Superpixel-based appearance change prediction for long-term navigation across seasons

Changing environments pose a serious problem to current robotic systems aiming at long term operation under varying seasons or local weather conditions. This paper is built on our previous work where we propose to learn to predict the changes in an environment. Our key insight is that the occurring scene changes are in part systematic, repeatable and therefore predictable. The goal of our work is to support existing approaches to place recognition by learning how the visual appearance of an environment changes over time and by using this learned knowledge to predict its appearance under different environmental conditions. We describe the general idea of appearance change prediction (ACP) and investigate properties of our novel implementation based on vocabularies of superpixels (SP-ACP). Our previous work showed that the proposed approach significantly improves the performance of SeqSLAM and BRIEF-Gist for place recognition on a subset of the Nordland dataset under extremely different environmental conditions in summer and winter. This paper deepens the understanding of the proposed SP-ACP system and evaluates the influence of its parameters. We present the results of a large-scale experiment on the complete 10 h Nordland dataset and appearance change predictions between different combinations of seasons.

Minnie’s Bow-Toons seasons 2 and 3

Minnie’s Bow-Toons follows the adventures of Minnie Mouse and her best friend Daisy Duck as they run Minnie's Bow-tique, a specialty shop stocked only with colorful bows and bowties. In the third season Minnie, Daisy and their assistant Cuckoo Loca opens a pet grooming salon adjacent to the Bow-tique. In the fourth season Minnie, Daisy and Cuckoo Loca travel around the world, visiting cities like London, Venice and Tokyo.

Genetics of heifer performance in 'wet' and 'dry' seasons and their relationships with steer performance in two tropical beef genotypes.

The genetics of heifer performance in tropical 'wet' and 'dry' seasons, and relationships with steer performance, were studied in Brahman (BRAH) and Tropical Composite (TCOMP) (50% Bos indicus, African Sanga or other tropically adapted Bos taurus; 50% non-tropically adapted Bos taurus) cattle of northern Australia. Data were from 2159 heifers (1027 BRAH, 1132 TCOMP), representing 54 BRAH and 51 TCOMP sires. Heifers were assessed after post-weaning 'wet' (ENDWET) and 'dry' (ENDDRY) seasons. Steers were assessed post-weaning, at feedlot entry, over a 70-day feed test, and after similar to 120-day finishing. Measures studied in both heifers and steers were liveweight (LWT), scanned rump fat, rib fat and M. longissimus area (SEMA), body condition score (CS), hip height (HH), serum insulin-like growth factor-I concentration (IGF-I), and average daily gains (ADG). Additional steer measures were scanned intra-muscular fat%, flight time, and daily (DFI) and residual feed intake (RFI). Uni- and bivariate analyses were conducted for combined genotypes and for individual genotypes. Genotype means were predicted for a subset of data involving 34 BRAH and 26 TCOMP sires. A meta-analysis of genetic correlation estimates examined how these were related to the difference between measurement environments for specific traits. There were genotype differences at the level of means, variances and genetic correlations. BRAH heifers were significantly (P < 0.05) faster-growing in the 'wet' season, slower-growing in the 'dry' season, lighter at ENDDRY, and taller and fatter with greater CS and IGF-I at both ENDWET and ENDDRY. Heritabilities were generally in the 20 to 60% range for both genotypes. Phenotypic and genetic variances, and genetic correlations, were commonly lower for BRAH. Differences were often explained by the long period of tropical adaptation of B. indicus. Genetic correlations were high between corresponding measures at ENDWET and ENDDRY, positive between fat and muscle measures in TCOMP but negative in BRAH (mean of 13 estimates 0.50 and -0.19, respectively), and approximately zero between steer feedlot ADG and heifer ADG in BRAH. Numerous genetic correlations between heifers and steers differed substantially from unity, especially in BRAH, suggesting there may be scope to select differently in the sexes where that would aid the differing roles of heifers and steers in production. Genetic correlations declined as measurement environments became more different, the rates of decline (environment sensitivity) sometimes differing with genotype. Similar measures (LWT, HH and ADG; IGF-I at ENDWET in TCOMP) were genetically correlated with steer DFI in heifers as in steers. Heifer SEMA was genetically correlated with steer feedlot RFI in BRAH (0.75 +/- 0.27 at ENDWET, 0.66 +/- 0.24 at ENDDRY). Selection to reduce steer RFI would reduce SEMA in BRAH heifers but otherwise have only small effects on heifers before their first joining.

Estimating winter crop area across seasons and regions using time-sequential MODIS imagery.

The wheat grain industry is Australia's second largest agricultural export commodity. There is an increasing demand for accurate, objective and near real-time crop production information by industry. The advent of the Moderate Resolution Imaging Spectroradiometer (MODIS) satellite platform has augmented the capability of satellite-based applications to capture reflectance over large areas at acceptable pixel scale, cost and accuracy. The use of multi-temporal MODIS-enhanced vegetation index (EVI) imagery to determine crop area was investigated in this article. Here the rigour of the harmonic analysis of time-series (HANTS) and early-season metric approaches was assessed when extrapolating over the entire Queensland (QLD) cropping region for the 2005 and 2006 seasons. Early-season crop area estimates, at least 4 months before harvest, produced high accuracy at pixel and regional scales with percent errors of -8.6% and -26% for the 2005 and 2006 seasons, respectively. In discriminating among crops at pixel and regional scale, the HANTS approach showed high accuracy. The errors for specific area estimates for wheat, barley and chickpea were 9.9%, -5.2% and 10.9% (for 2005) and -2.8%, -78% and 64% (for 2006), respectively. Area estimates of total winter crop, wheat, barley and chickpea resulted in coefficient of determination (R(2)) values of 0.92, 0.89, 0.82 and 0.52, when contrasted against the actual shire-scale data. A significantly high coefficient of determination (0.87) was achieved for total winter crop area estimates in August across all shires for the 2006 season. Furthermore, the HANTS approach showed high accuracy in discriminating cropping area from non-cropping area and highlighted the need for accurate and up-to-date land use maps. The extrapolability of these approaches to determine total and specific winter crop area estimates, well before flowering, showed good utility across larger areas and seasons. Hence, it is envisaged that this technology might be transferable to different regions across Australia.

Spawning seasons of Rasbora tawarensis (Pisces: Cyprinidae) in Lake Laut Tawar, Aceh Province, Indonesia

Rasbora tawarensis is an endemic freshwater fish in Lake Laut Tawar, Aceh Province, Indonesia. Unfortunately, its status is regarded a critical endangered with populations decreasing in recent years. To date no information on the spawning activities of the fish are available. Therefore, this study provides a contribution to the. knowledge on reproductive biology of R. tawarensis especially on spawning seasons as well as basic information for conservation of the species. Monthly sampling was conducted from April 2008 to March 2009 by using selective gillnets. The gonadosomatic index, size composition and sex ratio were assessed. The gonadal development was evaluated based on macroscopic and microscopic examinations of the gonads. The gonadosomatic index (GSI) varied between 6.65 to 18.16 in female and 4.94 to 8.56 for male. GSI of the female R. tawarensis was higher in March, September and December indicating the onset of reproductive seasons, the GSI and oocyte size being directly correlated with gonadal development stages. Although, a greater proportion of mature male than female was detected during the study, the sex ratio showed that the overall number of female was higher than male. The ovaries had multiple oocyte size classes at every stage of gonadal development, thus R. tawarensis can be classified as a group synchronous spawner or a fractional multiple spawner. The spawning seasons of R. tawarensis were three times a year and September being the peak of the reproductive season and the female was the predominant sex. This species is classified as a group synchronous spawner. (PDF contains 8 pages)

Circulation pattern of the Egyptian Mediterranean waters during winter and summer seasons

The water circulation of the Egyptian Mediterranean waters was computed during winter and summer seasons using the dynamic method. The reference level was set at the 1000db surface. The results showed that the surface circulation is dominated by the Atlantic water inflow along the North African coast and by two major gyres, the Mersa Matruth anticyclonic gyre and El-Arish cyclonic gyre. The results showed a seasonal reversal of El-Arish gyre, being cyclonic in winter and anticyclonic in summer. El-Arish gyre had not been previously measured. The geostrophic current velocity at the edges of the Mersa Matruth gyre varied between 12.5 and 29.1cm/sec in winter and between 6.5 and 13.1cm/sec in summer. The current velocity reached its maximum values (>40cm/sec) at El-Arish gyre. The current velocity at the two gyres decreased with increasing depth. The North African Current affects the surface waters down to a depth of 100m, and that its mean velocity varies between 6 and 38cm/sec.

On the troll line investigations off Cochin during five fishing seasons. Pt. 1. Investigations during 1960-61 and 1961-62 seasons

There is apparently great scope for improvement of the design and operational aspects of the gear particularly for the effective exploitation of seasonal fisheries like that of seer, tuna, barracuda etc. In order to evolve improved, yet cheap trolling gear regular investigations were undertaken by the Craft & Gear Wing of the Central Institute of Fisheries Technology, off Cochin for five fishing seasons and the results of these studies are incorporated in this paper.

On the troll line investigations off Cochin during five fishing seasons. Pt. 2. Investigations during 1963-64 season

During this season the investigations were mainly directed towards elucidation of the selective action of trolling lures. Feather jigs, buffalo horn jigs, stainless steel jigs, Japanese whale bone jigs and plastic jigs were selected. Operations were carried out from Fisheries technology No. 5.

On the troll line investigations off Cochin during five fishing seasons. Pt. 3. Investigations during 1965-66 and 1966-67 seasons

During these two seasons investigations were carried out with a view to exploring the possibility of this operation on commercial basis and to study the effect of certain meteorological factors on catch.

Heat budget studies of the north Arabian Sea during summer and winter seasons, 1992

In this study heat budget components and momentum flux for August and January 1992 over the north Arabian Sea are computed. The marine meteorological data measured on board during the cruises of PAK-US joint project (NASEER) are used for the computation. Significant differences were found in the heat budget components as well as in the momentum flux during different monsoon periods over the north Arabian Sea. The latent heat flux was always positive and attributed to the large vapour pressure gradient. The computed moisture and latent heat fluxes in January were higher than August The highest value of latent heat flux 309 W/m2 at station 8 was evaluated. These higher latent heat fluxes were due to the large vapour pressure gradient, air-sea temperature difference, the wind speed, and the prevailing wind direction (from north and northeast). Negative values of sensible heat fluxes in both seasons indicate that the heat transfer was from the atmosphere to the ocean. The negative values of net heat gain indicate that the sea surface field became an energy sink: or the sea surface supplied more energy to the atmosphere than it received from it. Large variation in the momentum flux mainly attributed to the variation in the wind speed. Aerial averages of heat and momentum fluxes were also computed.