An active stereo vision-based learning approach for robotic tracking, fixating and grasping control

In this paper, an active stereo vision-based learning approach is proposed for a robot to track, fixate and grasp an object in unknown environments. First, the functional mapping relationships between the joint angles of the active stereo vision system and the spatial representations of the object are derived and expressed in a three-dimensional workspace frame. Next, the self-adaptive resonance theory-based neural networks and the feedforward neural networks are used to learn the mapping relationships in a self-organized way. Then, the approach is verified by simulation using the models of an active stereo vision system which is installed in the end-effector of a robot. Finally, the simulation results confirm the effectiveness of the present approach.

Image matching using TI multi-wavelet transform

A multi-resolution image matching technique based on multiwavelets followed by a coarse to fine strategy is presented. The technique addresses the estimation of optimal corresponding points and the corresponding disparity maps in the presence of occlusion, ambiguity and illuminative variations in the two perspective views taken by two different cameras or at different lighting conditions. The problem of occlusion and ambiguity is addressed by a geometric topological refining approach along with the uniqueness constraint whereas the illuminative variation is dealt by using windowed normalized correlation.

Stereo-vision-based moving object tracking via robust linear filtering

Vision-based tracking sensors typically provide nonlinear measurements
of the targets Cartesian position and velocity state components. In this paper we derive linear measurements using an analytical measurement conversion technique which can be used with two (or more) vision sensors. We derive
linear measurements in the target’s Cartesian position and velocity components and we derive a robust version of a linear Kalman filter. We show that our linear robust filter significantly outperforms the extended Kalman Filter. Moreover, we prove that the state estimation error is bounded.

Fingerprint recognition system using hybrid matching techniques

With an increasing emphasis on the emerging automatic person identification application, biometrics based, especially fingerprint-based identification, is receiving a lot of attention. This research developed an automatic fingerprint recognition system (AFRS) based on a hybrid between minutiae and correlation based techniques to represent and to match fingerprint; it improved each technique individually. It was noticed that, in the hybrid approach, as a result of an improvement of minutiae extraction algorithm in post-process phase that combines the two algorithms, the performance of the minutia algorithm improved. An improvement in the ridge algorithm that used centre point in fingerprint instead of reference point was also observed. Experiments indicate that the hybrid technique performs much better than each algorithm individually.

Depth estimation using multi-wavelet analysis based stereo vision approach

The problem of dimensional defects in aluminum die- casting is widespread throughout the foundry industry and their detection is of paramount importance in maintaining product quality. Due to the unpredictable factory environment and metallic, with highly reflective, nature of aluminum die-castings, it is extremely hard to estimate true dimensionality of the die-casting, autonomously. In this work, we propose a novel robust 3D reconstruction algorithm capable of reconstructing dimensionally accurate 3D depth models of the aluminum die-castings. The developed system is very simple and cost effective as it consists of only a stereo cameras pair and a simple fluorescent light. The developed system is capable of estimating surface depths within the tolerance of 1.5 mm. Moreover, the system is invariant to illuminative variations and orientation of the objects in the input image space, which makes the developed system highly robust. Due to its hardware simplicity and robustness, it can be implemented in different factory environments without a significant change in the setup.

Stereo correspondence estimation using multiwavelets scale-space representation-based multiresolution analysis

A multiresolution technique based on multiwavelets scale-space representation for stereo correspondence estimation is presented. The technique uses the well-known coarse-to-fine strategy, involving the calculation of stereo correspondences at the coarsest resolution level with consequent refinement up to the finest level. Vector coefficients of the multiwavelets transform modulus are used as corresponding features, where modulus maxima defines the shift invariant high-level features (multiscale edges) with phase pointing to the normal of the feature surface. The technique addresses the estimation of optimal corresponding points and the corresponding 2D disparity maps. Illuminative variation that can exist between the perspective views of the same scene is controlled using scale normalization at each decomposition level by dividing the details space coefficients with approximation space. The problems of ambiguity, explicitly, and occlusion, implicitly, are addressed by using a geometric topological refinement procedure. Geometric refinement is based on a symbolic tagging procedure introduced to keep only the most consistent matches in consideration. Symbolic tagging is performed based on probability of occurrence and multiple thresholds. The whole procedure is constrained by the uniqueness and continuity of the corresponding stereo features. The comparative performance of the proposed algorithm with eight famous existing algorithms, presented in the literature, is shown to validate the claims of promising performance of the proposed algorithm.

A generalized joint inference approach for citation matching

Citation matching is the problem of extracting bibliographic records from citation lists in technical papers, and merging records that represent the same publication. Generally, there are three types of data- sets in citation matching, i.e., sparse, dense and hybrid types. Typical approaches for citation matching are Joint Segmentation (Jnt-Seg) and Joint Segmentation Entity Resolution (Jnt-Seg-ER). Jnt-Seg method is effective at processing sparse type datasets, but often produces many errors when applied to dense type datasets. On the contrary, Jnt-Seg-ER method is good at dealing with dense type datasets, but insufficient when sparse type datasets are presented. In this paper we propose an alternative joint inference approach–Generalized Joint Segmentation (Generalized-Jnt-Seg). It can effectively deal with the situation when the dataset type is unknown. Especially, in hybrid type datasets analysis there is often no a priori information for choosing Jnt-Seg method or Jnt-Seg-ER method to process segmentation and entity resolution. Both methods may produce many errors. Fortunately, our method can effectively avoid error of segmentation and produce well field boundaries. Experimental results on both types of citation datasets show that our method outperforms many alternative approaches for citation matching.

Depth estimation using multiwavelet analysis based stereo vision approach

The problem of dimensional defects in aluminum die-casting is widespread throughout the foundry industry and their detection is of paramount importance in maintaining product quality. Due to the unpredictable factory environment and metallic, with highly reflective, nature of aluminum die-castings, it is extremely hard to estimate true dimensionality of the die-casting, autonomously. In this work, we propose a novel robust 3D reconstruction algorithm capable of reconstructing dimensionally accurate 3D depth models of the aluminum die-castings. The developed system is very simple and cost effective as it consists of only a stereo camera pair and a simple fluorescent light. The developed system is capable of estimating surface depths within the tolerance of 1.5 mm. Moreover, the system is invariant to illuminative variations and orientation of the objects in the input image space, which makes the developed system highly robust. Due to its hardware simplicity and robustness, it can be implemented in different factory environments without a significant change in the setup.

Matching training needs and opportunities : the case for training brokers in the Australian agricultural sector

Lifelong learning has been linked by policymakers to economic and social wellbeing. This paper introduces the concept of training brokerage as an efficient way of meeting the needs of learners, industry and education and training providers. It presents findings from a study of the features, processes and outcomes of training brokerage arrangements within the Australian agricultural and natural resource management sectors. The purpose of the study was to identify and promote effective brokerage arrangements and models. The study used multi-method, multi-site techniques, comprising a telephone survey, case studies of good broking practice and stakeholder participation through workshops and a reference group. Training brokers act as facilitators or intermediaries in identifying and matching training needs and opportunities. They have close links with industry, and extensive networks that include reputable training providers. Brokers work with others to identify training needs and engage participants, and to identify, negotiate and plan appropriate training. Evaluation and further training are a key part of the process. Effective broking activity is underpinned by a series of ten generic principles. Brokerage has implications for the agricultural sector in developed and developing countries, in terms of improving the match of training provision to training needs, communication, coordination and collaboration across regions and industries. It also has broader implications for facilitating participation in client-driven lifelong learning, particularly for disenfranchised learners.