Search

To improve foresight and make correct judgment in advance, pedestrian trajectory prediction has a wide range of application values in autonomous driving, robot interaction, and safety monitoring. However, most of the existing methods only focus on the interaction of local pedestrians according to distance, ignoring the influence of far pedestrians; the range of network input (receptive field) is small. In this paper, an extended graph attention network (EGAT) is proposed to increase receptive field, which focuses not only on local pedestrians, but also on those who are far away, to further strengthen pedestrian interaction. In the temporal domain, TSG-LSTM (TS-LSTM and TG-LSTM) and P-LSTM are proposed based on LSTM to enhance information transmission by residual connection. Compared with state-of-the-art methods, the model EGAT achieves excellent performance on both ETH and UCY public datasets and generates more reliable trajectories.

Action recognition is an important research direction of computer vision, whose performance based on video images is easily affected by factors such as background and light, while deep video images can better reduce interference and improve recognition accuracy. Therefore, this paper makes full use of video and deep skeleton data and proposes an RGB-D action recognition based two-stream network (SV-GCN), which can be described as a two-stream architecture that works with two different data. Proposed Nonlocal-stgcn (S-Stream) based on skeleton data, by adding nonlocal to obtain dependency relationship between a wider range of joints, to provide more rich skeleton point features for the model, proposed a video based Dilated-slowfastnet (V-Stream), which replaces traditional random sampling layer with dilated convolutional layers, which can make better use of depth the feature; finally, two stream information is fused to realize action recognition. The experimental results on NTU-RGB+D dataset show that proposed method significantly improves recognition accuracy and is superior to st-gcn and Slowfastnet in both CS and CV.

Compared with the bank card number of the flat font, the bank card number of the concave-convex font is not easily distinguishable from the background. The paper builds on the CTPN text area location, and uses the end-to-end identification network-CRNN to identify the concave-convex font. When training the data set, it is preprocessed by the convolution network to generate the corresponding feature model. When identifying, the test picture is processed by the same convolutional network as in the training, and the extracted picture features are compared with the picture features that generated during training, then the highest similarity is determined as the recognized number. The card number recognition accuracy of the concave-convex font can reach 92.33% when the card number is positioned accurately.

We develop an image reconstruction algorithm in this paper using inverse transformation of principal component residual to automatically detect the tire defects in its X-ray image. A tire X-ray image to be inspected is first transformed to a new coordinate system, i.e. principal component space, in which the k major components and their corresponding eigenvectors represent the dominant normal textures of tires; Unlike traditional principal component analysis, we set the k major component eigenvalues as zeros, then the above principal component space matrix is called principal component residual in this paper, which stands for none-dominant textures of tires that is considered as abnormal or defect textures. We perform inverse transformation of this principal component residual and reconstruct the defect left only image. To localize the defect part, binarization operation is processed on the obtained left over image with upper and lower thresholds statistically. The proposed scheme can both reveal the defect locations and also present defect patch shapes for identifications. The experiment results show the high effectiveness of our scheme in detecting defects for tire X-ray images.

Pedestrian tracking is a critical problem in the field of computer vision. Particle filters have been proven to be very useful in pedestrian tracking for nonlinear and non-Gaussian estimation problems. However, pedestrian tracking in complex environment is still facing many problems due to changes of pedestrian postures and scale, moving background, mutual occlusion, and presence of pedestrian. To surmount these difficulties, this paper presents tracking algorithm of multiple pedestrians based on particle filters in video sequences. The algorithm acquires confidence value of the object and the background through extracting a priori knowledge thus to achieve multipedestrian detection; it adopts color and texture features into particle filter to get better observation results and then automatically adjusts weight value of each feature according to current tracking environment. During the process of tracking, the algorithm processes severe occlusion condition to prevent drift and loss phenomena caused by object occlusion and associates detection results with particle state to propose discriminated method for object disappearance and emergence thus to achieve robust tracking of multiple pedestrians. Experimental verification and analysis in video sequences demonstrate that proposed algorithm improves the tracking performance and has better tracking results.

The objective of this study is to improve the accuracy in tire defect classification with limited training samples under varying illuminations. We investigate an algorithm based on deep learning to achieve high accuracy with limited samples. First, image contrast normalizations and data augmentation were used to avoid overfitting problems of the network with a large number of parameters. Furthermore, multi-column CNN is proposed by combining several CNNs trained on differently preprocessed data into a multi-column CNN (MC-CNN), and then their predictions are averaged as the output of the proposed network. An average accuracy of 98.47% is achieved with the proposed CNN-based method. Experimental results show that our scheme receives satisfactory classification accuracy and outperforms state-of-the-art methods on the same tire defect dataset.