2017 2nd Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)

16-18 June 2017

Filter Results

Displaying Results 1 - 25 of 73
  • [Front cover]

    Publication Year: 2017, Page(s):c1 - c4
    Request permission for commercial reuse | PDF file iconPDF (1953 KB)
    Freely Available from IEEE
  • [Title page]

    Publication Year: 2017, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (54 KB)
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2017, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (80 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2017, Page(s):iii - xi
    Request permission for commercial reuse | PDF file iconPDF (186 KB)
    Freely Available from IEEE
  • A multimodal gesture-based virtual interactive piano system using computer vision and a motion controller

    Publication Year: 2017, Page(s):1 - 6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (408 KB) | HTML iconHTML

    Everyday life activities rely on technology and in order to compliment modern day lifestyle, technology has to be either portable or interoperable. In this paper, we propose a close to real-time, gesture-based virtual piano system, using computer vision and motion tracking, with the notion of being accessible in different environments. The solution focuses on capturing a user's hand movements usin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition and location of solar panels based on machine vision

    Publication Year: 2017, Page(s):7 - 12
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (640 KB) | HTML iconHTML

    This paper mainly aims at the aerial image obtained by UAV, and proposes a new solar panel recognition method based on machine vision. In this paper, OpenCV and VS2013 are used to build the experimental platform. Firstly, the image is preprocessed, then the image is segmented in HSV color space, and then the morphological operation is carried out. Finally, according to the prior knowledge, the sys... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • NS-SOF: A non-feature matching approach for sparse optical flow

    Publication Year: 2017, Page(s):13 - 18
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (814 KB) | HTML iconHTML

    This paper presents a novel approach to compute sparse optical flow field, which is different from the traditional feature matching methods such as SURF. The approach consists mainly of three novel parts. First, the improved PatchMatch that is tailored to sparse optical flow computation is used to generate NNF quickly. And the NNF is smoothed using a threshold filtering rather than global optimiza... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An implementation framework for fast image processing

    Publication Year: 2017, Page(s):19 - 22
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (553 KB) | HTML iconHTML

    Efficient processing of image data is a key aspect of achieving real-time performance for image and video applications. Here, a biologically inspired novel framework which uses a spiral indexing scheme is used to facilitate fast image processing. In particular we demonstrate the effectiveness of our approach on low-level image operations (convolution) and feature extraction (edge detection). Unlik... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel image retrieval model based on semantic information and probability rough set analysis method

    Publication Year: 2017, Page(s):23 - 27
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (302 KB) | HTML iconHTML

    Image Retrieval is one of the most active research areas in computer vision and pattern recognition. This paper presents an image retrieval technique based on semantic information and probability rough set analysis method to study uncertain systems. The rough set theory defines an objective type of function and does not require extra parameters or models for analysis, and is therefore very advanta... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Superpixel finite element segmentation for RGB-D images

    Publication Year: 2017, Page(s):28 - 32
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (655 KB) | HTML iconHTML

    Computer vision research has advanced from focusing solely on intensity images to the use of depth images, or combinations of RGB, intensity and depth images, mainly due to the recent development of low cost depth cameras. These images can be efficiently represented as a space-variant image by segmenting the images using a superpixel representation. Whilst superpixel representations offer advantag... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detection of salient region of in-field rapeseed plant images based-on visual attention model

    Publication Year: 2017, Page(s):33 - 36
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (294 KB) | HTML iconHTML

    Detection of salient region of in-field plant based-on visual attention shift with human visual perception was proposed in this study. Based on in-field condition, visual features such as color, intensity and gradient of images, were extracted to build up saliency model with human semantic behavior. Salient regions were obtained by visual attention model and region growing approach. Through analyz... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Study on the movable detection method about inland vessels ultra-draft violations

    Publication Year: 2017, Page(s):37 - 41
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (317 KB) | HTML iconHTML

    Since sand under water occurs siltation and leads to clogging issue, it has become a serious security problem to ships in inner-river. Therefore, it is very important to lay mattress in waterway to cure sediment and ensure the normal depth. However, due to the underwater flow speed, laying mattress is very difficult. The Mattress is often in offset position, and this could result in exposing river... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tongue shape classification integrating image preprocessing and Convolution Neural Network

    Publication Year: 2017, Page(s):42 - 46
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (362 KB) | HTML iconHTML

    Tongue diagnosis is one of the most important parts in “inspection diagnosis” of Traditional Chinese Medicine (TCM). Observing tongue shape can help to understand the changes in human body and thereby to estimate the illness. This paper presents a method of recognizing tongue shapes based on Convolution Neural Network. The proposed method enhances the features of tongue images with p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Face spoof detection using light reflection in moderate to low lighting

    Publication Year: 2017, Page(s):47 - 52
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (440 KB) | HTML iconHTML

    Face recognition is widely viewed as an alternative means of authentication to replace traditional password methods in different applications for access control. Despite significant improvements, this form of authentication remains plagued by a number of vulnerabilities ranging from the use of printed photographs, 3D masks, and video replay attacks, prompting the need for a more robust approach in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Online image Jacobian identification using optimal adaptive robust Kalman filter for uncalibrated visual servoing

    Publication Year: 2017, Page(s):53 - 57
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (495 KB) | HTML iconHTML

    Dynamic image Jacobian matrix identification is proved complicated and tough in uncalibrated visual servoing. Comparing with standard Kalman Filter (KF), which is exhausted to find the optimal value of unknown noise covariance, the adaptive robust KF is developed to deal with uncertainty noise covariance information. The state model and measurement of noise covariance matrices are adopted recursiv... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vision-based localization in campus with a multi-stage framework

    Publication Year: 2017, Page(s):58 - 61
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (509 KB) | HTML iconHTML

    In this paper, a novel vision-based multi-stage localization framework is proposed. Our framework makes rough classification scenes in a wide range of Campus, using the powerful classification ability of the convolutional neural network for multi class objects. Then, refined classification is implemented based on SIFT and GIST features, which achieves a good scene classification effect and complet... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-pedestrian detection in crowded places on quadrotor's view

    Publication Year: 2017, Page(s):62 - 65
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (413 KB) | HTML iconHTML

    In this paper, detecting multi-pedestrian in crowded areas on quadrotor's view is explored. This paper proposes a new method to combine Kalman filter with detection to reduce missed pedestrians. The detection is based on the supervised machine learning method, which is support vector machine (SVM) with histogram of oriented gradients (HOG) feature. And Kalman filter is used to estimate the locatio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Lip detection and adaptive tracking

    Publication Year: 2017, Page(s):66 - 72
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (625 KB) | HTML iconHTML

    Performance of automatic speech recognition (ASR) systems utilizing only acoustic information degrades significantly in noisy environments such as a car cabins. Incorporating audio and visual information together can improve performance in these situations. This work proposes a lip detection and tracking algorithm to serve as a visual front end to an audio-visual automatic speech recognition (AVAS... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self-adaptive weighted majority vote algorithm based on entropy

    Publication Year: 2017, Page(s):73 - 77
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (502 KB) | HTML iconHTML

    Based on the novel idea of assigning different weight for same sample by different classifier according to the classification ability and assigning different weight for different sample by same classifier according to the separable degree of sample respectively, a self-adaptive weighted vote algorithm based on entropy is proposed. Probability Multi-class Relevance Vector Machine (PRVM_OVO) is exte... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Classification based on label semantic characteristic analysis

    Publication Year: 2017, Page(s):78 - 82
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (323 KB) | HTML iconHTML

    Classification is a machine learning technique that assigns labels to a collection of data in order to aid in more accurate predictions and analysis. It has been widely studied and many classification approaches have been proposed from different fields. However, there is no one optimal classifier in all respects or for all the data sets as No-Free-Lunch theorem states. In addition, there is a lack... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A method for improving consistency of judgment matrix in the AHP

    Publication Year: 2017, Page(s):83 - 87
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (273 KB) | HTML iconHTML

    This paper presents an approach to improve consistency of judgment matrix in the Analytic Hierarchy Process (AHP), which utilizes the relationship between induced matrix and judgment matrix. By using this method, judgment matrix can be modified to satisfy the consistency requirement and reserve most information that the original matrix contains. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Storing and querying AIS data in HBase

    Publication Year: 2017, Page(s):88 - 92
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (365 KB) | HTML iconHTML

    With the wide application of Automatic Identification System (AIS) on ships, a large amount of data is generated, namely AIS data. It is of great significance for the development of water transportation to process the data effectively. Traditional relational database management systems (RDBMS) have low performance when processing massive data. In this paper, HBase which is a representative of the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The fluorescence spectroscopy recognition of the traditional Chinese medicine injection based on the lifting wavelet-BP-Fuzzy Neural Network

    Publication Year: 2017, Page(s):93 - 97
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (431 KB) | HTML iconHTML

    There is a lot of noise in the original spectral signal collected from the detector. In this paper, the lifting wavelet was used to remove the noise. The singular value eigenvector obtained by the Excitation-Emission Matrix (EEM) factorization from the fluorescence spectroscopy was used to recognize the information of the traditional Chinese medicine injection. The singular value eigenvector was t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis and application of functional safety based on modified FMEA method

    Publication Year: 2017, Page(s):98 - 103
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (395 KB) | HTML iconHTML

    According to the requirements of ISO 26262, the functional safety analysis of the corresponding system, the use of hazard analysis and risk assessment of the system has different functions and their corresponding failure of the car safety integrity level (ASIL, Automotive Safety Integrity Level). Then, the modified FMEA method based on fuzzy rule base and gray relational degree is introduced into ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Identification of research fronts in artificial intelligence

    Publication Year: 2017, Page(s):104 - 108
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (407 KB) | HTML iconHTML

    Based on the data of artificial intelligence papers in web of science, the subject research trend and front recognition is analyzed. Firstly, using the total papers and aggregate impact factor, the development trend is analyzed. Through the comparison of subject scale and academic influence of 7 computer discipline, the subject status of the field is assessed. Based on the comparison of top 10 age... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.