Search

Abstract For citrus trees cultivated by dwarf dense planting, the fruits are randomly distributed in space, which poses difficulties for mechanized picking. To improve picking efficiency, a citrus picking system based on dual robot collaboration is designed and a global scanning picking scheme that scans the entire fruit tree to achieve orderly fruit picking is proposed in this research. The dual‐robot calibration with the iterative method and closed‐form method is completed in the research. The picking problem is attributed to the single traveling salesman problem, and the trajectory planning and the picking task are completed with genetic algorithm in the research. The picking experiments are designed in the research. As a result, in the picking experiments, the average time for planning the picking sequence of citrus was 0.1184 s, the longest time is 0.1560 s. In each group of citrus picking experiments, the total picking time averaged 158.9 s, the longest group took 170 s, the picking success rate is 82%. The picking results show that the built dual‐machine system can effectively complete the picking task and meet the real‐time requirement of picking. The proposed dual‐robot picking system can provide a reference for the establishment of other picking robot system.

In remote sensing image classification task, it is often apply a model trained on one dataset (source domain) to another dataset (target domain). However, due to the presence of domain shift between these domains where data are not independent and identically distributed, the performance of the model typically deteriorates. Domain adaptation aims to improve the generalization performance of the model in the target domain. In response to the challenges of intricate backgrounds, domain shift, and potentially unlabeled target domain in remote sensing images, this article proposes a network specifically designed for unsupervised domain adaptation (UDA) classification of remote sensing images, named PPLM-net. The network consists of a domain adversarial training (DAT) module, a partial patch local masking (PPLM) module and a teacher–student network module. The DAT module enables the network to extract domain-invariant features. The PPLM module compels the model to focus on the global information of target domain remote sensing images with intricate backgrounds, learning contextual content to improve model performance. The teacher network generates pseudolabels for complete unlabeled target domain images. The student network trained with PPLM target domain classification loss to generate robust and discriminative features. We construct a dataset dedicated to the UDA scene classification task of remote sensing images named RSDA. We collect images from four publicly available datasets spanning seven common categories, containing over 10 000 images. Compared with the current state-of-the-art UDA model, PPLM-net achieves the best results in 12 domain adaptation classification tasks on RSDA. The average accuracy reaches 99.115%.

In the detection of building changes in high spatial-resolution remote sensing images, both the distribution position and surface characteristics of the same objects are probably different under different imaging phases, which potentially causes high false positives. In order to improve the detection accuracy of building changes, an integration network, named R&D net is proposed in this article, which comprises a registration network (R-net) followed by a change detection network (D-net). In R-net, two different phase images are accepted as inputs, corner points and their descriptors are generated to spatially align those images. After that, the spatially aligned images are fed into the D-net, and building images are detected accordingly. In this article, a multiview automatic labeling method is proposed to obtain labeling corner points. A new dataset containing 5104 image pairs is established. Experimental results demonstrate that the R-net can extract robust invariant features, and then improve registration accuracy under circumstances with obvious changes of surface feature, which is a base of D-net. Uniting pyramid pooling structure with a focal loss function in D-net, both leaky and wrong segmentations can be dramatically improved under complex scenes with many interferences. When compared with baseline methods on different high-resolution remote sensing scenes, the proposed method achieves better performance and more accurate detection results of building changes.

Instance segmentation in remote sensing images (RSI) poses significant challenges due to the diverse scales of targets, scene complexity, and a high number of targets, making most methods struggle with suboptimal performance and time-consuming computations. To solve those problems, a fast and accurate RSI instance segmentation model (named DCTC) is designed in this article. DCTC transforms classification problem into regression problem to improve the reference speed. DCTC contains two parallel branches. The contour branch performs iterative regression on contours, extracting precise contour information to improve boundary accuracy. Meanwhile, the discrete cosine transformation (DCT) branch refines mask predictions and supplements instance context information, which particularly benefits the segmentation of small targets. DCT encoding is employed in the DCT branch to convert the mask representation into DCT format, aligning the outputs of the contour and DCT branches. Three innovative modules are introduced in the DCT branch: the coarse result generation (CRG) module, iteratively deform and regression (IDR) module, and contour and DCT fusion module (CDF). The CRG module generates coarse DCT vectors and contour coordinates, facilitating information exchange between the contour and DCT branches. The IDR module iteratively refines DCT vectors, enabling DCTC to focus more on small targets and instance details. The CDF module merges DCT vectors and contour coordinates, ensuring effective interaction between boundary and context information, thereby enhancing performance. Extensive experiments demonstrate the superiority of DCTC, which achieves 67.7, 36.3, 67.4, and 55.1AP on NWPU VHR-10, iSAID, synthetic aperture radar (SAR) ship detection dataset, and high-resolution SAR images dataset, respectively, and ranks first among state-of-the-art methods while maintaining real-time processing capability. Furthermore, DCTC exhibits strong performance on both optical and SAR images, and the designed DCT branch can be simply plug into any contour-based method to improve the network performance.

The precise and automatic cutting of sheep carcasses can improve the quality of mutton. Robots are widely used in meat processing because of their good repeatability and high precision. Two essential problems encountered in robot working of sheep carcass processing are robot calibration and cutting trajectory planning. A method of cutting sheep carcasses based on 3D point clouds with a dual-robot system was proposed in this study. The dual-robot system consists of a 3D scanning system, a fixing device for sheep carcasses, and a cutting robot. The calibration of the dual-robot system was completed by solving the matrix problem AXB=YCZ using the iterative method and the closed-form method. The 3D model of a sheep carcass was constructed using a 3D scanner. The cutting scheme of the cutting robot was planned based on the processed 3D point clouds. To show the feasibility of the proposed sheep carcass processing scheme, practical experiments were carried out. The results of the experiments show that the cutting robot can accurately perform the cutting actions according to the planned cutting scheme. The system proposed in this study can improve the efficiency and precision of sheep carcass cutting. [ABSTRACT FROM AUTHOR]