Search

Fast and accurate counting of wheat ears in field conditions is a key element for determining wheat yield. To obtain the number of wheat ears in a field, we propose a new counting algorithm based on computer vision. This algorithm counts wheat ears in remote images through semantic segmentation regression network (SSRNet). SSRNet is a multistage convolutional neural network that we propose to achieve counting problems through regression. In SSRNet, first, the original image is cropped to increase the amount of data. This method effectively solves the small sample dataset. Next, based on the cropping results, we build a fully convolutional neural network (FCNN) to segment wheat ears in field conditions. FCNN increases the accuracy of wheat ears counting by accurately segmenting wheat ears in a complex background. Then, we build a regression convolutional neural network (RCNN) to count wheat ears based on the segmentation results of FCNN. In RCNN, we propose a new activation function positive rectification linear unit (PrLU) to process the last layer of the fully connected layer, so that RCNN can effectively count the number of wheat ears in the image. Finally, a counting strategy is proposed to count the number of wheat ears in the original image. To verify the counting performance of SSRNet, we compare the counting result of SSRNet with the real value of manual statistics. The results show that the average accuracy (Acc), R², and root mean squared error (RMSE) of the SSRNet count results on the test set in this article are 0.980, 0.996, and 9.437, respectively. It can be seen from the results that our proposed method can accurately count wheat ears in field conditions. At the same time, the counting time (0.11 s) shows that SSRNet can quickly estimate the number of wheat ears in field conditions. We concluded that this study can provide important technical support for the high-throughput field wheat ears counting task in large-scale phenotyping work.

As an important part of higher learning, experimental teaching plays a significant role in developing innovative and applied talents. In the traditional mode of experiment teaching , there are some obvious disadvantages in the excavation of students' self-initiative. Consequently, developing a mobile learning system becomes more necessary. As android intelligent mobile platform is characterized by efficiency and intelligence, this paper will introduce how to make use of it to build an Android-based mobile learning system for experimental teaching, realizing the experimental information publishing, online learning, experiment reservation and teacher-student communication. The system has features of convenience, individualized instruction and ample interaction, which allows learners access to learning conveniently and flexibly, aggregate fragmented space-time. Also it gets teachers and students closer, more personalized and more fruitful interaction. With the purpose to improve the quality of experimental teaching, this research puts forward some ideas and sums up some experience in promoting the reform of the experimental teaching methods.

Parking space monitoring algorithm serves to constantly and correctly update parking information which is vulnerable to the influences of shadows of surrounding objects and weather conditions through image processing. By analyzing and comparing various parking space detection algorithms, this paper selects the most suitable algorithm to achieve parking space detection in Nios II soft core embedded in FPGA. The algorithm can accurately and quickly reflect the change of state of parking spaces and can ensure real-time processing. After detection of parking spaces, real time status of parking spaces and parking guidance information will be displayed via VGA.