In this paper, we study the problem of monocular 3D human pose estimation based on deep learning. Due to single view limitations, the monocular human pose estimation cannot avoid the inherent occlusion problem. The common methods use the multi-view based 3D pose estimation method to solve this problem. However, single-view images cannot be used directly in multi-view methods, which greatly limits practical applications. To address the above-mentioned issues, we propose a novel end-to-end 3D pose estimation network for monocular 3D human pose estimation. First, we propose a multi-view pose generator to predict multi-view 2D poses from the 2D poses in a single view. Secondly, we propose a simple but effective data augmentation method for generating multi-view 2D pose annotations, on account of the existing datasets (e.g., Human3.6M, etc.) not containing a large number of 2D pose annotations in different views. Thirdly, we employ graph convolutional network to infer a 3D pose from multi-view 2D poses. From experiments conducted on public datasets, the results have verified the effectiveness of our method. Furthermore, the ablation studies show that our method improved the performance of existing 3D pose estimation networks.
Agricultural land extraction is an essential technical means to promote sustainable agricultural development and modernization research. Existing supervised algorithms rely on many finely annotated remote-sensing images, which is both time-consuming and expensive. One way to reduce the annotation cost approach is to migrate models trained on existing annotated data (source domain) to unannotated data (target domain). However, model generalization capability is often unsatisfactory due to the limit of the domain gap. In this work, we use an unsupervised adversarial domain adaptation method to train a neural network to close the gap between the source and target domains for unsupervised agricultural land extraction. The overall approach consists of two phases: inter-domain and intra-domain adaptation. In the inter-domain adaptation, we use a generative adversarial network (GAN) to reduce the inter-domain gap between the source domain (labeled dataset) and the target domain (unlabeled dataset). The transformer with robust long-range dependency modeling acts as the backbone of the generator. In addition, the multi-scale feature fusion (MSFF) module is designed in the generator to accommodate remote sensing datasets with different spatial resolutions. Further, we use an entropy-based approach to divide the target domain. The target domain is divided into two subdomains, easy split images and hard split images. By training against each other between the two subdomains, we reduce the intra-domain gap. Experiments results on the “DeepGlobe → LoveDA”, “GID → LoveDA” and “DeepGlobe → GID” unsupervised agricultural land extraction tasks demonstrate the effectiveness of our method and its superiority to other unsupervised domain adaptation techniques.
Carbon emissions caused by economic growth are the main cause of global warming, but controlling economic growth to reduce carbon emissions does not meet China's conditions. Therefore, how to synergize economic growth and carbon emission reduction is not only a sustainable development issue for China, but also significant for mitigating global warming. The territorial spatial functional pattern (TSFP) is the spatial carrier for coordinating economic development and carbon emissions, but how to establish the TSFP of synergizing economic growth and carbon emission reduction remains unresolved. We propose a decision framework for optimizing TSFP coupled with the multi-objective fuzzy linear programming and the patch-generating land use simulation model, to provide a new path to synergize economic growth and carbon emission reduction in China. To confirm the reliability, we took Qionglai City as the demonstration. The results found a significant spatiotemporal coupling between TSFP and the synergistic states between economic growth and carbon emission reduction (q ≥ 0.8220), which resolves the theoretical uncertainty about synergizing economic growth and carbon emission reduction through the path of TSFP optimization. The urban space of Qionglai City in 2025 and 2030 obtained by the decision framework was 6497.57 hm2 and 6628.72 hm2 respectively, distributed in the central and eastern regions; the rural space was 60,132.92 hm2 and 56,084.97 hm2, concentrated in the east, with a few located in the west; and the ecological space was 71,072.52 hm2 and 74,998.31 hm2, mainly located in the western and southeastern areas. Compared with the TSFP in 2020, the carbon emission intensity of the TSFP obtained by the decision framework was reduced by 0.7 and 4.7 tons/million yuan, respectively, and realized the synergy between economic growth and carbon emission reduction (decoupling index was 0.25 and 0.21). Further confirming that TSFP optimization is an effective way to synergize economic growth and carbon emission reduction, which can provide policy implications for coordinating economic growth and carbon emissions for China and even similar developing countries.
In recent years, convolutional neural networks (CNNs) have been widely used in hyperspectral image (HSI) classification. However, feature extraction on hyperspectral data still faces numerous challenges. Existing methods cannot extract spatial and spectral-channel contextual information in a targeted manner. In this paper, we propose an encoder–decoder network that fuses spatial attention and spectral-channel attention for HSI classification from three public HSI datasets to tackle these issues. In terms of feature information fusion, a multi-source attention mechanism including spatial and spectral-channel attention is proposed to encode the spatial and spectral multi-channels contextual information. Moreover, three fusion strategies are proposed to effectively utilize spatial and spectral-channel attention. They are direct aggregation, aggregation on feature space, and Hadamard product. In terms of network development, an encoder–decoder framework is employed for hyperspectral image classification. The encoder is a hierarchical transformer pipeline that can extract long-range context information. Both shallow local features and rich global semantic information are encoded through hierarchical feature expressions. The decoder consists of suitable upsampling, skip connection, and convolution blocks, which fuse multi-scale features efficiently. Compared with other state-of-the-art methods, our approach has greater performance in hyperspectral image classification.
Phenotypic analysis has always played an important role in breeding research. At present, wheat phenotypic analysis research mostly relies on high-precision instruments, which make the cost higher. Thanks to the development of 3D reconstruction technology, the reconstructed wheat 3D model can also be used for phenotypic analysis. In this paper, a method is proposed to reconstruct wheat 3D model based on semantic information. The method can generate the corresponding 3D point cloud model of wheat according to the semantic description. First, an object detection algorithm is used to detect the characteristics of some wheat phenotypes during the growth process. Second, the growth environment information and some phenotypic features of wheat are combined into semantic information. Third, text-to-image algorithm is used to generate the 2D image of wheat. Finally, the wheat in the 2D image is transformed into an abstract 3D point cloud and obtained a higher precision point cloud model using a deep learning algorithm. Extensive experiments indicate that the method reconstructs 3D models and has a heuristic effect on phenotypic analysis and breeding research by deep learning.
Hand pose estimation from 3D data is a key challenge in computer vision as well as an essential step for human–computer interaction. A lot of deep learning-based hand pose estimation methods have made significant progress but give less consideration to the inner interactions of input data, especially when consuming hand point clouds. Therefore, this paper proposes an end-to-end capsule-based hand pose estimation network (Capsule-HandNet), which processes hand point clouds directly with the consideration of structural relationships among local parts, including symmetry, junction, relative location, etc. Firstly, an encoder is adopted in Capsule-HandNet to extract multi-level features into the latent capsule by dynamic routing. The latent capsule represents the structural relationship information of the hand point cloud explicitly. Then, a decoder recovers a point cloud to fit the input hand point cloud via a latent capsule. This auto-encoder procedure is designed to ensure the effectiveness of the latent capsule. Finally, the hand pose is regressed from the combined feature, which consists of the global feature and the latent capsule. The Capsule-HandNet is evaluated on public hand pose datasets under the metrics of the mean error and the fraction of frames. The mean joint errors of Capsule-HandNet on MSRA and ICVL datasets reach 8.85 mm and 7.49 mm, respectively, and Capsule-HandNet outperforms the state-of-the-art methods on most thresholds under the fraction of frames metric. The experimental results demonstrate the effectiveness of Capsule-HandNet for 3D hand pose estimation.