Search

Head Pose Estimation (HPE) has a wide range of applications in computer vision, but still faces challenges: (1) Existing studies commonly use Euler angles or quaternions as pose labels, which may lead to discontinuity problems. (2) HPE does not effectively address regression via rotated matrices. (3) There is a low recognition rate in complex scenes, high computational requirements, etc. This paper presents an improved unconstrained HPE model to address these challenges. First, a rotation matrix form is introduced to solve the problem of unclear rotation labels. Second, a continuous 6D rotation matrix representation is used for efficient and robust direct regression. The RepVGG-A2 lightweight framework is used for feature extraction, and by adding a multi-level feature fusion module and a coordinate attention mechanism with residual connection, to improve the network's ability to perceive contextual information and pay attention to features. The model's accuracy was further improved by replacing the network activation function and improving the loss function. Experiments on the BIWI dataset 7:3 dividing the training and test sets show that the average absolute error of HPE for the proposed network model is 2.41. Trained on the dataset 300W_LP and tested on the AFLW2000 and BIWI datasets, the average absolute errors of HPE of the proposed network model are 4.34 and 3.93. The experimental results demonstrate that the improved network has better HPE performance. [ABSTRACT FROM AUTHOR]

Lane detection is one of the difficulties in implementing an advanced driving assistance system. In this paper, we show that the existing single frame-based algorithm suffers from the problem of unsatisfied detection result, which is directly caused by some extremely poor road environments (such as severe shadow occlusion and severe fading). To solve the problem, this paper proposes a multi-lane detection method based on the improved U-SegNet model. In order to get better feature extraction results, the number of network layers of the U-SegNet model is deepened, and a many-to-many structure is also proposed to improve the recognition rate of the algorithm. During the training stage, continuous multiple frames are input into the RNN module to get the feature maps for feature learning and prediction. The proposed method is tested on Caltech lane marking dataset, the results show that the proposed algorithm has good robustness and real-time performance, the multi-lane marking can be better detected under most complex road conditions, and the average detecting accuracy can achieve 96.95%. [ABSTRACT FROM AUTHOR]

Aerial image-based target detection has problems such as low accuracy in multiscale target detection situations, slow detection speed, missed targets and falsely detected targets. To solve this problem, this paper proposes a detection algorithm based on the improved You Only Look Once (YOLO)v3 network architecture from the perspective of model efficiency and applies it to multiscale image-based target detection. First, the K-means clustering algorithm is used to cluster an aerial dataset and optimize the anchor frame parameters of the network to improve the effectiveness of target detection. Second, the feature extraction method of the algorithm is improved, and a feature fusion method is used to establish a multiscale (large-, medium-, and small-scale) prediction layer, which mitigates the problem of small target information loss in deep networks and improves the detection accuracy of the algorithm. Finally, label regularization processing is performed on the predicted value, the generalized intersection over union (GIoU) is used as the bounding box regression loss function, and the focal loss function is integrated into the bounding box confidence loss function, which not only improves the target detection accuracy but also effectively reduces the false detection rate and missed target rate of the algorithm. An experimental comparison on the RSOD and NWPU VHR-10 aerial datasets shows that the detection effect of high-efficiency YOLO (HE-YOLO) is significantly improved compared with that of YOLOv3, and the average detection accuracies are increased by 8.92% and 7.79% on the two datasets, respectively. The algorithm not only shows better detection performance for multiscale targets but also reduces the missed target rate and false detection rate and has good robustness and generalizability. [ABSTRACT FROM AUTHOR]

Recently, deep learning has become a promising technique for constructing gesture recognition classifiers from surface electromyography (sEMG) signals in human–computer interaction. In this paper, we propose a gesture recognition method with sEMG signals based on a deep multi-parallel convolutional neural network (CNN), which solves the problem that traditional machine learning methods may lose too much useful information during feature extraction. CNNs provide an efficient way to constrain the complexity of feedforward neural networks by weight sharing and restriction to local connections. Sophisticated feature extraction is to be avoided and hand gestures are to be classified directly. A multi-parallel and multi-convolution layer convolution structure is proposed to classify hand gestures. Experiment results show that in comparison with five traditional machine learning methods, the proposed method could achieve higher accuracy. [ABSTRACT FROM AUTHOR]

Denoising autoencoder is a data compression algorithm in deep learning, and it can successfully extract features which contain main information of the input data. However, this method is trained in an unsupervised manner and cannot aim at extracting the specified information. Therefore, the input data will be classified into a class label by main but not necessary information using traditional denoising autoencoder, and redundant information reduces the classification accuracy. To solve this problem, denoising class autoencoder presented in this paper is adopted to train a classification function and extract class features. Both the proposed approach and traditional methods are trained on MNIST handwritten digit database with mini-batch gradient descent, moreover the recognition result of the proposed approach demonstrates the effectiveness in comparison with conventional methods. [ABSTRACT FROM AUTHOR]

For the problem that the limited star map field angle cannot obtain the complete star map accurately, the paper study astral intrinsic and imaging features, a star map stitching algorithm based on the principle of visual perception is proposed firstly. The matching models of time and space dimensions is constructed by simulating the visual perception, then the stars and the planets points are saved by searching the matching star group dynamically, the star map is stitched and reconstructed efficiently by creating the computer sparse storage model. The experimental results show that the algorithm can achieve data compression quickly, compression ratio is 99.54%, which can reduce complexity of manual processing and can achieve star map stitching accurately. [ABSTRACT FROM AUTHOR]

Handwriting, printed character recognition is an interesting area in image processing and pattern recognition. It consists of a number of phases which are preprocessing, feature extraction and classification. The phase of feature extraction is carried out by different techniques; zoning, profile projection, and ameliored Freeman. The high number of features vector can increase the error rate and the training time. So, to solve this problem, we present in this paper a new method of selecting attributes based on the evolution strategy in order to reduce the feature vector dimension and to improve the recognition rate. The proposed model has been applied to recognize numerals and it obtained a better results and showed more robustness than without the selection system. [ABSTRACT FROM AUTHOR]

The text content of Aviation Safety Confidential Reports contains a large number of valuable information. Term frequency-inverse document frequency algorithm is commonly used in text analysis, but it does not take into account the sequential relationship of the words in the text and its role in semantic expression. According to the seven category labels of civil aviation unsafe incidents, aiming at solving the problems of TF-IDF algorithm, this paper improved TF-IDF algorithm based on co-occurrence network; established feature words extraction and words sequential relations for classified incidents. Aviation domain lexicon was used to improve the accuracy rate of classification. Feature words network model was designed for multi-documents unsafe incidents classification, and it was used in the experiment. Finally, the classification accuracy of improved algorithm was verified by the experiments. [ABSTRACT FROM AUTHOR]

Identifying influential nodes is of theoretical significance in many domains. Although lots of methods have been proposed to solve this problem, their evaluations are under single-source attack in scale-free networks. Meanwhile, some researches have speculated that the combinations of some methods may achieve more optimal results. In order to evaluate this speculation and design a universal strategy suitable for different types of networks under the consideration of multi-source attacks, this paper proposes an attribute fusion method with two independent strategies to reveal the correlation of existing ranking methods and indicators. One is based on feature union (FU) and the other is based on feature ranking (FR). Two different propagation models in the fields of recommendation system and network immunization are used to simulate the efficiency of our proposed method. Experimental results show that our method can enlarge information spreading and restrain virus propagation in the application of recommendation system and network immunization in different types of networks under the condition of multi-source attacks. [ABSTRACT FROM AUTHOR]

The self-organizing map (SOM) is a traditional neural network algorithm used to achieve feature extraction, clustering, visualization and data exploration. However, it is known that the computational cost of the traditional SOM, used to search for the winner neuron, is expensive especially in case of treating high-dimensional data. In this paper, we propose a novel hierarchical SOM search algorithm which significantly reduces the expensive computational cost associated with traditional SOM. It is shown here that the computational cost of the proposed approach, compared to traditional SOM, to search for the winner neuron is reduced into O(D1 + D2 + ⋯ + DN) instead of O(D1 × D2 × ⋯ × DN), where Dj is the number of neurons through a dimension dj of the feature map. At the same time, the new algorithm maintains all merits and qualities of the traditional SOM. Experimental results show that the proposed algorithm is a good alternate to traditional SOM, especially, in high-dimensional feature space problems. [ABSTRACT FROM AUTHOR]