Microbial community and functional genes in the rhizosphere of alfalfa in crude oil-contaminated soil

A rhizobox system constructed with crude oil- contaminated soil was vegetated with alfalfa （Medicago sativa L.） to evaluate the rhizosphere effects on the soil microbial population and functional structure, and to explore the potential mechanisms by which plants enhance the removal of crude oil in soil. During the 80-day experiment, 31.6% of oil was removed from the adjacent rhizosphere （AR）; this value was 27% and 53% higher than the percentage of oil removed from the far rhizosphere （FR） and from the non-rhizosphere （NR）, respectively. The populations of heterotrophic bacteria and hydrocarbon- degrading bacteria were higher in the AR and FR than in the NR. However, the removal rate of crude oil was positively correlated with the proportion of hydrocarbon- degrading bacteria in the rhizosphere. In total, 796, 731, and 379 functional genes were detected by microarray in the AR, FR, and NR, respectively. Higher proportions of functional genes related to carbon degradation and organic remediation, were found in rhizosphere soil compared with NR soil, suggesting that the rhizosphere selectively increased the abundance of these specific functional genes. The increase in water-holding capacity and decrease in pH as well as salinity of the soil all followed the order of AR 〉 FR 〉 NR. Canonical component analysis showed that salinity was the most important environmental factor influencing the microbial functional structure in the rhizosphere and that salinity was negatively correlated with the abundance of carbon and organic degradation genes.

A three-stage real-time detector for traffic signs in large panoramas

Traffic sign detection is one of the key components in autonomous driving.Advanced autonomous vehicles armed with high quality sensors capture high definition images for further analysis.Detecting traffic signs,moving vehicles,and lanes is important for localization and decision making.Traffic signs,especially those that are far from the camera,are small,and so are challenging to traditional object detection methods.In this work,in order to reduce computational cost and improve detection performance,we split the large input images into small blocks and then recognize traffic signs in the blocks using another detection module.Therefore,this paper proposes a three-stage traffic sign detector,which connects a Block Net with an RPN–RCNN detection network.Block Net,which is composed of a set of CNN layers,is capable of performing block-level foreground detection,making inferences in less than 1 ms.Then,the RPN–RCNN two-stage detector is used to identify traffic sign objects in each block;it is trained on a derived dataset named TT100 KPatch.Experiments show that our framework can achieve both state-of-the-art accuracy and recall;its fastest detection speed is 102 fps.