To enable the apple picking robot to quickly and accurately detect apples under the complex background in orchards, we propose an improved You Only Look Once version 4 (YOLOv4) model and data augmentation methods. Firstly, the crawler technology is utilized to collect pertinent apple images from the Internet for labeling. For the problem of insufficient image data caused by the random occlusion between leaves, in addition to traditional data augmentation techniques, a leaf illustration data augmentation method is proposed in this paper to accomplish data augmentation. Secondly, due to the large size and calculation of the YOLOv4 model, the backbone network Cross Stage Partial Darknet53 (CSPDarknet53) of the YOLOv4 model is replaced by EfficientNet, and convolution layer (Conv2D) is added to the three outputs to further adjust and extract the features, which make the model lighter and reduce the computational complexity. Finally, the apple detection experiment is performed on 2670 expanded samples. The test results show that the EfficientNet-B0-YOLOv4 model proposed in this paper has better detection performance than YOLOv3, YOLOv4, and Faster R-CNN with ResNet, which are state-of-the-art apple detection model. The average values of Recall, Precision, and F1 reach 97.43%, 95.52%, and 96.54% respectively, the average detection time per frame of the model is 0.338 s, which proves that the proposed method can be well applied in the vision system of picking robots in the apple industry.

Category-level object 6D pose estimation is essential for robotic manipulation, augmented reality and 3D scene understanding. It aims to accurately predict the translation and rotation of arbitrary shape instances from a given set of object classes without models of each instance. However, such estimation is cumbersome owing to the intra-class variation and the difficulty of accurately regressing dense correspondences between an observed point cloud and the reconstructed instance model from high-order and complex features. In this study, we propose a framework comprising geometry-guided instance-aware prior and multi-stage reconstruction networks to address these challenges. The geometry-guided instance-aware prior network can avoid unstable RGB data interference and robustly learn implicit relations on semantic and geometric information between the observed point cloud and prior. We take advantage of these potential relations using a transformer network to cope with the intra-class variation. Furthermore, the proposed multi-stage reconstruction network is designed to learn the residual of the preliminary reconstruction and improve the accuracy of predicting dense correspondences originating from the complex feature. The results of extensive experiments on a well-acknowledged benchmark for category-level 6D pose estimation demonstrate that our proposed method achieves a significant improvement in performance compared to previous methods.

Three-dimensional (3D) point cloud registration is a critical topic in 3D computer vision and remote sensing. Several algorithms based on deep learning techniques have recently tried to deal with indoor partial-to-partial point cloud registration by searching the correspondences between input point clouds. However, existing correspondence-based methods are vulnerable to noise and do not adequately exploit geometric information to extract features, resulting in incorrect correspondences. In this work, we develop a novel network using correspondence confidence and overlap scores to address these challenges. Specifically, we first introduce a feature interaction module that combines spatial structure information to encode unique geometric embedding, greatly enhancing the feature perception. Furthermore, we design a corresponding point matching module, which includes a two-stage point filtering strategy. This method effectively improves the ability to identify embedded inliers from outliers and accurately remove spurious matches, thus allowing the network to focus more on the accurate correspondences of overlapping regions. Extensive experiments on different benchmark datasets indicate that our network shows superior performance of indoor point cloud registration, especially in low overlap registration, with significant improvement over state-of-the-art (SOTA) methods. Our code can be found at https://github.com/tranceok/COPRNet.