Pub Date : 2022-03-12DOI: 10.1109/ICIPRob54042.2022.9798740
Shota Kaneda, C. Premachandra
In this paper, we present a comparison of the accuracies of AI-based object recognition using a general camera and an omnidirectional camera. Recently, with the improvement in machine learning technology, there has been significant research related to the detection and classification of objects from images and videos. In this field, it is common to use horizontal images and videos. However, omnidirectional cameras, which can acquire information from the entire surrounding area, are becoming popular in addition to general cameras. Although there are some studies on object recognition using these cameras, almost no studies have focused on comparisons between object recognition using general and omnidirectional cameras. Therefore, in this study, we compared the recognition rate of object recognition using the YOLO algorithm on both general and omnidirectional images taken in the same environment.
{"title":"AI Based Object Recognition Performance between General Camera and Omnidirectional Camera Images","authors":"Shota Kaneda, C. Premachandra","doi":"10.1109/ICIPRob54042.2022.9798740","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798740","url":null,"abstract":"In this paper, we present a comparison of the accuracies of AI-based object recognition using a general camera and an omnidirectional camera. Recently, with the improvement in machine learning technology, there has been significant research related to the detection and classification of objects from images and videos. In this field, it is common to use horizontal images and videos. However, omnidirectional cameras, which can acquire information from the entire surrounding area, are becoming popular in addition to general cameras. Although there are some studies on object recognition using these cameras, almost no studies have focused on comparisons between object recognition using general and omnidirectional cameras. Therefore, in this study, we compared the recognition rate of object recognition using the YOLO algorithm on both general and omnidirectional images taken in the same environment.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132469579","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 : 2022-03-12DOI: 10.1109/ICIPRob54042.2022.9798743
Ridma Ganganath, B. Annasiwaththa
Inverted pendulum is one of the nonlinear problems discussed in undergraduate level control engineering courses, and the knowledge gained by studying Inverted pendulum can be widely used in many control applications. Apart from the conventional linear and rotary pendulum systems, balance control of an inverted pendulum using an inertia wheel through angular momentum exchange has been discussed in this research paying special attention to the applicability to distance learning. The closed-loop PID control is used to balance the pendulum system and in order to filter the noise effects, a discrete-time FIR filter has been introduced. In order to verification of the developed controller, the computer simulation-based non-linear simulator using the MATLAB Simulink has been introduced. The control system designed in this work stabilizes the inverted pendulum system for both a noise-free environment and an environment with simulated noise. The designed simulator displays a clear visual simulation of the physical system aiding the online learning.
{"title":"1 DOF Inverted Pendulum Simulation and Control Using The Method of Momentum Exchange","authors":"Ridma Ganganath, B. Annasiwaththa","doi":"10.1109/ICIPRob54042.2022.9798743","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798743","url":null,"abstract":"Inverted pendulum is one of the nonlinear problems discussed in undergraduate level control engineering courses, and the knowledge gained by studying Inverted pendulum can be widely used in many control applications. Apart from the conventional linear and rotary pendulum systems, balance control of an inverted pendulum using an inertia wheel through angular momentum exchange has been discussed in this research paying special attention to the applicability to distance learning. The closed-loop PID control is used to balance the pendulum system and in order to filter the noise effects, a discrete-time FIR filter has been introduced. In order to verification of the developed controller, the computer simulation-based non-linear simulator using the MATLAB Simulink has been introduced. The control system designed in this work stabilizes the inverted pendulum system for both a noise-free environment and an environment with simulated noise. The designed simulator displays a clear visual simulation of the physical system aiding the online learning.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127282589","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 : 2022-03-12DOI: 10.1109/ICIPRob54042.2022.9798718
Wanxin Bao, Ren Komatsu, A. Yamashita, H. Asama
We propose a method for solving well-posed shape from shading problem by using implicit neural representations. We build an image irradiance equation and solve the equation by a sinusoidal representation network called SIREN, which is proposed by Sitzmann et al. in 2020. Object surface is expressed by Oren-Nayar model and a perspective projection model with light source located at the optical center is considered. Based on the above models, image irradiance equation is constructed, which is a partial differential equation (PDE). We introduce a neural network SIREN to solve this PDE, where implicit neural representations use the sine as a periodic activation function. Experiments are performed on three synthetic images and two real images. Results demonstrate that our proposed method performs with much higher accuracy.
{"title":"Solving Well-posed Shape from Shading Problem Using Implicit Neural Representations","authors":"Wanxin Bao, Ren Komatsu, A. Yamashita, H. Asama","doi":"10.1109/ICIPRob54042.2022.9798718","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798718","url":null,"abstract":"We propose a method for solving well-posed shape from shading problem by using implicit neural representations. We build an image irradiance equation and solve the equation by a sinusoidal representation network called SIREN, which is proposed by Sitzmann et al. in 2020. Object surface is expressed by Oren-Nayar model and a perspective projection model with light source located at the optical center is considered. Based on the above models, image irradiance equation is constructed, which is a partial differential equation (PDE). We introduce a neural network SIREN to solve this PDE, where implicit neural representations use the sine as a periodic activation function. Experiments are performed on three synthetic images and two real images. Results demonstrate that our proposed method performs with much higher accuracy.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125555153","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：