Manimehala Nadarajan

Probabilistic multi SVM weed species classification for weed scouting and selective spot weeding

In this paper, a probabilistic output multi SVMs were used to classify the weed seedlings into groups for spot spraying and weed scouting application. Weeds in the samples are collected at approximely 1-4 weeks after post emergence. The weed seedlings are classified using Support Vector machines while feature selection and fine tuning of classifier parameters were fine tuned using genetic algorithm. The features which included regional shapes parameters, fractal dimensions and elliptical Fourier coefficients, skeleton statistics, boundary to centroid and colour statistics were extracted from individual leaves and the overall binarized shape of the weed seedlings. The resulting SVM ensemble classifier is able to classify the various weed seedlings into various classes at a reasonable rate which can be further improved by enlarging training sets and improving individual SVMs.

Medical Tele-Diagnosis Robot (MTR) - Internet Based Communication & Navigation System

Medical Tele-diagnosis Robot (MTR) is a cost effective telemedicine mobile robot that provides tele-presence capability for the specialist on a remote location to virtually meet the patient, perform diagnostics and consult the resident doctor regarding the patient via internet. This paper highlights on the development of a doctor-robot interface where the doctor or user can control the robot reliably via regular internet connection from a different location, a distributed secured network for MTRs communication, an audiovisual communication system for tele-diagnosis and a navigation safety system called Danger Monitoring System (DMS) as part of MTRs assistive internet based navigation remote control system. The overall setup and maintenance cost of MTR is reduced by adopting a decentralized network via hybrid P2P technology. With this, the network load is distributed among the users. As for the audiovisual system, the timeliness of the video transmission from the robot to the operator can be attained by CUDA H.264 video encoding to reduce the size of the video stream and by taking advantage of the highly-parallel processors in the graphics processing unit. Combinations of sensors are place around the robot to provide data on the robots surrounding during operation. The sensors data are fed into the DMS algorithm which is equipped with fuzzy logic based artificial intelligence system to process the data from all the sensors and user input to decide preventative measures to avoid any danger to humans and the robot in terms of obstacle avoidance and robot tilt angle safety. The overall system is tested by a set of experiments and found to be demonstrating an acceptable performance. This system proved to be suitable to be used in MTR.

A LabVIEW Design for Frontal and Non-Frontal Human Face Detection System in Complex Background

Biometric identification has advanced vastly since many decades ago. It became a blooming area for research as biometric technology has been used extensively in areas like robotics, surveillance, security and others. Face technology is more preferable due to its reliability and accuracy. By and large, face detection is the first processing stage that is performed before extending to face identification or tracking. The main challenge in face detection is the sensitiveness of the detection to pose, illumination, background and orientation. Thus, it is crucial to design a face detection system that can accommodate those problems. In this paper, a face detection algorithm is developed and designed in LabVIEW that is flexible to adapt changes in background and different face angle. Skin color detection method blending with edge and circle detection is used to improve the accuracy of face detected. The overall system designed in LabVIEW was tested in real time and it achieves accuracy about 97%.

Design and Development of Tangible Instruction Set for Educational Robotic System

Programmable tangible blocks educational robotic system (C-Block) was introduced as an approach for project-based learning (PBL) curriculum. It aims to provide a tangible method of doing programming for younger kids and hence allowing them to exploring in STEM education as early as possible. In this paper, the design and development of instruction block sets and the corresponding system to extract the information out from the instruction blocks were discussed. The state-of-the-art technology proposed in this research can be very fruitful to enhance the implementation of the robotics in education system.

Detection of Amaranthus palmeri sp. Seedlings in Vegetable Farms Using Genetic Algorithm Optimized Support Vector Machine

This research is a part of a larger research scope to recognise individual weed species for weed scouting and spot weeding. Support Vector Machines are used to classify the presence of specified weeds (Amaranthus palmeri ) by analysing the shape of the weeds. Weed leaves are extracted using image dilation and erosion methods. Several shape feature types were proposed and a total of 59 features were used as the feature pool. The feature selection and fine tuning of the Support Vector Machine are performed using Genetic Algorithm. The outcome is a generalised classifier that enables classification of weed leaves with an average of 90.5% classification rate.

An Application on Medical Tele-Diagnosis Robot (MTR) for Real-Time Motion Detection

The use of medical robots in healthcare industry especially in rural areas are hitting limelight these days. Development of Medical Tele-diagnosis Robot (MTR) has gain importance to unravel the need of medical emergencies. Nevertheless, challenges for a better visual communication still arises. Thus, a face identification and tracking system for MTR is designed to allow an automated visual which will ease the medical specialist to identify and keep the patient in the best view for visual communication. This paper emphasis on the motion detection module which is the first module of the system. An improved motion detection technique is proposed which suits a real-time application for a dynamic background. Frame differencing method was used to detect the motion of the target. The developed motion detection module succeeded an accuracy of 96% resulting an average of 97% of the whole MTR.