Currently, single-stage point-based 3D object detection network remains underexplored. Many approaches worked on point cloud space without optimization and failed to capture the relationships among neighboring point sets. In this paper, we propose DCGNN, a novel single-stage 3D object detection network based on density clustering and graph neural networks. DCGNN utilizes density clustering ball query to partition the point cloud space and exploits local and global relationships by graph neural networks. Density clustering ball query optimizes the point cloud space partitioned by the original ball query approach to ensure the key point sets containing more detailed features of objects. Graph neural networks are very suitable for exploiting relationships among points and point sets. Additionally, as a single-stage 3D object detection network, DCGNN achieved fast inference speed. We evaluate our DCGNN on the KITTI dataset. Compared with the state-of-the-art approaches, the proposed DCGNN achieved better balance between detection performance and inference time.

Numerous human actions such as “Phoning,” “PlayingGuitar,” and “RidingHorse” can be inferred by static cue-based approaches even if their motions in video are available considering one single still image may already sufficiently explain a particular action. In this research, we investigate human action recognition in still images and utilize deep ensemble learning to automatically decompose the body pose and perceive its background information. Firstly, we construct an end-to-end NCNN-based model by attaching the nonsequential convolutional neural network (NCNN) module to the top of the pretrained model. The nonsequential network topology of NCNN can separately learn the spatial- and channel-wise features with parallel branches, which helps improve the model performance. Subsequently, in order to further exploit the advantage of the nonsequential topology, we propose an end-to-end deep ensemble learning based on the weight optimization (DELWO) model. It contributes to fusing the deep information derived from multiple models automatically from the data. Finally, we design the deep ensemble learning based on voting strategy (DELVS) model to pool together multiple deep models with weighted coefficients to obtain a better prediction. More importantly, the model complexity can be reduced by lessening the number of trainable parameters, thereby effectively mitigating overfitting issues of the model in small datasets to some extent. We conduct experiments in Li’s action dataset, uncropped and 1.5x cropped Willow action datasets, and the results have validated the effectiveness and robustness of our proposed models in terms of mitigating overfitting issues in small datasets. Finally, we open source our code for the model in GitHub (https://github.com/yxchspring/deep_ensemble_learning) in order to share our model with the community.

Object 3D reconstruction from a single-view image is an ill-posed problem. Inferring the self-occluded part of an object makes 3D reconstruction a challenging and ambiguous task. In this paper, we propose a novel neural network for generating a 3D-object point cloud model from a single-view image. The proposed network named 3D-ReConstnet, an end to end reconstruction network. The 3D-ReConstnet uses the residual network to extract the features of a 2D input image and gets a feature vector. To deal with the uncertainty of the self-occluded part of an object, the 3D-ReConstnet uses the Gaussian probability distribution learned from the feature vector to predict the point cloud. The 3D-ReConstnet can generate the determined 3D output for a 2D image with sufficient information, and 3D-ReConstnet can also generate semantically different 3D reconstructions for the self-occluded or ambiguous part of an object.We evaluated the proposed 3D-ReConstnet on ShapeNet and Pix3D dataset, and obtained satisfactory improved results.

Network traffic classification based on machine learning is an important branch of pattern recognition in computer science. It is a key technology for dynamic intelligent network management and enhanced network controllability. However, the traffic classification methods still facing severe challenges: The optimal set of features is difficult to determine. The classification method is highly dependent on the effective characteristic combination. Meanwhile, it is also important to balance the experience risk and generalization ability of the classifier. In this paper, an improved network traffic classification model based on a support vector machine is proposed. First, a filter-wrapper hybrid feature selection method is proposed to solve the false deletion of combined features caused by a traditional feature selection method. Second, to balance the empirical risk and generalization ability of support vector machine (SVM) traffic classification model, an improved parameter optimization algorithm is proposed. The algorithm can dynamically adjust the quadratic search area, reduce the density of quadratic mesh generation, improve the search efficiency of the algorithm, and prevent the over-fitting while optimizing the parameters. The experiments show that the improved traffic classification model achieves higher classification accuracy, lower dimension and shorter elapsed time and performs significantly better than traditional SVM and the other three typical supervised ML algorithms.

We proposed a new method of gist feature extraction for building recognition and named the feature extracted by this method as the histogram of oriented gradient based gist (HOG-gist). The proposed method individually computes the normalized histograms of multiorientation gradients for the same image with four different scales. The traditional approach uses the Gabor filters with four angles and four different scales to extract orientation gist feature vectors from an image. Our method, in contrast, uses the normalized histogram of oriented gradient as orientation gist feature vectors of the same image. These HOG-based orientation gist vectors, combined with intensity and color gist feature vectors, are the proposed HOG-gist vectors. In general, the HOG-gist contains four multiorientation histograms (four orientation gist feature vectors), and its texture description ability is stronger than that of the traditional gist using Gabor filters with four angles. Experimental results using Sheffield Buildings Database verify the feasibility and effectiveness of the proposed HOG-gist.