Search

Obtaining near real-time road features is very important in emergent situations like flood and geological disaster cases. Remote sensing images with very high spatial resolution usually have many details in land use and land cover, which complicate the detection and extraction of road features. In this paper, we propose a deep residual deconvolutional network (Deep ResDCLnet), to extract road features from unmanned aerial vehicle (UAV) images. This proposed network is based on the deep neural network from SegNet architecture, the rich skip connection in a residual bottleneck, and the direct relationship among intermediate feature maps from the pixel deconvolution algorithm. It can improve the performance of a supervised learning model by differentiating and extracting complex road features on aerial photographs and UAV imagery. The proposed network is evaluated with the standard public Massachusetts road dataset and the UAV dataset collected alongside Yangtze River, and is compared with four state-of-art network architectures. The results show that the Deep ResDCLnet outperforms all four networks in terms of extraction accuracy, which demonstrates the effectiveness of the network in road extraction from very high spatial resolution imagery.

To study on the morphological character of cytology and physiological and biochemical mechanism of alfalfa cytoplasmic male sterile line, this paper took sterile line MS-GN1A and maintainer line MS-GN1B as raw material, separately conducted microscopic observation to anther in different development stage and determined the content of soluble sugar, starch, soluble protein, free proline and malondialdehyde, and the activity of antioxidant enzyme (catalase, peroxidase and superoxide dismutase). The results showed that: 1. Compared with maintainer line, the pollen grain of alfalfa cytoplasmic male sterile line presented shriveled appearance, smaller size with deletion and few; during the tetrad period of pollen, tapetum cell abnormally grew; callose and epidermis didn’t disintegrate and couldn’t release pollen grain; pollen abortion of alfalfa cytoplasmic sterile line was related to the abnormal development of connective vascular bundle. 2. With the growth and development of bud and the development and maturity of pollen, the content of soluble sugar, starch, soluble protein, and free proline showed deficient phenomenon in each development period of bud of sterile line MS-GN1A; as peroxidation index of membranous substance, the activity of malondialdehyde and antioxidant enzyme was higher than it of homotype maintainer line MS-GN1B.