Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182606
Zuoliang Tang, Lijia Xu, Hong Xie
Aiming at the phenomenon that to pick citrus by robot arm is in low efficiency, this paper chooses improved immune algorithm (IIA) for picking path planning of the citrus fruits on the surface of the tree canopy after many experiments. IIA is proposed by improving the neighborhood structure of basic immune algorithm (BIA) and using tabu search strategy to search the neighborhood structure of the current optimal solution which is already got by immune search in the final stage intensively. The world coordinates of citrus fruits are obtained by processing the photos taken by a ZED camera based on the principle of binocular vision. The experiment results show that when picking 6, 20 and 31 citrus fruits, the average planning time of IIA are 13.33%, 21.49% and 23.96% less than BIA, and the average picking distance are 0%, 0.66% and 0.67% shorter than BIA. This shows that IIA can not only effectively shorten the time of trajectory planning, but also shorten the distance of picking path, which provides theoretical support of improving the working efficiency of picking robot.
{"title":"Picking Trajectory Planning of Citrus Based on Improved Immune Algorithm and Binocular Vision","authors":"Zuoliang Tang, Lijia Xu, Hong Xie","doi":"10.1109/ICAICA50127.2020.9182606","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182606","url":null,"abstract":"Aiming at the phenomenon that to pick citrus by robot arm is in low efficiency, this paper chooses improved immune algorithm (IIA) for picking path planning of the citrus fruits on the surface of the tree canopy after many experiments. IIA is proposed by improving the neighborhood structure of basic immune algorithm (BIA) and using tabu search strategy to search the neighborhood structure of the current optimal solution which is already got by immune search in the final stage intensively. The world coordinates of citrus fruits are obtained by processing the photos taken by a ZED camera based on the principle of binocular vision. The experiment results show that when picking 6, 20 and 31 citrus fruits, the average planning time of IIA are 13.33%, 21.49% and 23.96% less than BIA, and the average picking distance are 0%, 0.66% and 0.67% shorter than BIA. This shows that IIA can not only effectively shorten the time of trajectory planning, but also shorten the distance of picking path, which provides theoretical support of improving the working efficiency of picking robot.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121042821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182424
Xinrong Hu, Xiao Zeng, Junping Liu, Tao Peng, R. He, Changnian Chen
In order to reduce the difficulty in constructing garment modeling and improve the construction efficiency of garment modeling. In this paper, a method of garment 3D reconstruction based on monocular and multi view is proposed. Firstly, the garment image sequence is obtained, and then the contour information including garment part is obtained by instantiating and segmenting the garment image sequence. The feature points and matching of each image are extracted by SIFT algorithm, and the error matching is eliminated by adding double constraints. Then, sparse point cloud and dense point cloud are reconstructed. Finally, Poisson reconstruction is used to restore the surface details of clothing. The results show that the point cloud noise can be effectively reduced and the reconstruction speed can be accelerated by adding case segmentation and double constraints in the process of garment monocular multi view garment 3D reconstruction. This method can also restore the surface details of clothing in the process of 3D model reconstruction.
{"title":"Research and Implementation of 3D Reconstruction Algorithm for Multi-angle Monocular Garment Image","authors":"Xinrong Hu, Xiao Zeng, Junping Liu, Tao Peng, R. He, Changnian Chen","doi":"10.1109/ICAICA50127.2020.9182424","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182424","url":null,"abstract":"In order to reduce the difficulty in constructing garment modeling and improve the construction efficiency of garment modeling. In this paper, a method of garment 3D reconstruction based on monocular and multi view is proposed. Firstly, the garment image sequence is obtained, and then the contour information including garment part is obtained by instantiating and segmenting the garment image sequence. The feature points and matching of each image are extracted by SIFT algorithm, and the error matching is eliminated by adding double constraints. Then, sparse point cloud and dense point cloud are reconstructed. Finally, Poisson reconstruction is used to restore the surface details of clothing. The results show that the point cloud noise can be effectively reduced and the reconstruction speed can be accelerated by adding case segmentation and double constraints in the process of garment monocular multi view garment 3D reconstruction. This method can also restore the surface details of clothing in the process of 3D model reconstruction.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121213752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182574
Gang Sha, Junsheng Wu, Bin Yu
Because of the problem that the complexity of spine CT images, the irregular shape of vertebral boundary, low contrast, noise and unevenness in images, meanwhile there are artificial deviations and low efficiencies in clinic, which needs doctors' prior knowledge and clinical experience to determine lesions location in CT images, so it can not meet the clinical real-time needs. In this paper, We use deep learning to process the CT images of spine, and to divide lesions of (cervical fracture, cfracture), (thoracic fracture, tfracture), (lumbar fracture, lfracture) by the improved U-net[1]. The experiment shows that we can effectively segment spinal fracture lesions by U-net, which can basically meet the clinical real-time needs.
{"title":"Spinal fracture lesions segmentation based on U-net","authors":"Gang Sha, Junsheng Wu, Bin Yu","doi":"10.1109/ICAICA50127.2020.9182574","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182574","url":null,"abstract":"Because of the problem that the complexity of spine CT images, the irregular shape of vertebral boundary, low contrast, noise and unevenness in images, meanwhile there are artificial deviations and low efficiencies in clinic, which needs doctors' prior knowledge and clinical experience to determine lesions location in CT images, so it can not meet the clinical real-time needs. In this paper, We use deep learning to process the CT images of spine, and to divide lesions of (cervical fracture, cfracture), (thoracic fracture, tfracture), (lumbar fracture, lfracture) by the improved U-net[1]. The experiment shows that we can effectively segment spinal fracture lesions by U-net, which can basically meet the clinical real-time needs.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"27 24","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113942039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182600
Huang Zhixiong, Shi Zhuo, Kong Qian, Li Rongbin, Yang Ming, Zhang Mengxue, Yu Ke
In order to solve the problem that the process of manually identifying national symbols is extremely tedious and the recognition effect is not satisfactory, the paper uses the TensorFlow framework to build a convolutional neural network to identify domestic symbols simply and efficiently. In this paper, the classified Zhuang ethnic symbol pictures are labeled and normalized to make a data set, and then during the training process, the loss value between the prediction result and the correct answer is continuously reduced to train a convolution layer, pool The convolutional neural network of the visualization layer, the fully connected layer, and the SoftMax layer. Finally, the images are classified by the SoftMax layer. The experimental results show that after a lot of training, the model has been more robust, and the recognition rate of 15 symbol types can reach 89%, which is faster and more accurate than the manual recognition process.
{"title":"National Cultural Symbols Recognition Based on Convolutional Neural Network","authors":"Huang Zhixiong, Shi Zhuo, Kong Qian, Li Rongbin, Yang Ming, Zhang Mengxue, Yu Ke","doi":"10.1109/ICAICA50127.2020.9182600","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182600","url":null,"abstract":"In order to solve the problem that the process of manually identifying national symbols is extremely tedious and the recognition effect is not satisfactory, the paper uses the TensorFlow framework to build a convolutional neural network to identify domestic symbols simply and efficiently. In this paper, the classified Zhuang ethnic symbol pictures are labeled and normalized to make a data set, and then during the training process, the loss value between the prediction result and the correct answer is continuously reduced to train a convolution layer, pool The convolutional neural network of the visualization layer, the fully connected layer, and the SoftMax layer. Finally, the images are classified by the SoftMax layer. The experimental results show that after a lot of training, the model has been more robust, and the recognition rate of 15 symbol types can reach 89%, which is faster and more accurate than the manual recognition process.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121817226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182525
Weiran Hua, Qiang Tong
Because facial expression is easy to be confused, and is easily affected by environment, Angle and other factors, this paper proposes an improved Faster R-CNN based facial expression detection method. In this method, histogram equalization and adaptive histogram equalization are preprocessed for SFEW 2.0 of the facial expression data set, and the facial expression data is enhanced and expanded. Then the repetitive experimental optimization of the hyperparameters is carried out to improve the training and learning effect of the model and improve the detection accuracy. In the end, based on the regularization model structure optimization, Soft-max cross entropy classification loss function and L1 Smooth regression loss function with parameter constraint term were proposed. The regularization method was used to optimize parameter weight, improve detection accuracy, and an improved Faster R-CNN model adapted to face expression characteristics was obtained.
{"title":"Research on Face Expression Detection Based on Improved Faster R-CNN","authors":"Weiran Hua, Qiang Tong","doi":"10.1109/ICAICA50127.2020.9182525","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182525","url":null,"abstract":"Because facial expression is easy to be confused, and is easily affected by environment, Angle and other factors, this paper proposes an improved Faster R-CNN based facial expression detection method. In this method, histogram equalization and adaptive histogram equalization are preprocessed for SFEW 2.0 of the facial expression data set, and the facial expression data is enhanced and expanded. Then the repetitive experimental optimization of the hyperparameters is carried out to improve the training and learning effect of the model and improve the detection accuracy. In the end, based on the regularization model structure optimization, Soft-max cross entropy classification loss function and L1 Smooth regression loss function with parameter constraint term were proposed. The regularization method was used to optimize parameter weight, improve detection accuracy, and an improved Faster R-CNN model adapted to face expression characteristics was obtained.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123850425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9181887
Niu Yan, Jia Yafei, Ye Sheng-lan
The arbitrariness and unpredictability of the sequence generated by the key stream generator determine the strength of the stream cipher, the design of the key stream generator becomes the core problem, the linear feedback shift register is generally used as the driving part of the key stream generator. The number of stages of the shortest linear shift register that produces the sequence is an important indicator of the strength of the stream cipher system, called the linear complexity of the sequence. Based on this, this paper applies the Boyer-Moore algorithm to the cryptography problem, and proves the feasibility of using the Boyer-Moore algorithm to obtain the shortest linear shift register and the linear complexity of the sequence, and proves the uniqueness of the shortest linear shift register obtained by the Boyer-Moore algorithm.
{"title":"Application Research of Boyer-Moore Algorithm in Cryptography","authors":"Niu Yan, Jia Yafei, Ye Sheng-lan","doi":"10.1109/ICAICA50127.2020.9181887","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9181887","url":null,"abstract":"The arbitrariness and unpredictability of the sequence generated by the key stream generator determine the strength of the stream cipher, the design of the key stream generator becomes the core problem, the linear feedback shift register is generally used as the driving part of the key stream generator. The number of stages of the shortest linear shift register that produces the sequence is an important indicator of the strength of the stream cipher system, called the linear complexity of the sequence. Based on this, this paper applies the Boyer-Moore algorithm to the cryptography problem, and proves the feasibility of using the Boyer-Moore algorithm to obtain the shortest linear shift register and the linear complexity of the sequence, and proves the uniqueness of the shortest linear shift register obtained by the Boyer-Moore algorithm.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131460920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182466
Yingying Zhao, Hui Xu, Cheng Zhou
Community detection based on nonnegative matrix factorization (NMF) has the advantages of clear physical meaning, simple calculation and strong interpretability, but its accuracy needs to be improved. For this reason, this paper puts forward the community detection algorithm using NMF with two attribute information matrices(2AMNMF). First of all, two attribute information matrices are created from calculating similarity between the entity and entity, then one of which is decomposed into two non-negative matrices by NMF, another attribute information matrix is added into objective function for optimization. Evaluation is made by modularity Q. The experiment results show that the algorithm of community detection we proposed is more accurate than the original NMF algorithm.
{"title":"Nonnegative Matrix Factorization Algorithm with Two Attribute Matrices for Community Detection","authors":"Yingying Zhao, Hui Xu, Cheng Zhou","doi":"10.1109/ICAICA50127.2020.9182466","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182466","url":null,"abstract":"Community detection based on nonnegative matrix factorization (NMF) has the advantages of clear physical meaning, simple calculation and strong interpretability, but its accuracy needs to be improved. For this reason, this paper puts forward the community detection algorithm using NMF with two attribute information matrices(2AMNMF). First of all, two attribute information matrices are created from calculating similarity between the entity and entity, then one of which is decomposed into two non-negative matrices by NMF, another attribute information matrix is added into objective function for optimization. Evaluation is made by modularity Q. The experiment results show that the algorithm of community detection we proposed is more accurate than the original NMF algorithm.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121763698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182567
Yuyang Li, Xuemei Xu, Yipeng Ding, Linzi Yin
In this paper, we introduce the principle of identifying state transition based on the Van der Pol-Duffing oscillator in weak signal detection, which demonstrate the importance to indicate external perturbation existence and detect weak signal accurately. Starting from analyzing the insufficiency of employing classical identification methods occurring in the detecting process, we put forward a novel identification method named region analyzation method to improve the deficiency. Then, an establishment and feasibility analysis of this proposed method are described exhaustively. Numerical experiments on merits of this proposed method that is compared with the classical methods are carried out. The results indicate that this proposed method has better identifying capability than the classical methods and provides extendibility to engineering application.
本文介绍了在弱信号检测中基于Van der Pol-Duffing振荡器的状态转移识别原理，证明了识别外部扰动存在性和准确检测弱信号的重要性。从分析传统识别方法在检测过程中存在的不足入手，提出了一种新的识别方法——区域分析法。然后详细介绍了该方法的建立和可行性分析。通过数值实验对该方法的优点进行了比较，并与经典方法进行了比较。结果表明，该方法比传统方法具有更好的识别能力，并具有可扩展性。
{"title":"A novel method for identification of state transition based on the van der Pol-Duffing oscillator in weak signal detection","authors":"Yuyang Li, Xuemei Xu, Yipeng Ding, Linzi Yin","doi":"10.1109/ICAICA50127.2020.9182567","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182567","url":null,"abstract":"In this paper, we introduce the principle of identifying state transition based on the Van der Pol-Duffing oscillator in weak signal detection, which demonstrate the importance to indicate external perturbation existence and detect weak signal accurately. Starting from analyzing the insufficiency of employing classical identification methods occurring in the detecting process, we put forward a novel identification method named region analyzation method to improve the deficiency. Then, an establishment and feasibility analysis of this proposed method are described exhaustively. Numerical experiments on merits of this proposed method that is compared with the classical methods are carried out. The results indicate that this proposed method has better identifying capability than the classical methods and provides extendibility to engineering application.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"59 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133677909","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182657
Xiaoming Zhang, Hang Lu, Jiahao Li, Xushan Peng, Yongping Li, Li Liu, Zhengwu Dai, Weicong Zhang
In recent years, with the rapid development of electronic technology and the improvement of people's quality of life, smart home system gradually comes into being. People often waste the use of lighting system in places with long lighting time and more lighting equipment (such as school classrooms, shopping malls, etc.). Due to the lack of scientific management and the weak sense of responsibility of management personnel, it is necessary to implement lighting energy-saving measures on the premise of ensuring lighting quality. In order to realize the intelligent lighting control system for places with long lighting, the system mainly uses the intelligent lighting control hardware, as well as the python terminal to obtain local time. In this way, the change of lighting can be controlled according to the local time, so as to reduce the artificial management time and the waste of electric energy. This can not only save energy, but also produce obvious economic benefits.
{"title":"Design and Implementation of Intelligent Light Control System Based on Arduino","authors":"Xiaoming Zhang, Hang Lu, Jiahao Li, Xushan Peng, Yongping Li, Li Liu, Zhengwu Dai, Weicong Zhang","doi":"10.1109/ICAICA50127.2020.9182657","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182657","url":null,"abstract":"In recent years, with the rapid development of electronic technology and the improvement of people's quality of life, smart home system gradually comes into being. People often waste the use of lighting system in places with long lighting time and more lighting equipment (such as school classrooms, shopping malls, etc.). Due to the lack of scientific management and the weak sense of responsibility of management personnel, it is necessary to implement lighting energy-saving measures on the premise of ensuring lighting quality. In order to realize the intelligent lighting control system for places with long lighting, the system mainly uses the intelligent lighting control hardware, as well as the python terminal to obtain local time. In this way, the change of lighting can be controlled according to the local time, so as to reduce the artificial management time and the waste of electric energy. This can not only save energy, but also produce obvious economic benefits.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132281093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We propose a method of 3D reconstruction of small-sized object based on Kinect V2 RGB-D camera and turntable, which eliminates the need of costly feature extraction and robust matching techniques for motion estimation. Identification and detection of a QR code are used to calibrate the system, and on this basis, point cloud coordinate conversion and background removal are realized. Our coarse registration algorithm uses the fixed rotation angle of the turntable to construct the rotation matrix between frames. Combined with ICP (Iterative Closest Point) algorithm for precise registration, the object point cloud model is obtained. We achieve a cost-effective, convenient and practical 3D reconstruction process for small-sized objects. Experimental results show that the method can stably and effectively obtain 3D models of objects that are small and difficult to extract features, which has certain application value in product display.
{"title":"3D Object Reconstruction with Kinect Based on QR Code Calibration","authors":"Shidong Chen, Jianjun Yi, Hongkai Ding, Zhuoran Wang, Jinyang Min, Hailei Wu, Shuqing Cao, Jinzhen Mu","doi":"10.1109/ICAICA50127.2020.9181884","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9181884","url":null,"abstract":"We propose a method of 3D reconstruction of small-sized object based on Kinect V2 RGB-D camera and turntable, which eliminates the need of costly feature extraction and robust matching techniques for motion estimation. Identification and detection of a QR code are used to calibrate the system, and on this basis, point cloud coordinate conversion and background removal are realized. Our coarse registration algorithm uses the fixed rotation angle of the turntable to construct the rotation matrix between frames. Combined with ICP (Iterative Closest Point) algorithm for precise registration, the object point cloud model is obtained. We achieve a cost-effective, convenient and practical 3D reconstruction process for small-sized objects. Experimental results show that the method can stably and effectively obtain 3D models of objects that are small and difficult to extract features, which has certain application value in product display.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134210442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：