Facial expression recognition is becoming a hot topic due to its wide applications in computervision research fields. Traditional methods adopt hand-crafted features combined with classifiers to achieve the recogniti...
详细信息
ISBN:
(纸本)9789811379864;9789811379857
Facial expression recognition is becoming a hot topic due to its wide applications in computervision research fields. Traditional methods adopt hand-crafted features combined with classifiers to achieve the recognition goal. However, the accuracy of these methods often relies heavily on the extracted features and the classifier's parameters, and thus cannot get good result with unseen data. Recently, deep learning, which simulates the mechanism of human brain to interpret data, has shown remarkable results in visual object recognition. In this paper, we present a novel convolutional neural network which consists of local binary patterns and improved Inception-ResNet layers for automatic facial expression recognition. We apply the proposed method to three expression datasets, i.e., the Extended Cohn-kanade Dataset (CK+), the Japanese Female Expression Database (JAFFE), and the FER2013 Dataset. the experimental results demonstrate the feasibility and effectiveness of our proposed network.
the article presents an automated assembly station designed by students as part of Project Based Learning. the task of the project was to familiarize withthe issues of integration of automation and control elements o...
详细信息
this paper describes a new method of constructing a saliency map that can be used in object finding for a robotvision system. A saliency map shows the weight of each pixel in an image. the weights represent the proba...
详细信息
ISBN:
(纸本)9781467321112
this paper describes a new method of constructing a saliency map that can be used in object finding for a robotvision system. A saliency map shows the weight of each pixel in an image. the weights represent the probability of the location of a given object. Traditionally, a saliency map is constructed based on the analysis of the image color features of the RGB color space. We redefine the saliency map of an image on the HSL color space, which makes our method more robust under a wide range of luminance. Experimental results show that the range can cover most cases in everyday life. thus, the system can successfully find objects under different conditions and various light sources.
the aim of this study is to design and implement the mobile controlled sanitizing robot with a camera by comparing it with a pesticide spraying robot. the components used in the design of a mobile controlled sanitizin...
详细信息
the aim of this study is to design and implement the mobile controlled sanitizing robot with a camera by comparing it with a pesticide spraying robot. the components used in the design of a mobile controlled sanitizing robot are Arduino, Bluetooth module, motor shield, camera, and chassis. the Arduino board is programmed from a computer using the Arduino IDE app. For groups 1 and 2, the overall sample size is 20. Sanitizing robot achieved 35% less standard error, moves 23.77% faster than the pesticide spraying robot, and has a significance value of less than 0.0001(p<0.05). In this study, it is found that the sanitizing robot performs better than the pesticide spraying robot in spraying on a plain surface.
We demonstrate that structured light-based depth sensing with standard perception algorithms can enable mobile peer-to-peer interaction between humans and robots. We posit that the use of recent emerging devices for d...
详细信息
We demonstrate that structured light-based depth sensing with standard perception algorithms can enable mobile peer-to-peer interaction between humans and robots. We posit that the use of recent emerging devices for depth-based imaging can enable robot perception of non-verbal cues in human movement in the face of lighting and minor terrain variations. Toward this end, we have developed an integrated robotic system capable of person following and responding to verbal and non-verbal commands under varying lighting conditions and uneven terrain. the feasibility of our system for peer-to-peer HRI is demonstrated through two trials in indoor and outdoor environments.
this paper describes a wirelessly controlled underwater robotthat can move under water and it can be even controlled by an android smart phone very easily. An arduino based platform in used to process, transmit and r...
详细信息
this paper describes a wirelessly controlled underwater robotthat can move under water and it can be even controlled by an android smart phone very easily. An arduino based platform in used to process, transmit and receive all information. there are many kinds of robots have been designed and constructed withthe development of computer and information processing technology. A low cost underwater robot and its propulsion system are complete wirelessly using the combination of a pair of arduino board and a pair of RF module that makes our project different. Six handmade waterproof thrusters control the propulsion system horizontally and vertically of this robot. the camera of this robot works as eyes. this robot can be used in various purpose such as underwater environmental monitoring, oceanographic survey, pipeline and subsea structure inspection, debris inspection and more related purpose.
Waste collection has become one of the most challenging tasks in highly populated countries. In places like pond and surrounding's, people gather and put light weight waste regularly. Waste collection in both wate...
详细信息
ISBN:
(纸本)9781665414487
Waste collection has become one of the most challenging tasks in highly populated countries. In places like pond and surrounding's, people gather and put light weight waste regularly. Waste collection in both water and land requires unusual manual effort. However, by using robot with special design it become very easy. In this paper, a novel design of screw propelled amphibian robot is proposed to manage waste collection in both land and water. the robot can work autonomously in wide variety of terrains which includes grass, road, marsh, water, etc. the mechanical design of the robot was developed in computer Aided Design (CAD) and prototype was designed and tested in various working environments. Mobile Application was developed for manual control.
We present the Utility Model - a mathematical model to incorporate the dynamics of adaptive multimedia systems (AMSs). It is based on the concepts of quality profile, quality-resource mapping, session and system utili...
详细信息
Based appear for magnetic navigation system for substation inspection robot navigation course accumulation of errors phenomenon, fuzzy PID control algorithm is applied to inspection robot navigation system, navigation...
详细信息
ISBN:
(纸本)9781510813465
Based appear for magnetic navigation system for substation inspection robot navigation course accumulation of errors phenomenon, fuzzy PID control algorithm is applied to inspection robot navigation system, navigation paththrough the logic of correction, to achieve stability navigation. On the movement patterns of inspection robot is modeled using fuzzy algorithm parameters that affect the stability of the navigation processing, the simulation shows that fuzzy-PID robot navigation algorithm higher precision control, better operational stability.
Automatic pedestrian detection and tracking is an important issue in the field of computervision and robot navigation. We propose a scheme to implement multi-pedestrian tracking in a scene obtained by a static camera...
详细信息
Automatic pedestrian detection and tracking is an important issue in the field of computervision and robot navigation. We propose a scheme to implement multi-pedestrian tracking in a scene obtained by a static camera. We combine HOG and HOF features to describe the characteristics of persons. AdaBoost algorithm is then utilized to train a strong classifier for better detection accuracy of persons. We use particle filter as the tracking framework and train a online SVM classifier, which is the observation model, by reliable samples from associated detections without occlusion. In consideration of the target's velocity into the weights calculation, the data association is more reliable. the preliminary experiments on some benchmark data demonstrate the feasibility of the proposed scheme.
暂无评论