Accurate silhouette segmentation using motion detection and graph cuts

Acquiring accurate silhouettes has many applications in computer vision. This is usually done through motion detection, or a simple background subtraction under highly controlled environments (i.e. chroma-key backgrounds). Lighting and contrast issues in typical outdoor or office environments make accurate segmentation very difficult in these scenes. In this paper, gradients are used in conjunction with intensity and colour to provide a robust segmentation of motion, after which graph cuts are utilised to refine the segmentation. The results presented using the ETISEO database demonstrate that an improved segmentation is achieved through the combined use of motion detection and graph cuts, particularly in complex scenes.

Accurate silhouettes for surveillance : improved motion segmentation using graph cuts

Silhouettes are common features used by many applications in computer vision. For many of these algorithms to perform optimally, accurately segmenting the objects of interest from the background to extract the silhouettes is essential. Motion segmentation is a popular technique to segment moving objects from the background, however such algorithms can be prone to poor segmentation, particularly in noisy or low contrast conditions. In this paper, the work of [3] combining motion detection with graph cuts, is extended into two novel implementations that aim to allow greater uncertainty in the output of the motion segmentation, providing a less restricted input to the graph cut algorithm. The proposed algorithms are evaluated on a portion of the ETISEO dataset using hand segmented ground truth data, and an improvement in performance over the motion segmentation alone and the baseline system of [3] is shown.

With budget cuts coming, ABC and SBS stand divided

Did SBS chief executive Michael Ebeid score a well-timed free kick or an own goal in his attack on the ABC this week? The ABC recently secured the free-to-air television rights for the Asian Cup football tournament to be held in Australia early next year, together with tonight’s match between the Socceroos and Japan. A lower bid by SBS – still in some circles fondly known as the “Soccer Broadcasting Service” – was rejected, dealing a significant blow to the smaller public broadcaster. The ABC was reportedly asked to make a bid by Football Federation Australia. The FFA presumably believes the ABC’s coverage will attract larger audiences to the game. This is despite SBS’s long-term success with the sport. It should not be forgotten, however, that while SBS has largely been defined by its long connection with the world game, ABC was the home of football from the late 1950s until the 1980s. But the stoush is only partly about football. It was surely no coincidence that it comes on the eve of the government’s formal announcement of the size of the cuts to public broadcasting...

Dietary intake in Australian children aged 4–24 months: Consumption of meat and meat alternatives

Meat/meat alternatives (M/MA) are key sources of Fe, Zn and protein, but intake tends to be low in young children. Australian recommendations state that Fe-rich foods, including M/MA, should be the first complementary foods offered to infants. The present paper reports M/MA consumption of Australian infants and toddlers, compares intake with guidelines, and suggests strategies to enhance adherence to those guidelines. Mother–infant dyads recruited as part of the NOURISH and South Australian Infants Dietary Intake studies provided 3 d of intake data at three time points: Time 1 (T1) (n 482, mean age 5·5 (SD 1·1) months), Time 2 (T2) (n 600, mean age 14·0 (SD 1·2) months) and Time 3 (T3) (n 533, mean age 24 (SD 0·7) months). Of 170 infants consuming solids and aged greater than 6 months at T1, 50 (29 %) consumed beef, lamb, veal (BLV) or pork on at least one of 3 d. Commercial infant foods containing BLV or poultry were the most common form of M/MA consumed at T1, whilst by T2 BLV mixed dishes (including pasta bolognaise) became more popular and remained so at T3. The processed M/MA increased in popularity over time, led by pork (including ham). The present study shows that M/MA are not being eaten by Australian infants or toddlers regularly enough; or in adequate quantities to meet recommendations; and that the form in which these foods are eaten can lead to smaller M/MA serve sizes and greater Na intake. Parents should be encouraged to offer M/MA in a recognisable form, as one of the first complementary foods, in order to increase acceptance at a later age.

Owning omega-3: Monsanto and the invention of meat

In August of 2010, Anna Salleh of the Science Unit of the Australian Broadcasting Corporation broke a story about Monsanto seeking to patent the enhancement of meat, including omega-3 fatty acids: ‘Enhanced port is sparking debate over the ethics of placing patents on food. Patent applications covering the enhancement of meat, including pork with omega-3 fatty acids, are stimulating debate over the ethics and legalities of claiming intellectual property over food. Monsanto has filed patents that cover the feeding of animals soybeans, which have been genetically modified by the company to contain stearidonic acid (SDA), a plant-derived omega-3 fatty acid... Omega-3s have been linked to improved cardiovascular health and there are many companies engineering them into foodstuffs. But the new patent applications have touched a raw nerve among those who see them as an attempt by the company to exert control over the food chain.’ This article providers a critical evaluation of the controversy of Monsanto’s patent applications, and the larger issues over patenting food. It first considers the patent portfolio of Monsanto; the nature of the patent claims; and the examination of the claims by patent examiners. Second, it examines the withdrawal and revision of the patent claims by Monsanto in the wake of criticism by patent authorities and the public disquiet over the controversial application. Third, this article considers the larger policy issues raised by Monsanto’s patent applications – including the patenting of plants, animals, and foodstuffs. There is also a consideration of the impact of patents upon the administration of health-care, competition, and research.

Modeling meat yield based on measurements of body traits in genetically improved giant freshwater prawn (GFP) Macrobrachium rosenbergii

A single-generation dataset consisting of 1,730 records from a selection program for high growth rate in giant freshwater prawn (GFP, Macrobrachium rosenbergii) was used to derive prediction equations for meat weight and meat yield. Models were based on body traits [body weight, total length and abdominal width (AW)] and carcass measurements (tail weight and exoskeleton-off weight). Lengths and width were adjusted for the systematic effects of selection line, male morphotypes and female reproductive status, and for the covariables of age at slaughter within sex and body weight. Body and meat weights adjusted for the same effects (except body weight) were used to calculate meat yield (expressed as percentage of tail weight/body weight and exoskeleton-off weight/body weight). The edible meat weight and yield in this GFP population ranged from 12 to 15 g and 37 to 45 %, respectively. The simple (Pearson) correlation coefficients between body traits (body weight, total length and AW) and meat weight were moderate to very high and positive (0.75–0.94), but the correlations between body traits and meat yield were negative (−0.47 to −0.74). There were strong linear positive relationships between measurements of body traits and meat weight, whereas relationships of body traits with meat yield were moderate and negative. Step-wise multiple regression analysis showed that the best model to predict meat weight included all body traits, with a coefficient of determination (R 2) of 0.99 and a correlation between observed and predicted values of meat weight of 0.99. The corresponding figures for meat yield were 0.91 and 0.95, respectively. Body weight or length was the best predictor of meat weight, explaining 91–94 % of observed variance when it was fitted alone in the model. By contrast, tail width explained a lower proportion (69–82 %) of total variance in the single trait models. It is concluded that in practical breeding programs, improvement of meat weight can be easily made through indirect selection for body trait combinations. The improvement of meat yield, albeit being more difficult, is possible by genetic means, with 91 % of the variation in the trait explained by the body and carcass traits examined in this study.

Brace yourself for a fatter, unhealthier Queensland after health promotion cuts

Queensland appears intent on dismantling its public and preventive health services. Health Minister Lawrence Springborg last week outlined the rationale for getting rid of more than 150 jobs in nutrition, health promotion and Indigenous health, arguing previous “campaigns” and “messaging” around obesity were “piecemeal” and had “grossly failed”. The plan now, the minister argued, is to focus on a new centrally-driven and high-profile approach...

Fraudsters change tactics as a crackdown cuts some losses due to online scams

The amount of financial loss from online fraud suffered by people in Western Australia has almost halved, dropping from A$16.8 million in 2014 to A$9.8 million for 2015, according to a statement this January from the state’s Attorney General and Minister for Commerce, Michael Mischin. In addition, the minister noted that losses from relationship and dating fraud have fallen by 55%, to A$4.9 million lost last year. These are both impressive claims, and at face value, there is truth to the statistics. Both assertions are based on data received by WA’s Scamnet, which is the public interface between consumer protection and citizens. While it is good to see a reduction in the number of losses overall, particularly to relationship and dating fraud, it is highly unlikely that the statistics tell the full story.