Бидний тухай
Багш ажилтан
Robotic arms are widely used for many applications in various fields such as industry, health care, and military. Most robotic arms are programmed to perform specific tasks. However, controlling the robotic arm to move in any position is not easy and requires experience. In this study, we used Leap motion sensor to detect and track human hand movement and trajectory. We developed a mathematical model that converts human hand coordinates that are acquired from Leap motion sensor to 6-axis robotic arm control coordinates using Python language. To evaluate performance, we compared human hand coordinates with controlled 6-axis robotic arm coordinates. As a result, the 6-axis robotic arm followed the human hand trajectory successfully. Therefore, using Leap motion sensor and the proposed mathematical model, 6-axis robotic arm can follow the human hand movement and trajectory accurately. Based on the result, in future, we can develop the robotic arm chess player that plays chess automatically without human help.
The stone tools excavated from the ruins are washed, given identification number, classified for assembly, and then assembled. After that, each stone tools are investigated to know its manufacturing method and usage. However, since the identification information may be lost in the process of investigation, a system that automatically presents the identification number from the actual stone tool is required. This paper propose a method for identifying real stone tools measured by an RGB-D camera in order to automate the identification of stone tools. In this method, the point cloud of the stone tool measured by an RGB-D camera, and the point cloud that has been scanned in advance are compared by an algorithm that combines 2D and 3D methods. As the result stone tool becomes identified. Specifically, by combining the matching method using 2D contours and the ICP algorithm, we have achieved faster processing and higher discrimination accuracy. As a result of creating a database of 82 stone tool point cloud data constructed from 24 stone tools and applying this method to some stone tools, good results were obtained.
Researchers assume that the bodies of several Tara statues may have been molded from the same template. Therefore, researchers are eager to study the shape similarities between the Tara statues. Motivated by the archaeologist's requirements, this study presents an efficient approach to evaluate shape similarities between point clouds of two different Tara statues right-arm models. The evaluation approach consists of two main stages. The first is the reconstruction of individual body parts without decoration using a B-spline surface approximation technique. In previous reconstruction process, the surrounding surface selection parameter was manually specified. If the manually applied parameter is inadequate, it reduces the accuracy of the surface approximation and hole-filling, resulting in reduced accuracy of the evaluation result. Therefore, in this study, the surrounding surface selection parameter is automatically determined based on the Golden-section-search algorithm. The second stage evaluates the shape similarities between two different point clouds. The evaluation method considers a simple point-to-surface distance metric method with overlapping-surface detection and when compared with generic point-to-point distance metric method, the evaluation results proved that the proposed methodology was reliable and effective for this application. The approximation accuracy affects the evaluation result when the reconstruction method fills the gap by adding new points through the approximated surface. Therefore, in this study, the shape similarities were investigated between the two arm models with holes, immediately after separating the decoration parts.
Due to population growth, urbanization, and industrialization, the quality of the Tuul River is degraded, which requires efficient regular monitoring and analysis. Thus, it is of critical importance to apply modeling methods that have overcome the limitations of conventional modeling methods. The main objective of this study is to examine the artificial intelligence-based artificial neural network (ANN) model in water quality analysis. In this regard, 1260 values of 18 physicochemical parameters of the Tuul River at 10 sampling points were collected and assessed. The Pearson correlation coefficient was used to identify the parameters to be used as input and output variables of the ANN modeling and the number of neurons in the hidden layer was identified by using a rule-of-thumb approach as well as the trial-and-error process. The model was trained with two different algorithms, i.e. Levenbergh-Marquardt and Bayesian Regularization. The performance of the ANN model was evaluated using mean square error (MSE) and coefficient of correlation (R). The result showed that the performance of the ANN model trained with the Levenbergh-Marquardt algorithm was better than the Bayesian Regularization at the hidden layer number of 10. The optimized ANN model with input variables of electrical conductivity (EC), total dissolved solids (TDS), total hardness (TH), chemical oxygen demand (COD), biological oxygen demand (BOD5), sodium and potassium (Na++K+), calcium (Ca2+), magnesium (Mg2+), ammonium (NH4+), and bicarbonate (HCO3-) for prediction of chloride (Cl-) was MSE=12.03 mg/l, R2=0.97. It was found that the developed ANN model could be employed in estimating the Cl-.
Дуу хоолойг хувиргах гэдэг нь бодит цаг хугацааны хувьд хүний яриаг өөр хүн ярьж байгаа юм шиг дуу хоолойг нь хувиргах буюу өөрчлөхөд ашигладаг техник юм. Хүний дуу хоолой хувиргалтын алгоритмыг ISP болон зар сурталчилгааны компаниуд түгээмэл хэрэглэдэг. Гэхдээ ихэвчлэн дуу хоолой хувиргалтын алгоритмын хэрэгжүүлэлтийг бэлэн платформ буюу нээлттэй-эх код ашиглан хийдэг бөгөөд энэ нь дохиог өөрсдийнхөө хүссэн дуу хоолойруу хөрвүүлэх гэх мэт боломжуудыг хязгаарладаг. Иймээс бид энэхүү судалгааны ажлаар Питч шилжүүлэлтийн алгоритмыг МАТЛАБ програм болон C++ хэл дээр хэрэгжүүлсэн. Эхлээд хүний ярианы дохиог тодорхой хэмжээтэй фрейм болгон хуваасан бөгөөд нэг фрейм нь дохионы питч буюу үндсэн давтамж юм. Фрейм болгон хуваахын тулд бид тухайн хүний ярианы дохионоос питч илрүүлэх процессийг хийнэ. Өөрөөр хэлбэл тухайн хүний ярианы давтамжийн хүрээг олно. Хэрэгжүүлэлтийг монгол хүний дуу хоолой ашиглан хийсэн бөгөөд питч үнэлэх, питч тэмдэглэх, Pitch Synchronous Over Lap Add алгоритм гэсэн гурван алхмын дагуу хийсэн. Бидний энэхүү систем нь дурын хүний дуу хоолойн дохиог далайц болон хугацааны хувьд өөрчлөх замаар хувиргаж хувиргасан дуу хоолойг гаргадаг. Мөн энэхүү алгоритмын тусламжтайгаар хүний ярианы дохиог хувиргасан хэдий ч дууны чанарыг сайжруулах шаардлага гарсан учраас далайцын утгуудыг сэргээх алгоритмыг мөн хэрэгжүүлсэн.
Энэхүү судалгааны ажлаар дотооддоо тариалж буй хүнсний ногоог импортоор орж ирсэн хүнсний ногооноос ялгах зорилготой машин сургалтын модель хөгжүүлэхийг зорив. Хүнсний ногоо дундаа байцаа болон өргөст хэмхийг онцлон сонгосон шалтгаан нь санал асуулгын дүн ба өгөгдөл цуглуулах боломжтой байсан тул сонгосон. Хөгжүүлэлтийг CNN болон Mask- RCNN[1] гэсэн хоёр модель ашиглан сургасан. Mask-RCNN модель танилт илүү өндөртэй нэмэлт үйлдэл буюу хүрээлэх нь орчин үеийн үр дүнд[2] хүрсэн.
遺跡から発掘された石器は，洗浄，採番，母岩分類の後，組み立てを行い，それぞれの石器が識別番号を与えられ，その製法や 用法を知るために調査される．しかし，調査の過程でその識別情報が失われてしまう可能性があるため，実物の石器から識別番号 を自動で提示するシステムが求められている． 本稿では，石器の識別自動化のため，カメラで計測した実物の石器を識別する手法を提案する．RGB-D カメラを用いること で，石器の表面の点群を計測し，計測した点群と事前にスキャンした石器の点群を 2D と 3D の手法を組み合わせたアルゴリズム によって比較することで石器の番号を識別する．具体的には，処理速度の早い輪郭を用いたマッチング手法と ICP アルゴリズム を組み合わせることで，点群のみを用いた手法よりも速い処理速度と，輪郭のみを用いた手法よりも高い識別精度を実現する．
Many researchers are eager to study the stone tool production process based on ancient stone tools that were excavated from ruins. The assembly and disassembly of joining materials are repeated many times for investigation that is a better way to understand the stone tool production process. In our previous work, we have implemented an interactive assembly guiding program using the contours of stone tool images taken by an RGB camera. However, this method was not suitable for thick stone tools. In this work, we examine stone tool identification methods by using an RGB-D camera and 3D point cloud processing.
Through the study of stone tools in Japan, archaeologists can gain insights into the behaviors of Paleolithic people. By joining materials, stone tools can be reassembled into their original form. This assembly is a crucial and unavoidable process in archeology because it is essential for studying the relationships and connections of stones. Through trial and error, archaeologists attempt to recreate and map the structures of joining materials. When pieces of joining material are investigated after it is disassembled, archaeologists must reassemble them. Therefore, the identification of stone tools and visualization of their joining order is crucial. In this paper, we propose a faster and more efficient approach to identifying target stone tools using stable posture estimation and matching. The proposed method is applied to real objects and offers a novel approach to identification and reassembly in archeology.
Abstract—Analyzing body shape similarities between Tara statues of Zanabazar is worthwhile since researchers have assumed that the bodies of several statues were molded from the same template. This paper provides a novel and easy methodology for analyzing shape similarities between point clouds from two different Tara statue arm models, for the archaeological application. The methodology has two main steps. In the first step, individual body parts were reconstructed without decorations on it, using the previously proposed methods. The second step, the main contribution of this paper, is to evaluate shape similarities between point clouds of the two different arm models. The proposed methodology was tested on arm parts of Mongolian Buddha statues, and similarities between different, undecorated arm models were examined, using the proposed method and established point-to-point error metric, which showed that the proposed methodology was reliable and effective, in this application.
We propose a novel and adaptive method for point-cloud simplification within a bounded error by preserving feature points. The method comprises two main phases. The first phase is a uniform simplification phase. In this phase, with an approximated simplification degree, the point-reduction process is conducted by maintaining feature points. A segmentation range (k-neighbors) of the feature points is determined by the user-defined simplification degree, and lower feature points in the range are removed. In the second error-correction phase, we construct a mesh on the preserved point cloud using the spiraling-edge method, avoiding recalculation of the k-neighbors. Subsequently, meshes with large error are corrected by reusing removed points. Experimental results for different models indicate that our method can quickly generate a high-quality error-bounded simplified point cloud by preserving feature points with a specific simplification degree.
Extracting the reconstructed decoration parts of a Buddha statue contributes to the analysis in archaeology and culture.A segmented decoration part with good precision is required for reconstructing the solid model of a decoration. This paper presents a novel segmentation algorithm of a point cloud for decoration points with a simple calculation based on divided rectangular surfaces. In our method, the decoration feature of the standard form according to a template is used to detect an exact decoration region. A differentiation graph indicating a variation of tangent vectors is introduced to extract the feature of a decoration region in a two-dimensional domain. A decoration region is detected according to higher correlation values with the decoration feature of the standard form. The proposed method is tested on the arm parts of a Mongolian Buddha statue and the effectiveness of our algorithm is confirmed and evaluated. The decoration points are segmented precisely, and the decoration and background parts are separated. Moreover, holes in the separated background are filled using a B-spline surface fitting technique for generating a complete surface model of the decoration parts and background.
Extracting reconstructed decoration and body parts from Buddha statues collection contributes to cultural and archaeological analyses. To fully analyze the similarity between different statues, reconstructed body parts without decoration are required. This paper proposes a sufficient hole-filling method to reconstruct solid models of a statue arm that does not feature decoration on the surface. In our approach, decoration and body parts are separated according to segmented decoration points. Once decoration parts are separated from the original model, complex holes and gaps are left in the body part. Thus, a hole-filling method is introduced in this paper, to construct a complete surface model of an arm. We implemented our hole-filling method using a general B-spline surface-fitting technique based on information from divided rectangular surfaces. Once the body part is completed using the hole-filling method, a solid model is reconstructed. The proposed method was tested on arm parts from Mongolian Buddha statues and the precision of the hole-filling method was confirmed. The solid model of an arm part was reconstructed from point clouds of completed body model.
