The influence of weather and solar elevation on perceived colour of Blue Lake, Mount Gambier, South Australia

Previous studies of the remarkable seasonal colour changes of Blue Lake, Mount Gambier, South Australia have speculated on the roles of weather and solar elevation in this phenomenon. In this study the influence of weather and solar elevation on apparent colour is examined. Solar elevation and some weather variables were found to have a statistically significant influence, particularly when Blue Lake is undergoing transition from its blue to grey stage. However, the proportion of the overall variation in colour explained by solar elevation and weather was only 16%, so it is concluded that in-lake properties are probably the main determinants of colour.

Machine vision system for automatic inspection of surface defects in aluminum die casting

A camera based machine vision system for the automatic inspection of surface defects in aluminum die casting is presented. The system uses a hybrid image processing algorithm based on mathematic morphology to detect defects with different sizes and shapes. The defect inspection algorithm consists of two parts. One is a parameter learning algorithm, in which a genetic algorithm is used to extract optimal structuring element parameters, and segmentation and noise removal thresholds. The second part is a defect detection algorithm, in which the parameters obtained by a genetic algorithm are used for morphological operations. The machine vision system has been applied in an industrial setting to detect two types of casting defects: parts mix-up and any defects on the surface of castings. The system performs with a 99% or higher accuracy for both part mix-up and defect detection and is currently used in industry as part of normal production.

High reproducibility of patellar tendon vascularity assessed by colour doppler ultrasonography : a reliable measurement tool for quantifying tendon pathology

Background: This study examined whether patellar tendon vascularity could be quantified accurately in the clinical setting using colour Doppler ultrasonography.

Methods: A sonographer and two radiologists visually estimated tendon vascularity in millimetres in 74 tendons during ultrasound (US) examination and from hard copy films. These estimates were then compared to the length of vessels measured from the digital image in millimetres and the correlation between them was determined. A subset of 16 tendons was used to compare the estimates of vascularity by two examiners at US examination.

Results: The estimation of vascular length at US examination correlated highly with the measured vascular length (r = 0.92; 95% confidence interval (CI) 0.87 to 0.94), as did the length estimated from the films (r = 0.94; 95% CI 0.9 to 0.96). The correlation between examiners was 0.84 (95% CI 0.51 to 0.94) for the estimates made during US examination and 0.85 (95% CI 0.59 to 0.95) for the vessel lengths measured from the digital images.

Conclusions: These excellent correlations indicate that tendon vascularity can be reliably estimated using colour Doppler ultrasonography and tendon vascularity could therefore be used by clinicians to rate clinical change. This method of quantifying tendon vascularity could also be used in research to investigate the effects of tendon treatments on vascularity.

An active stereo vision-based learning approach for robotic tracking, fixating and grasping control

In this paper, an active stereo vision-based learning approach is proposed for a robot to track, fixate and grasp an object in unknown environments. First, the functional mapping relationships between the joint angles of the active stereo vision system and the spatial representations of the object are derived and expressed in a three-dimensional workspace frame. Next, the self-adaptive resonance theory-based neural networks and the feedforward neural networks are used to learn the mapping relationships in a self-organized way. Then, the approach is verified by simulation using the models of an active stereo vision system which is installed in the end-effector of a robot. Finally, the simulation results confirm the effectiveness of the present approach.

Mcommerce - a vision in time

Global mCommerce revenues are expected to grow from $400 million in 2000, to 22.2 billion by 2005 (Raczkowski, 2002) mCommerce is a key driver in developing the global information society, with applications emerging in numerous areas including banking, financial services, security services and shopping (Khalifa and Cheng, 2002). With optimistic projections regarding its growth, many researchers are actively determining the future of mCommerce. In this paper, we have tried to synthesise some predictions and evolving definitions, explored security as a critical impediment and developing solutions; investigated the mPayment scenario; and derived a futuristic research framework. Specifically, we have attempted to capture the moving mCommerce scenario in present time, with a special focus into mPayments.

Machine vision system for automatic inspection of surface defects in aluminium die casting

A machine vision system is presented for the automatic inspection of surface defects in aluminium die casting. The system uses a hybrid image processing algorithm based on mathematic morphology to detect defects with different sizes and shapes. The defect inspection algorithm consists of two parts. One is a parameter learning algorithm, in which a genetic algorithm is used to extract optimal structuring element parameters, and segmentation and noise removal thresholds. The second part is a defect detection algorithm, in which the parameters obtained by a genetic algorithm are used for morphological operations. The machine vision system has been applied in an industrial setting to detect two types of casting defects: parts mix-up and any defects on the surface of castings. The system performs with a 99% or higher accuracy for both part mix-up and defect detection and is currently used in industry as part of normal production.

Effect of cage colour and light environment on the skin colour of Australian Snapper Pagrus auratus (Bloch & Schneider, 1801)

A two-factor experiment was performed to evaluate the effects of cage colour (black or white 0.5 m³ experiment cages) and light environment (natural sunlight or reduced level of natural sunlight) on the skin colour of darkened Australian snapper. Each treatment was replicated four times and each replicate cage was stocked with five snapper (mean weight=351 g). Snapper exposed to natural sunlight were held in experimental cages located in outdoor tanks. An approximately 70% reduction in natural sunlight (measured as PAR) was established by holding snapper in experimental cages that were housed inside a 'shade-house' enclosure. The skin colour of anaesthetized fish was measured at stocking and after a 2-, 7- and 14-day exposure using a digital chroma-meter (Minolta CR-10) that quantified skin colour according to the L*a*b* colour space. At the conclusion of the experiment, fish were killed in salt water ice slurry and post-mortem skin colour was quantified after 0.75, 6 and 22 h respectively. In addition to these trials, an ad hoc market appraisal of chilled snapper (mean weight=409 g) that had been held in either white or in black cages was conducted at two local fish markets. Irrespective of the sampling time, skin lightness (L*) was significantly affected by cage colour (P<0.05), with fish in white cages having much higher L* values (L*≈64) than fish held in black cages (L*≈49). However, the value of L* was not significantly affected by the light environment or the interaction between cage colour and the light environment. In general, the L* values of anaesthetized snapper were sustained post mortem, but there were linear reductions in the a* (red) and b* (yellow) skin colour values of chilled snapper over time. According to the commercial buyers interviewed, chilled snapper that had been reared for a short period of time in white cages could demand a premium of 10–50% above the prices paid for similar-sized snapper reared in black cages. Our results demonstrate that short-term use of white cages can reduce the dark skin colour of farmed snapper, potentially improving the profitability of snapper farming.

Stereo-vision-based moving object tracking via robust linear filtering

Vision-based tracking sensors typically provide nonlinear measurements
of the targets Cartesian position and velocity state components. In this paper we derive linear measurements using an analytical measurement conversion technique which can be used with two (or more) vision sensors. We derive
linear measurements in the target’s Cartesian position and velocity components and we derive a robust version of a linear Kalman filter. We show that our linear robust filter significantly outperforms the extended Kalman Filter. Moreover, we prove that the state estimation error is bounded.

Vision based target tracking using robust linear filtering

The use of perspective projection in tracking a target from a video stream involves nonlinear observations. The target dynamics, however, are modeled in Cartesian coordinates and result in a linear system. In this paper we provide a robust version of a linear Kalman filter and perform a measurement conversion technique on the nonlinear optical measurements. We show that our linear robust filter significantly outperforms the Extended Kalman Filter. Moreover, we prove that the state estimation error is bounded in a probabilistic sense.

Depth estimation using multi-wavelet analysis based stereo vision approach

The problem of dimensional defects in aluminum die- casting is widespread throughout the foundry industry and their detection is of paramount importance in maintaining product quality. Due to the unpredictable factory environment and metallic, with highly reflective, nature of aluminum die-castings, it is extremely hard to estimate true dimensionality of the die-casting, autonomously. In this work, we propose a novel robust 3D reconstruction algorithm capable of reconstructing dimensionally accurate 3D depth models of the aluminum die-castings. The developed system is very simple and cost effective as it consists of only a stereo cameras pair and a simple fluorescent light. The developed system is capable of estimating surface depths within the tolerance of 1.5 mm. Moreover, the system is invariant to illuminative variations and orientation of the objects in the input image space, which makes the developed system highly robust. Due to its hardware simplicity and robustness, it can be implemented in different factory environments without a significant change in the setup.