Xinnan Fan

A Thermal Infrared and Visible Images Fusion Based Approach for Multitarget Detection under Complex Environment

Multitarget detection under complex environment is a challenging task, where the measured signal will be submerged by noise. D-S belief theory is an effective approach in dealing with nMultitarget detection. However, there are some limitations of the general D-S belief theory under complex environment. For example, the basic belief assignment is difficult to establish, and the subjective factors will influence the update process of evidence. In this paper, a new Multitarget detection approach based on thermal infrared and visible images fusion is proposed. To easily characterize the defected heterogeneous image, a basic belief assignment based on the distance distribution function of heterogeneous characteristics is presented. Furthermore, to improve the discrimination and effectiveness of the Multitarget detection, a concept of comprehensive credibility is introduced into the proposed approach and a new update rule of evidence is designed. Finally, some experiments are carried out and the experimental results show the efficiency and effectiveness of the proposed approach in the Multitarget detection task.

The Research and Application of Human Detection Based on Support Vector Machine Using in Intelligent Video Surveillance System

This paper presented a special design and implementation of human detection based on SVM (support vector machine) and this method is used in intelligent video surveillance system. In order to simplify the design of the SVM classifier and improve efficiency of machine learning, both a grid vector representation and a center radiating vector representation are proposed to abstract features of the object. The sample data is obtained through processing and analysis including human and no-human which forms the training input to SVM. Finally, we used the trained recognizer to identify whether there is somebody broken into the object region. If there is, the automatic warning device gives the alarm, which guarantees a real-time surveillance.

Design of automatic target-scoring system of shooting game based on computer vision

This paper describes a machine vision system with back lighting illumination and friendly man-machine interface. Subtraction is used to segment target holes quickly and accurately. The oval obtained after tracing boundary is processed by Generalized Hough Transform to acquire the targets center. Marked-holes area, perimeter and moment invariants are extracted as cluster features. The auto-scoring software, programmed by Visual C++, has successfully solved the recognition of off-target and overlapped holes through alarming surveillance and bullet tacking programs. The experimental results show that, when the target is distorted obviously, the system can recognize the overlapped holes on real time and also clusters random shape holes on the target correctly. The high accuracy, fast computing speed, easy debugging and low cost make the system can be widely used.

A novel underwater dam crack detection and classification approach based on sonar images

Underwater dam crack detection and classification based on sonar images is a challenging task because underwater environments are complex and because cracks are quite random and diverse in nature. Furthermore, obtainable sonar images are of low resolution. To address these problems, a novel underwater dam crack detection and classification approach based on sonar imagery is proposed. First, the sonar images are divided into image blocks. Second, a clustering analysis of a 3-D feature space is used to obtain the crack fragments. Third, the crack fragments are connected using an improved tensor voting method. Fourth, a minimum spanning tree is used to obtain the crack curve. Finally, an improved evidence theory combined with fuzzy rule reasoning is proposed to classify the cracks. Experimental results show that the proposed approach is able to detect underwater dam cracks and classify them accurately and effectively under complex underwater environments.

Inspection of surface defects in copper strip based on machine vision

Though copper products are important raw materials in industrial production, there is little domestic research focused on copper strip surface defects inspection based on automated visual inspection. According to the defect image characteristics on copper strips surface, a defect detection algorithm is proposed on the basis of wavelet-based multivariate statistical approach. First, the image is divided into several sub-images, and then each sub-image is further decomposed into multiple wavelet processing units. Then each wavelet processing unit is decomposed by 1-D db4 wavelet function. Then multivariate statistics of Hotelling T2 are applied to detect the defects and SVM is used as defect classifier. Finally, the defect detection performance of the proposed approach is compared with traditional method based on grayscale. Experimental results show that the proposed method has better performance on identification, especially its application in the ripple defects can achieve 96.7% accuracy, which was poor in common algorithms.

A novel automatic dam crack detection algorithm based on local-global clustering

Dam crack detection is necessary to ensure the safety of dams. However, traditional detection methods always perform poorly, with a low detection rate and high false alarm rate, due to the complex underwater environment. In this paper, a novel automatic dam crack detection algorithm (CrackLG) is proposed based on local-global clustering analysis that can find cracks on dam surfaces accurately and quickly using images as well as reduce human subjectivity. First, an image shot of an underwater dam surface is divided into non-overlapping image blocks after pre-processing. Then, image blocks containing crack pixels are identified by local clustering analysis. Second, the image is binarized by adaptive bi-level thresholding based on the local gray intensity. Meanwhile, some noise is removed based on the computed optimal threshold. After extracting global 3-D features, final crack regions are obtained by global clustering analysis. The advantage of CrackLG is that the threshold for realizing image binarization is self-adaptive. Additionally, it can automatically perform crack detection without human supervision. The simulation and comparison show that the proposed CrackLG method is more effective for underwater dam crack detection.

A Single-Way Ranging Localization of AUVs Based on PSO of Outliers Elimination

Localization of autonomous underwater vehicles (AUVs) is a very important and challenging task for the AUVs applications. In long baseline underwater acoustic localization networks, the accuracy of single-way range measurements is the key factor for the precision of localization of AUVs, whether it is based on the way of time of arrival (TOA), time difference of arrival (TDOA), or angle of arrival (AOA). The single-way range measurements do not depend on water quality and can be taken from long distances; however, there are some limitations which exist in these measurements, such as the disturbance of the unknown current velocity and the outliers caused by sensors and errors of algorithm. To deal with these problems, an AUV self-localization algorithm based on particle swarm optimization (PSO) of outliers elimination is proposed, which improves the performance of angle of arrival (AOA) localization algorithm by taking account of effects of the current on the positioning accuracy and eliminating possible outliers during the localization process. Some simulation experiments are carried out to illustrate the performance of the proposed method compared with another localization algorithm.

Positioning technology of mobile vehicle using self-repairing heterogeneous sensor networks

Abstract Mobile vehicle positioning can provide the reference to navigation, tracking and multi vehicles collaboration. Applying spatiotemporal distribution characteristics of positioning errors between strap-down inertial navigation system (SINS) and wireless sensor network (WSN) approaches, a mobile vehicle positioning is proposed as a component of heterogeneous sensor networks (HSN). The attitude, velocity and position equations of mobile vehicle are derived based on the kinematics parameter constraints and inertial parameter errors. Meanwhile, WSN approach can provide position estimation using inaccurate anchor nodes. However, SINS is known for its cumulative errors over long time, while WSN approach can have large positioning errors in certain areas. As an effort to overcome the limitations of pure SINS or WSN approach, an integrated SINS and WSN approach is proposed to form a self-repairing HSN approach, which can provide sound position and attitude for mobile vehicle. Then, multi-parameter interaction and cooperative correction strategy are explored when SINS or WSN measurement is abnormal. Finally, a comprehensive set of experiments of position and attitude estimations for mobile vehicle are performed on the actual environment platform.

A multi-sensor image fusion algorithm based on region-based selection and IHS transform

The multi-sensor image fusion technology can obtain a more comprehensive and more accurate and reliable image, in order to understand the scene or recognize the target more easily. However, most existing algorithms are mainly based on optical remote sensing images, which is highly susceptible by media interference, supplemented by SAR images. The image fusion between SAR images and PAN images also cannot save the textural feature and the color information effectively at the same time. In view of these problems, this paper presents a multi-sensor image fusion algorithm based on region-based selection and IHS transform. The SAR image and PAN image are firstly IHS transformed to achieve the intensity (I), hue (H) and saturation (S) weights. The I weights of SAR image and PAN image are separately decomposed using SIDWT algorithm to extract wavelet coefficients. Then, the I weight of SAR image is divided into regular area and irregular area based on a new adaptive segmentation method. A new fusion rules is presented according to local feature, and then used to fuse corresponding wavelet coefficients of the I weight of SAR image and PAN image. Inverse SIDWT is carried out on the fused wavelet coefficients to get the I weight (I’) of fused image. Finally, the fused image is obtained by inverse IHS transform of I’ weight with the H, S weight of PAN image. Experimental results of real images validated the effectiveness of the proposed algorithm by objective evaluation such as standard deviation, entropy, average gradient, etc.

An evidence fusion approach for characterization of heterogeneous images under complex environment

Characterization, recognition under complex environment is a challenging task. The measured signal will be submerged by noise in complex environment, which makes it difficult to characterize targets, especially when the targets share the similar characteristics. Multi-sensor information fusion will improve characterization significantly and DS evidence theory is an effective approach in heterogeneous information fusion. However, evidence from multi-sensor information is always affected by subjective factors in the process of evidence fusion. In this paper, a new evidence fusion approach for improving characterization under complex environment is proposed. To characterize the heterogeneous images better, a concept of comprehensive credibility is introduced into the proposed approach and a new update rule of evidence is designed. Some experimental results show the efficiency and effectiveness of the proposed approach.