To find an economical solution to infer the depth of the surrounding environment of unmanned agricultural vehicles (UAV), a lightweight depth estimation model called MonoDA based on a convolutional neural network is proposed. A series of sequential frames from monocular videos are used to train the model. The model is composed of two subnetworks—the depth estimation subnetwork and the pose estimation subnetwork. The former is a modified version of U-Net that reduces the number of bridges, while the latter takes EfficientNet-B0 as its backbone network to extract the features of sequential frames and predict the pose transformation relations between the frames. The self-supervised strategy is adopted during the training, which means the depth information labels of frames are not needed. Instead, the adjacent frames in the image sequence and the reprojection relation of the pose are used to train the model. Subnetworks’ outputs (depth map and pose relation) are used to reconstruct the input frame, then a self-supervised loss between the reconstructed input and the original input is calculated. Finally, the loss is employed to update the parameters of the two subnetworks through the backward pass. Several experiments are conducted to evaluate the model’s performance, and the results show that MonoDA has competitive accuracy over the KITTI raw dataset as well as our vineyard dataset. Besides, our method also possessed the advantage of non-sensitivity to color. On the computing platform of our UAV’s environment perceptual system NVIDIA JETSON TX2, the model could run at 18.92 FPS. To sum up, our approach provides an economical solution for depth estimation by using monocular cameras, which achieves a good trade-off between accuracy and speed and can be used as a novel auxiliary depth detection paradigm for UAVs.

IEC–LIBS could rapidly and sensitively detect different valence states of Cr in water and soil.

In 1960 the first ruby laser came out , after 40 years’ development, laser engraving technology has been widely used in various areas. This paper describes the characteristics of laser engraving, the advantages and applications in industries and study images of laser engraving key technologies in-depth from image processing, laser engraving process parameters and clean carbide processing , and JK-2030 CO2 laser engraving machines on paulownia color photos as examples for authentication, making laser engraving images more easily and efficiently .

As we all know, the whole life cycle of product knowledge reuse is the key to responded to market demanding, according to knowledge reuse of current research situation, this paper propose the idea of green of knowledge reuse and designs a green framework for the whole life cycle of knowledge reuse system. Accordance with operating mechanism of knowledge reuse system, we put forward a newly feasible structural framework for the knowledge reuse system. Applying for the software development platform of PowerBuilder and the database platform of SQL Server 2005 , we develop a prototype system of knowledge reuse.