Search

In order to solve the problems of large number of parameters and high GPU resource cost in binocular vision stereo matching method based on neural network in robot and unmanned driving fields, this paper proposed a multi-scale aggregation stereo matching method. Firstly, this paper proposed a multi-scale feature extraction network to obtain richer features without changing the resolution by using dilated convolution, and introduced the attention mechanism was. Then, features at different resolutions were cross-fused to improve the feature information. Secondly, the acquisition method of cost volume was changed, the cost volume was obtained by aggregation at low scale, and continuously combined the high-scale similar information to update iteratively, and cross fused multiple cost volumes to obtain the final cost volume. Finally, combined with the refinement module of attention mechanism, the outliers and discontinuous regions in the initial disparity map are corrected to obtain the final disparity map. Experimental results show that the algorithm can run under low parameter number and low cost GPU resources, and obtain good matching accuracy. [ABSTRACT FROM AUTHOR]

Most of the existing steganalysis methods have weak generalization ability and cannot effectively detect unknown steganalysis algorithms, which makes the accuracy of their classification greatly reduced in the practical application process. To solve this problem, this paper proposed an image steganalysis method based on group convolution and snapshot ensembling（Snapshot Ensembling steganalysis network, SENet）. Firstly, residual convolution block and group convolution block are used to extract the features of the image. Secondly, the model with the best performance is obtained as the snapshot model in each training period. Finally, the selected snapshot models are integrated to classify the images. This method uses the techniques of group convolution and snapshot ensembling to avoid the high training cost of traditional integration methods and the limited generalization ability of a single classifier. Experimental results show that this method can improve the accuracy of steganographic analysis model, and can effectively classify when the training set and test set are mismatched, and has high model generalization ability. [ABSTRACT FROM AUTHOR]

Single-view 3D reconstruction based on deep learning is a research hot spot at present. In order to discover more high-frequency details, SDF-SRN algorithm introduces positional encoding, but neural network is easy to overfit without accurate supervision, and reconstructs uneven surface. To solve the problem, this paper proposed the network model based on sparse feature. The model enabled the network that preferred to overfitting to predict high-frequency residual by residual learning. The feature extraction network extracted sparse features and the global features. Then one hypernetwork took the sparse features as input and generated prediction shallow head. This shallow head predicted low-frequency part of signed distance function. Another hypernetwork took global features as input and generated another shallow head. This shallow head predicted high-frequency residual. It fused two predictions of shallow heads into final signed distance function. Spectrum analysis shows that the design purpose of network is achieved. Compared with other smooth surface reconstruction schemes, the network can achieve smoother surface reconstruction with enough details. It overcomes the overfitting of SDF-SRN. The qualitative and quantitative comparison with other advanced single-view reconstruction approaches show the superiority of the proposed approach. [ABSTRACT FROM AUTHOR]

The current ADMET classification methods have shortcomings in classifying the ADMET of compounds data with multiple characteristics and feature correlation. Moreover, the classification results of ADMET are not explainable. To solve these problems, this paper proposed a classification model based on capsule network（CapsMC). CapsMC model first proposed the Feature-to-Image algorithm. It used this algorithm to consider the correlation and dependence between features into the classification basis, and realized the multi-level extraction of features. Second, it explored the advanced application of capsule network, and designed a cognitive reasoning mechanism. It used this mechanism to carry out cognitive reasoning on features, and realized explainable classification of ADMET. Experimental results on five ADMET datasets show that CapsMC can achieve the explainable classification of ADMET well. [ABSTRACT FROM AUTHOR]

Aiming at the problem of missing detection and false detection caused by inaccurate motion feature extraction of existing video key frame extraction algorithms, this paper proposed a reinforcement learning key frame extraction algorithm combining multi-channel feature and attention mechanism. The algorithm extracted the human skeleton joint points from the video sequence through the human posture recognition algorithm firstly. Then it used the S-GCN and ResNet50 network to extract the motion features and static features in the video sequence respectively, and performed a weighted fusion of the two. Finally, it applied the attention mechanism to calculate the importance of the video frame of the feature sequence, and used reinforcement learning to extract and optimize key frames. The experimental results show that the algorithm can solve the problem of missing and false detection in the key frame extraction of motion video. It performs well in the detection of video frames containing key actions, with high accuracy and strong stability. [ABSTRACT FROM AUTHOR]

To solve the problems of difficult initialization and low positioning accuracy of SLAM algorithm caused by sparse feature points and fast camera movement in practical application scenes, this paper proposed a visual-inertial SLAM algorithm. It used EDLines feature extraction and matching algorithm to introduce rich line features to improve the robustness of feature tracking. Using the complementary advantages of the inertial sensor and the visual sensor, it carried out the optimization in three steps in the initial stage through the visual-inertial initialization by steps method, so as to improve the accuracy and speed of the initialization. Experiments show that the line feature extraction and matching algorithm used in this algorithm provides faster matching speed and lower mismatching rate than the traditional LSD algorithm. Moreover, the proposed algorithm has higher accuracy and stronger robustness in the estimation of camera pose in the visual-inertial data set. [ABSTRACT FROM AUTHOR]

The traditional curvature calculation method is sensitive to local changes and noise in the discrete domain, which makes the corner detection accuracy and location deviate. In order to solve the above problems, a multi-scale discrete curvature is proposed to calculate the curvature and detect corners. Firstly, Canny edge detector was used to process the input image to obtain a binary edge image, then the edge contour was extracted from the edge image, the gap was filled along the contour, and T-shaped corners were detected and marked. Secondly, under three different smoothing scales, Gaussian function was used to smooth each plane curve, and then a new curvature measurement method was used to calculate the curvature of each point on each contour after smoothing, and the local maximum point of absolute curvature was taken as the candidate corner point of each scale. Finally, the curvature value of candidate corners was compared with the curvature threshold. The points greater than the curvature threshold were defined as candidate real corners, and the candidate corners that could be detected at three scales were regarded as real corners. The experimental results show that when the algorithm is used to detect the standard corner data laboratory image, the correct corner number is 159, the wrong corner number is 90, the missing corner number is 16, and the localization error is 1.257 2,and that when the standard corner data block image is tested, the detected correct corner number is 46, the wrong corner number is 13, the missing corner number is 1, and the localization error is 1.013 2.Compared with the existing three classical corner detection algorithms, the detection method in this paper has better corner detection performance. [ABSTRACT FROM AUTHOR]