacitance current, and a wider potential window than untreated ECR nano-carbon. The electron transfer rates at an F-ECR electrode are as high as those of untreated carbons for , whereas they are much slower than those of untreated ECR nano-carbon for Fe^2+/3+ and owing to its selective sp² fluorination. These slow electron transfer rates for Fe^2+/3+ and are maintained during potential cycles due to its robust nanocrystalline structure. In contrast, these slow electron transfer rates were easily recovered for fluorinated glassy carbon under same condition. Furthermore, a smaller fluorination effect was observed for polycrystalline boron-doped diamond owing to the low reactivity of its sp³ bonds. Our ECR nano-carbon film is suitable for the effective fabrication of a fluorinated surface while maintaining a relatively active electrochemical interface and excellent stability.     

2,3-Dehydro-4α-hydroxylongilactone,a novel quassinoid and two known phenyl propanoids from Eurycoma longifolia Jack

A phytochemical study on the root of Eurycoma longifolia Jack afforded a novel 2,3-dehydro-4α-hydroxylongilactone (1) and two known phenyl propanoids, 2,3-dihydroxy-1-(4′-hydroxy-3′-methoxyphenyl)-propan-1-one (2) and scopolin (3), isolated from this plant for the first time. All structures were characterised by spectroscopic analysis (1D and 2D NMR experiments, HRMS, UV, IR and optical rotation) and by comparison with known data. This is the first report of a C₁₉ quassinoid from the Simaroubaceae family possessing an unsubstituted vinyl function and a C-4 methyl group of β-configuration in ring A.     

Comparison of carbonaceous aerosols in Tokyo before and after implementation of diesel exhaust restrictions

We compared the status of carbonaceous aerosols in Tokyo before and after the implementation of a diesel vehicle regulation intended to reduce the quantity of particulate carbon from diesel engines in one of the largest scale ever attempts at vehicle exhaust control. Radiocarbon (14C) in elemental carbon (EC) and total carbon (TC) were analyzed to identify fossil fuel carbonaceous particles emitted from diesel-powered vehicles. One-sided paired-month t-tests showed no distinct difference in the absolute concentrations of particles in terms of total mass (19.5 to 18.0 microg m(-3); p = 0.321), EC (3.6 to 3.3 microg m(-3); p = 0.272), and TC (6.3 to 6.2 microg m(-3); p = 0.418) for the finest particles (d(a) < 1.1 microm) after the implementation of the regulation. The ratios of the concentrations of the chemical constituents were, however, altered after the regulation. EC/TC was significantly decreased from 56.7% to 50.2% (p = 0.039). Although it was not statistically significant, the percentage of fossil carbon in EC also decreased (67.8% to 63.8%; p = 0.104). Since EC is predominantly of combustion origin, the observed decrease was likely due to the decrease in fossil EC emissions from diesel-powered vehicles. The decrease in EC/TC after the implementation of the regulation was also likely to have resulted from attachment to diesel vehicle exhaust systems of particulate filters as required as part of the regulation by the Tokyo Metropolitan Government. The EC/TC of fossil carbon of the finest particles decreased from 66.2% to 55.2% (p = 0.066), but EC/TC of biomass carbon did not decrease but rose slightly from 43.6% to 44.5% (p > 0.5). Thus, the relative ratios of components of carbonaceous aerosol particles, such as 14C, could provide a better understanding of the atmospheric pollution status, despite short-term fluctuations, than do measurements of absolute concentrations.