As a key component in overhead cables, insulators play an important role. However, in the process of insulator inspection, due to background interference, small fault area, limitations of manual detection, and other factors, detection is difficult, has low accuracy, and is prone to missed detection and false detection. To detect insulator defects more accurately, the insulator defect detection algorithm based on You Only Look Once version 5 (YOLOv5) is proposed. A backbone network was built with lightweight modules to reduce network computing overhead. The small-scale network detection layer was increased to improve the network for small target detection accuracy. A receptive field module was designed to replace the original spatial pyramid pooling (SPP) module so that the network can obtain feature information and improve network performance. Finally, experiments were carried out on the insulator image dataset. The experimental results show that the average accuracy of the algorithm is 97.4%, which is 7% higher than that of the original YOLOv5 network, and the detection speed is increased by 10 fps, which improves the accuracy and speed of insulator detection.

To improve the positioning accuracy and reliability of autonomous navigation agricultural machinery and reduce the cost of high-precision positioning, an integrated navigation system based on Real-Time Dynamic Kinematic BeiDou Navigation Satellite System (RTK-BDS) and Inertial Navigation System (INS) is designed in this study. On the one hand, an autonomous navigation control board is designed and made in the system, which integrates BDS high-precision analysis module, Inertial Measurement Unit (IMU) module, and radio module, and realizes the integrated navigation algorithm on the control board. On the other hand, low-cost RTK technology is realized by building differential reference stations and vehicle-mounted mobile stations. Experiments are carried out on actual farm machinery under different road conditions including open road, signal-shielded road, and urban congested road. According to the angular velocity and acceleration information from INS and the position and velocity information from the BDS high-precision analysis module, the system uses Kalman filter algorithm for data fusion to calculate the precise position, velocity, and attitude information of agricultural machinery in real time. The experimental results show that the position error of the integrated navigation system on the open road is within 3 cm, the azimuth error is within 0.6°, and the inclination error is within 1°, all of which converge rapidly when encountering bad road conditions. It can be known from the experimental results that the RTK-BDS/INS integrated navigation system has high positioning accuracy, strong adaptive anti-interference ability, and low implementation cost of RTK technology, which provides a reliable way for automatic navigation control of agricultural machinery.

No abstract

Agricultural equipment works poorly under low illumination such as nighttime, and there is more noise in soybean plant images collected under light constraints, and the reconstructed soybean plant model cannot fully and accurately represent its growth condition. In this paper, we propose a low-illumination soybean plant reconstruction and trait perception method. Our method is based on low-illumination enhancement, using the image enhancement algorithm EnlightenGAN to adjust soybean plant images in low-illumination environments to improve the performance of the scale-invariant feature transform (SIFT) algorithm for soybean plant feature detection and matching and using the motion recovery structure (SFM) algorithm to generate the sparse point cloud of soybean plants, and the point cloud of the soybean plants is densified by the face slice-based multi-view stereo (PMVS) algorithm. We demonstrate that the reconstructed soybean plants are close to the growth conditions of real soybean plants by image enhancement in challenging low-illumination environments, expanding the application of three-dimensional reconstruction techniques for soybean plant trait perception, and our approach is aimed toward achieving the accurate perception of current crop growth conditions by agricultural equipment under low illumination.