Search

In recent years, semantic segmentation of high-resolution remote sensing images has been gradually applied to many important scenes. However, with the rapid development of remote sensing data acquisition technology, the existing image data processing methods are facing major challenges. Especially in the accuracy of extraction and the integrity of the edges of objects, there are often problems such as small objects being assimilated by large objects. In order to solve the above problems, based on the excellent performance of Transformer, convolution and its variants, and feature pyramids in the field of deep learning image segmentation, we designed two encoders with excellent performance to extract global high-order interactive features and low-order local feature information. These encoders are then used as the backbone to construct a global and local feature fusion network with a dual encoder (GLFFNet) to effectively complete the segmentation of remote sensing images. Furthermore, a new auxiliary training module is proposed that uses the semantic attention layer to process the extracted feature maps separately, adjust the losses, and more specifically optimize each encoder of the backbone, thus optimizing the training process of the entire network. A large number of experiments show that our model achieves 87.96% mIoU on the Potsdam dataset and 80.42% mIoU on the GID dataset, and it has superior performance compared with some state-of-the-art methods on semantic segmentation tasks in the field of remote sensing. [ABSTRACT FROM AUTHOR]

In autonomous driving, LiDAR (light detection and ranging) data are acquired over time. Most existing 3D object detection algorithms propose the object bounding box by processing each frame of data independently, which ignores the temporal sequence information. However, the temporal sequence information is usually helpful to detect the object with missing shape information due to long distance or occlusion. To address this problem, we propose a temporal sequence information fusion 3D point cloud object detection algorithm based on the Ada-GRU (adaptive gated recurrent unit). In this method, the feature of each frame for the LiDAR point cloud is extracted through the backbone network and is fed to the Ada-GRU together with the hidden features of the previous frames. Compared to the traditional GRU, the Ada-GRU can adjust the gating mechanism adaptively during the training process by introducing the adaptive activation function. The Ada-GRU outputs the temporal sequence fusion features to predict the 3D object in the current frame and transmits the hidden features of the current frame to the next frame. At the same time, the label uncertainty of the distant and occluded objects affects the training effect of the model. For this problem, this paper proposes a probability distribution model of 3D bounding box coordinates based on the Gaussian distribution function and designs the corresponding bounding box loss function to enable the model to learn and estimate the uncertainty of the positioning of the bounding box coordinates, so as to remove the bounding box with large positioning uncertainty in the post-processing stage to reduce the false positive rate. Finally, the experiments show that the methods proposed in this paper improve the accuracy of the object detection without significantly increasing the complexity of the algorithm. [ABSTRACT FROM AUTHOR]

With the rapid development of deep learning, more and more complex models are applied to 3D point cloud object detection to improve accuracy. In general, the more complex the model, the better the performance and the greater the computational resource consumption it has. However, complex models are incompatible for deployment on edge devices with restricted memory, so accurate and efficient 3D point cloud object detection processing is necessary. Recently, a lightweight model design has been proposed as one type of effective model compression that aims to design more efficient network computing methods. In this paper, a lightweight 3D point cloud object detection network architecture is proposed. The core innovation of the proposal consists of a lightweight 3D sparse convolution layer module (LW-Sconv module) and knowledge distillation loss. Firstly, in the LW-Sconv module, factorized convolution and group convolution are applied to the standard 3D sparse convolution layer. As the basic component of the lightweight 3D point cloud object detection network proposed in this paper, the LW-Sconv module greatly reduces the complexity of the network. Then, the knowledge distillation loss is used to guide the training of the lightweight network proposed in this paper to further improve the detection accuracy. Finally, extensive experiments are performed to verify the algorithm proposed in this paper. Compared with the baseline model, the proposed model can reduce the FLOPs and parameters by 3.7 times and 7.9 times, respectively. The lightweight model trained with knowledge distillation loss achieves comparable accuracy to the baseline. Experiments show that the proposed method greatly reduces the model complexity while ensuring detection accuracy. [ABSTRACT FROM AUTHOR]