• The Journal of Korea Robotics Society
• /
• v.9 no.1
• /
• pp.39-47
• /
• 2014

Odometry using wheel encoders is one of the fundamental techniques for the pose estimation of wheeled mobile robots. However, odometry has a drawback that the position errors are accumulated when the travel distance increases. Therefore, position errors are required to be reduced using appropriate calibration schemes. The UMBmark method is the one of the widely used calibration schemes for two wheel differential drive robots. In UMBmark method, it is assumed that odometry error sources are independent. However, there is coupled effect of odometry error sources. In this paper, a new calibration scheme by considering the coupled effect of error sources is proposed. We also propose the test track design for the proposed calibration scheme. The numerical simulation and experimental results show that the odometry accuracy can be improved by the proposed calibration scheme.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.9
• /
• pp.401-410
• /
• 2016

3D registration is a computer vision technique of aligning multi-view range images with respect to a reference coordinate system. Various 3D registration algorithms have been introduced in the past few decades. Iterative Closest Point (ICP) is one of the widely used 3D registration algorithms, where various modifications are available nowadays. In the ICP-based algorithms, the closest points are considered as the corresponding points. However, this assumption fails to find matching points accurately when the initial pose between point clouds is not sufficiently close. In this paper, we propose a new method to solve this problem using the 6D distance (3D color space and 3D Euclidean distances). Moreover, a color segmentation-based adaptive sampling technique is used to reduce the computational time and improve the registration accuracy. Several experiments are performed to evaluate the proposed method. Experimental results show that the proposed method yields better performance compared to the conventional methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.15-23
• /
• 2017

The person Re-identification is the most challenging part of computer vision due to the significant changes in human pose and background clutter with occlusions. The picture from non-overlapping cameras enhance the difficulty to distinguish some person from the other. To reach a better performance match, most methods use feature selection and distance metrics separately to get discriminative representations and proper distance to describe the similarity between person and kind of ignoring some significant features. This situation has encouraged us to consider a novel method to deal with this problem. In this paper, we proposed an enhanced recurrent neural network with three-tier hierarchical network for person re-identification. Specifically, the proposed recurrent neural network (RNN) model contain an iterative expectation maximum (EM) algorithm and three-tier Hierarchical network to jointly learn both the discriminative features and metrics distance. The iterative EM algorithm can fully use of the feature extraction ability of convolutional neural network (CNN) which is in series before the RNN. By unsupervised learning, the EM framework can change the labels of the patches and train larger datasets. Through the three-tier hierarchical network, the convolutional neural network, recurrent network and pooling layer can jointly be a feature extractor to better train the network. The experimental result shows that comparing with other researchers' approaches in this field, this method also can get a competitive accuracy. The influence of different component of this method will be analyzed and evaluated in the future research.

• Molecules and Cells
• /
• v.45 no.11
• /
• pp.846-854
• /
• 2022

Neurons make long-distance connections via their axons, and the accuracy and stability of these connections are crucial for brain function. Research using various animal models showed that the molecular and cellular mechanisms underlying the assembly and maintenance of neuronal circuitry are highly conserved in vertebrates. Therefore, to gain a deeper understanding of brain development and maintenance, an efficient vertebrate model is required, where the axons of a defined neuronal cell type can be genetically manipulated and selectively visualized in vivo. Placental mammals pose an experimental challenge, as time-consuming breeding of genetically modified animals is required due to their in utero development. Xenopus laevis, the most commonly used amphibian model, offers comparative advantages, since their embryos ex utero during which embryological manipulations can be performed. However, the tetraploidy of the X. laevis genome makes them not ideal for genetic studies. Here, we use Xenopus tropicalis, a diploid amphibian species, to visualize axonal pathfinding and degeneration of a single central nervous system neuronal cell type, the retinal ganglion cell (RGC). First, we show that RGC axons follow the developmental trajectory previously described in X. laevis with a slightly different timeline. Second, we demonstrate that co-electroporation of DNA and/or oligonucleotides enables the visualization of gene function-altered RGC axons in an intact brain. Finally, using this method, we show that the axon-autonomous, Sarm1-dependent axon destruction program operates in X. tropicalis. Taken together, the present study demonstrates that the visual system of X. tropicalis is a highly efficient model to identify new molecular mechanisms underlying axon guidance and survival.