Department Publications

This Paper describes the implementation of a verification system that uses palm geometry to verify the identity of an individual. Palm geometry is a biometric scheme that uses the shape of the hand to confirm the identity of an individual.

Visual Cue Selection, Substitution and Integration for Robust Object Tracking | CiNii Research CiNii 国立情報学研究所 学術情報ナビゲータ[サイニィ] 詳細へ移動 検索フォームへ 移動 論文・データをさがす 大学図書館の本をさがす English 検索 タイトル 人物/団体名 著者ID/研究 者番号 所属機関 ISSN DOI 期間 ~ 本文リンク 本文リンクあり データソース JaLC IRDB Crossref DataCite NDLサーチ NDLデジコレ(旧NII-ELS) RUDA JDCat NINJAL CiNii Articles CiNii Books NACSIS-CAT/ILL DBpedia KAKEN Integbio PubMed LSDB Archive 極地研ADS 極地 研学術DB OpenAIRE 公共データカタログ すべて 研究データ 論文 本 博士論文 プロジェクト 人物 > 人物検索機能について Visual Cue Selection, Substitution and Integration for Robust Object Tracking Web Site Web Site Web Site 参考文献48件 Ajith Pasqual 相澤 清晴 書誌事項 タイトル別名 Visual Cue Selection Substitution and Integration for Robust …

The concept of vision information has become a key feature in modern vehicular traffic control and Intelligent Vehicle Highway Systems (IVHS)[1]. Vehicle detection by video cameras is one of the most promising new technologies used in implementing advanced traffic control and management systems [2].

Multiple visual features can be used to track objects in environments where the use of a single visual feature is not sufficient. We have proposed an alternative method to feature integration by way of feature substitution where the dominant feature at any instant is used for tracking. The problem of increased computational cost resulting from the use of multiple features is addressed by using software optimization techniques. Here we use software threads and special instructions provided in MMX processors to increase the frame rate. Experimental results indicate that it is not always necessary to adopt a hardware based approach for real time object tracking even when the computational cost is high.

In this paper we present a method of using multiple visual attributes (features) that are present in moving objects for carrying out object tracking, by way of feature substitution. The proposed method, in principle, can make use of many visual cues available from a scene such as texture, color, velocity (monocular features) and disparity, vergence (binocular features). For the present experiments we make use of 3 features, namely, texture, optical flow and color as the main visual features and defocus of objects (blur) as supportive feature. At any instance, tracking is carried out using only one feature and this feature is monitored closely for failures. The feature is substituted with another suitable feature only upon the failure or high uncertainty of the current features. In case of tracking using texture alone, we make use of a histogram based technique called Histogram Intersection Value. This technique is not only …

In this paper we present a method of selection and snbstitution of visual features for carrying out object tracking. The proposed method, in principle, can make use of many visual cues available from a scene such as texture, color, velocity (monocular features) and disparity, vergence (binocular features). For the present experiments we make use of 3 features, namely, texture, optical flow and color as the main visual features and defocus of objects (implicit depth) as supportive feature. At any instance, tracking is carried out using only one feature and this feature is monitored closely for failures. The feature is substituted with another suitable feature only upon the failure or high uncertainty of the current feature.

The concept of vision information has become a key feature in modern vehicular traffic control and Intelligent Vehicle Highway Systems (IVHS)[1]. Vehicle detection by video cameras is one of the most promising new technologies used in implementing advanced traffic control and management systems [2]. The CCTV Image Grabber discussed in this paper is a low cost design which can capture, store and transmit video information to a remote computer for visual site inspection and extraction of vehicular traffic parameters for adaptive control of road traffic.

The current water meters in Sri Lanka are manually read monthly, consuming more expenditure on human resources by the water board of Sri Lanka. As a solution to that problem, automating and digitizing the water meter can be presented. In order to read out the digits on the water meter more conveniently and effectively in a resource constrained environment, a low-cost imaged based direct reading system is presented in this paper. This system can automatically identify the digits on the water meter through a template matching algorithm. After recognizing the digits of the water meter reading, the processed meter reading output is transferred to a central server via Narrow-Band Internet of Things (NB-IoT) technology. Recently, NB-IoT is one of the most promising Low Power Wide Area technology which has attracted much attention from both academia and industry.

one of the most challenging problems of field robots is self-localization, which involves incremental update of position while in motion. Though wheel based odometry is cheaper to implement its accuracy degrades when wheels slip. In this paper performance of low-cost visual odometry approach is experimented as a feasibility test for field robot localization. We have used a downward-facing camera and tested localization error in view of various parameters such as frame size, frame rate, etc. A FFT-based image registration techniques was utilized to determine the precise translation distances and heading between consecutive frames captured from ground surface. Basic navigation experiments, including a loop-closing test and error propagation were conducted and interesting numerical results have been reported

In this work, a new histogram refinement technique, Large Centre Regions (LCR) Refinement, and a new region representation technique, LCR Sets, based on colour regions are presented. These methods extract a predefined number of largest regions at the centre of an image and match other images emphasizing this property. The LCR Refinement effectively represents large centre regions of an image. In addition to this, LCR Sets represent basic information about the shape of a region, thus, extra distinguishing capability among different images can be achieved. Since the regions at the centre are given the emphasis for matching, the effect of the background can be minimized as well, as the background often lies outside the centre zone. Experimental results show 20% average improvement in ranks with LCR Refinement compared to Histogram. By combining LCR Sets with either Histogram or LCR Refinement …