Search

On-line detection of fault characteristic gases released by the insulation oil of transformers is developed as a scientific basis for estimating explosion accidents. However, the performance of most gas sensors, such as H2 and C2H2 sensors, is usually affected by temperature, and there exists large detection error when the temperature of transformer oil changes in operation. And the existing temperature compensation methods suffer from problems such as low integration, large volume, and high costs. Herein, a sensor array based on three triple-electrode sensors with carbon nanotubes was fabricated. Each of the three sensors has three vertically stacked electrodes with various interelectrode distances. The first and second sensors were used to detect H2 and C2H2, respectively, and the third sensor was used to measure temperature. All the detection mechanisms are based on the dependence of discharge current on gas concentration and temperature. The sensor array could detect H2/C2H2 mixture and temperature due to the exponential function between the output currents and electrode separations. The proposed sensor exhibited low relative and repeatability error values less than 5.1% and 4.9%, respectively, and displayed humidity compensation potential like temperature. High integration makes the sensor array superior among the other mechanism sensors.

Accurate acquisition of the canopy information of fruit trees is very important for the precise variable spray of modern orchards. Using drones to obtain fruit tree canopy images is a better nondestructive method, but the lighting conditions in the orchard are complex. It is difficult to quickly extract the canopy of fruit trees from the aerial images of orchard by UAV, which can be used to guide UAV to apply pesticide in real time and accurately. Therefore, we propose a method for canopy segmentation of fruit tree canopy images using SegNet network model. We use images obtained from modern orchards to verify the accuracy and real time of the network, and use four indicators to compare our network model with Unet and FCN-8s network models: accuracy, precision, recall and harmonic average. After that, we optimize the SegNet network model structure from three aspects: input method, network training parameters and neural network structure. The results show that SegNet has achieved satisfactory results in segmenting the canopy. The optimized SegNet model has an average recognition accuracy of 95.30%, and the recognition time of a single image is as low as 0.045 s, and it has good robustness in both strong and weak light environments. This shows that using SegNet network segmentation to extract fruit tree canopy information is a promising method, and it can provide a reference for real-time and accurate spray of UAVs.

Highly effective pesticide applications require a continual adjustment of the pesticide spray flow rate that attends to different canopy characterizations. Real-time image processing with rapid target detection and data-processing technologies is vital for precision pesticide application. However, the extant studies do not provide an efficient and reliable method of extracting individual trees with irregular tree-crown shapes and complicated backgrounds. This paper on our study proposes a Mahalanobis distance and conditional random field (CRF)-based segmentation model to extract cherry trees accurately in a natural orchard environment. This study computed Mahalanobis distance from the image’s color, brightness and location features to acquire an initial classification of the canopy and background. A CRF was then created by using the Mahalanobis distance calculations as unary potential energy and the Gaussian kernel function based on the image color and pixels distance as binary potential energy. Finally, the study completed image segmentation using mean-field approximation. The results show that the proposed method displays a higher accuracy rate than the traditional algorithms K-means and GrabCut algorithms and lower labeling and training costs than the deep learning algorithm DeepLabv3+, with 92.1%, 94.5% and 93.3% of the average P, R and F1-score, respectively. Moreover, experiments on datasets with different overlap conditions and image acquisition times, as well as in different years and seasons, show that this method performs well under complex background conditions, with an average F1-score higher than 87.7%.

To minimize pesticide dosage and its adverse environmental impact, Unmanned Aerial Vehicle (UAV) spraying requires precise individual canopy information. Branches from neighboring trees may overlap, preventing image-based artificial intelligence analysis from correctly identifying individual trees. To solve this problem, this paper proposes a segmentation and evaluation method for mingled fruit tree canopies with irregular shapes. To extract the individual trees from mingled canopies, the study fitted the projection curve distribution of the interlacing tree with Gaussian Mixture Model (GMM) and solved the matter of segmentation by estimating the GMM parameters. For the intermingling degree assessment, the Gaussian parameters were used to quantify the characteristics of the mingled fruit trees and then as the input for Extreme Gradient Boosting (XGBoost) model training. The proposed method was tested on the aerial images of cherry and apple trees. Results of the experiments show that the proposed method can not only accurately identify individual trees, but also estimate the intermingledness of the interlacing canopies. The root mean squares (R) of the over-segmentation rate (Ro) and under-segmentation rate (Ru) for individual trees counting were less than 10%. Moreover, the Intersection over Union (IoU), used to evaluate the integrity of a single canopy area, was greater than 88%. An 84.3% Accuracy (ACC) with a standard deviation of 1.2% was achieved by the assessment model. This method will supply more accurate data of individual canopy for spray volume assessments or other precision-based applications in orchards.

Diabetic retinopathy (DR) is one of the leading causes of vision loss and can be effectively avoided by screening, early diagnosis and treatment. In order to increase the universality and efficiency of DR screening, many efforts have been invested in developing intelligent screening, and there have been great advances. In this paper, we survey DR screening from four perspectives: 1) public color fundus image datasets of DR; 2) DR classification and related lesion-extraction approaches; 3) existing computer-aided systems for DR screening; and 4) existing issues, challenges, and research trends. Our goal is to provide insights for future research directions on DR intelligent screening.