International Journal of Pattern Recognition and Artificial Intelligence

In recent years, the workload of security offers has increased along with the requirement of anti-terrorism. In the paper, a series of evaluation index of security inspection based on the EEG signals of the security officers were proposed to improve the accuracy of dangerous instances detection and decrease the workload of the officers. We performed an experiment to record the EEG data of security officers when they were watching the picture with or without the dangerous item in the uncovered and obscured scenes. Brain network analysis based on graph theory was applied to generate the indexes from the EEG induced by the parcel picture of security inspection, and is a new perspective on the classification of the parcel composition. The paper studied the low-frequency, multi-channel experts EEG signals, calculated the phase locking value (PLV) between every two channels to construct the topological functional brain network (FBN). The appropriate binary FBNs were obtained by setting the thresholds, and then the complex brain network parameters were estimated by the graph-theoretic methods, which were used for classification with 10-fold cross-validation and the average accuracy was 83.3$\pm$97.78%. The method was effectively applied to the substance classification and would further improve the recognition accuracy of the target by combining this method with the existing detection technology.

Armored equipment plays a crucial role in the ground battlefield. The fast and accurate detection of enemy armored targets is significant to take the initiative in the battlefield. Comparing to general object detection and vehicle detection, armored target detection in battlefield environment is more challenging due to the long distance of observation and the complicated environment. In this paper, an accurate and robust automatic detection method is proposed to detect armored targets in battlefield environment. Firstly, inspired by Feature Pyramid Network (FPN), we propose a top-down aggregation (TDA) network which enhances shallow feature maps by aggregating semantic information from deeper layers. Then, using the proposed TDA network in a basic Faster R-CNN framework, we explore the further optimization of the approach for armored target detection: for the Region of Interest (RoI) Proposal Network (RPN), we propose a multi-branch RPNs framework to generate proposals that match the scale of armored targets and the specific receptive field of each aggregated layer and design hierarchical loss for the multi-branch RPNs; for RoI Classifier Network (RCN), we apply RoI pooling on the single finest scale feature map and construct a light and fast detection network. To evaluate our method, comparable experiments with state-of-art detection methods were conducted on a challenging dataset of images with armored targets. The experimental results demonstrate the effectiveness of the proposed method in terms of detection accuracy and recall rate.

Image segmentation as one of the primary steps in image analysis for object identification has received much attention lately, the main aim being to recognize homogeneous regions of an image which belong to different objects. A noise-robust edge detector SCHEME based on anisotropic Gaussian Kernels (ANGKs) is proposed in this paper by combining the region-merging algorithm to obtain higher quality segmentation results, which consist of three basic blocks. The first two blocks give rise to an initial partition of an image, while the last block attains the final segmentation by iteratively merging similar fragmented regions. A series of experiments is used to evaluate the performance of the method. The experimental results show that the proposed method has good noise robustness and localization accuracy, and can solve the problem of over-segmentation effectively, the simulation result supports our proposed main ideas.

In this paper, we propose an efficient Multi-Circle detector which follows the fixed search order. The method makes use of horizontal and vertical search to realize circle detection, which is named as HVCD. First, this method computes edge areas in a given image. The edge areas could be divided into some regions by means of region growing. Each of regions could be efficiently searched to achieve not only one-pixel wide edges but edge segments as well. Next, the candidate circles can be extracted from every edge segment. Finally, the circle candidates could be validated with the help of Helmholtz principle. Experimental results demonstrate that HVCD could effectively detect circles on synthetic and natural images on the one hand; on the other hand, HVCD here could solve the weakness in the process of circle Hough transform implementation and EDcircles implementation.

This paper proposes boundary parallel-like index (BPI) to describe shape features for high-resolution remote sensing image classification. Parallel-like boundary is found to be a discriminating clue which can reveal the shape regularity of segmented objects. Therefore, multi-orientation distance projections were constructed to measure and quantify parallel-like information. The discriminating ability was tested using original and segmented ground objects, respectively. The proposed BPI showed better discrimination for both original and segmented data than for other shape features, especially for buildings. This was also confirmed by the considerably higher accuracy of BPI in building classification experiments of high-resolution remote sensing imagery. It suggests the proposed BPI is useful for building related applications.

A reconstruction-based image processing algorithm is developed to automatically extract feature points of digitalized 2D objects. This algorithm, which is introduced using a bumblebee flight case, is made up of two parts: a four-connected dot chasing rearrangement scheme and an extreme point extraction on a polarized contour. It is then applied to a dune evolution case that is simulated with a cellular automation model. The results show that the proposed algorithm is effective in characterizing individual moving objects. An additional algorithm is developed to categorize the extracted feature points of a bumblebee with translucent wings.

To address the problem that many existing approaches are not appropriate for action recognition in low-resolution (LR) videos, this paper presents a framework based on the Dempster–Shafer (DS) theory for this purpose. In the framework, artificial neural networks (ANNs) are firstly trained for every class with training samples, and then basic belief assignments (BBAs) for underlying classes are computed with the trained ANNs. The resulted BBAs are fused from all frames in the whole video sequentially by frame-by-frame based on DS’s rule of fusion. Action recognition is last performed with a threshold-based decision making. We conducted experiments on extensive testing data with various levels of video resolution. Results reveal that the proposed framework: (1) shows outperforming recognition performances compared with state-of-the-art classifications, respectively, such as sequence matching, voting-based strategy and bag-of-words (BoW) method; and (2) can achieve a low observational latency in recognition.

With the development of biometric recognition technology, sketch face recognition has been widely applied to assist the police to confirm the identity of the criminal suspect. Most of the present recognition methods use the image features directly, in which the key parts can’t be used sufficiently. This paper presents a sketch face recognition method based on P-HOG multi-features weighted fusion. Firstly, the global face image and the local face image which contains key components of the face are divided into patches based on spatial scale pyramid, and then the global P-HOG features and local P-HOG features are extracted, respectively. After that, the dimensions of global and local features are reduced using PCA and NLDA. Finally, the features are weighted based on sensitivity and fused. The nearest neighbor classifier is used to complete the final recognition. The experimental results on different databases show that the proposed method outperforms state-of-the-art methods.

In this paper, a novel feature extraction method based on an improved color local binary pattern (LBP) is proposed for color face recognition. Firstly, in a given neighborhood of every pixel, we choose some sampling points from three color channels simultaneously and the numbers of the sampling points from every channel may be different. Secondly, we use a new rule to select the threshold which does not always locate in the geometrical center of the given neighborhood. Thirdly, in order to excavate the potential of the proposed sampling method, we use the $k$-uniform LBP to obtain the binary code of each pixel. In addition, we embed the Hamming distance into our method for improving the recognition rate of the proposed method. For evaluating the performance of our method, we implement the proposed method and several related methods on five public face databases: FERET, CMU-PIE, Georgia, FEI and Asian databases. Experimental results show that our method possesses higher recognition rates and lower computational cost than other related color face recognition methods.

With the recent increase in IP traffic owing to fiber communication, previous schemes have become inadequate for link-layer processing of IP over SONET/SDH(POS). In this study, a proposal based on $m$ processors to provide mapping or demapping of IP datagrams from or into SONET/SDH is presented, and the value of $m$ is decided based on the link layer rate of POS. Further, the mathematic model of proposed architecture are presented in detail. Then the realization procedures are implemented in a Field-Programmable Gate Array (FPGA). Both theoretical analysis and experimental test prove that the proposed scheme is efficient, portable, cost-efficient and has a lower hardware resources consumption.

To accurately analyze the dynamic characteristics of the wind turbine planetary gear system, a dynamic model is established. The sensitivity of natural frequency to meshing stiffness is calculated by modal analysis method, the coupling factor is used to judge the occurrence of transition, the parameter instability caused by the meshing stiffness change is analyzed by the multi-scale method. The results the change rule on eigenvalue sensitivity, mode transition criterion and coincidence degree variation instabilities are obtained, the obtained rules can be used for dynamic analysis and design optimization.

The acquisition, presentation and management of autonomous driving decision-making knowledge of unmanned vehicles are the key and difficult issues in the autonomous driving decision-making system of unmanned vehicles. This paper presents a knowledge model, which includes problem description layer and problem-solving knowledge layer. The automatic driving decision knowledge base of unmanned vehicle is composed of a set of knowledge models. Knowledge model supports knowledge representation and reasoning. Based on the WEB visualization knowledge modeling tool and visualization knowledge service tool, we construct the decision-making knowledge base management system for autonomous driving of unmanned vehicles and then construct the autonomous driving decision-making system of unmanned vehicles. The reasoning example shows that the knowledge base management system can effectively improve the knowledge acquisition, representation and maintenance efficiency of autonomous driving decision-making system, which is of great significance in enhancing the intelligence level of autonomous driving decision-making system.

The safety problem is the primary factor that should be viewed in the regenerative braking system design of vehicles. To ensure braking safety and battery safety of the electrical vehicles (EVs) a regenerative braking system contain us two fuzzy logic controllers is designed in the paper. In the system, one controller includes slip coefficient, vehicle speed and the driver’s brake requirement to ensure braking security and the other takes battery State of Charge (SOC) and temperature as inputs to assure battery safety. Then, two proportional coefficients $K_r$ and $K_b$ satisfying the safety needs are introduced into the braking system. At last, the simulation model is established in the simulation software-ADVISOR (ADvanced VehIcle SimulatOR). Through simulation, the results verify that more energy can be regenerated from braking under the conditions of ensuring braking and batteries safety.