Search

Service robots have received increasing attention in mobile robotics field with the recent advancement in technology and computing power. One of the important aspects of service robots is the vision recognition system. This system is crucial for the robot to navigate through the surrounding and detect the objects such as obstacles and targets. Most of the recent service robots use costly sensors such as LIDAR and high-end vision system in order to recognize its environment. This paper proposes to use a cost-effective sensor which is an omni-directional camera to obtain a full 360° field of view (FOV) of the surrounding environment. The images from the camera were then used to identify the location of the human in any direction from the robot. From the results, the optimal method to unwrap the omni-directional image and recognition of human is promising. In addition, the direction and heading of the robot is also configurable in future works using the proposed method.

Vision aided pick and place cartesian robot is a combination of machine vision system and robotic system. They communicate with each other simultaneously to perform object sorting. In this project, machine vision algorithm for object sorting to solve the problem in failure sorting due to imperfection of images edges and different types of colours is proposed. The image is acquired by a camera and followed by image calibration. Pre-processing of image is performed through these methods, which are HSI colour space transformation, Gaussian filter for image filtering, Otsu’s method for image binarization, and Canny edge detection. LabVIEW edge-based geometric matching is selected for template matching. After the vision application analysed the image, electrical signal will send to robotic arm for object sorting if the acquired image is matched with template image. The proposed machine vision algorithm has yielded an accurate template matching score from 800 to 1000 under different disturbances and conditions. This machine vision algorithm provides more customizable parameters for each methods yet improves the accuracy of template matching.

There are variety of fruits around the world, different types of fruits contain different types of nutrients and vitamins which could benefits our health. In order to understand which fruit can provide specific type of nutrients, we need to identify the types of fruits. However, fruits grow in a different shape, colour and texture based on the country they were planted and the environment of the land. Implementing a machine vision-based recognition on the fruits can help people recognize them easily. In this paper, an edge detection method is applied using computer vision approach to recognize different types of fruits. The fruits are classified based on the features extracted from their images. In the experiment, a total of 450 images of three types of fruit are used, which are apples, lemons and mangoes. Pre-processing steps are applied on the captured image to improve the quality of fruit details and the edge features are extracted using Canny Edge Detection method. Classification of the fruits is accomplished using two different types of learning model, the deep leaning model, Convolution Neural Network (CNN) and machine learning model, Support Vector Machines (SVM). The performance of both classifiers is compared and the model with the best performance, SVM is chosen as the model for the system. The system can achieve 86% classification accuracy with the SVM model, which is good enough for fruit recognition.

We have designed a service robot that can be used for Wi-Fi RSSI Fingerprint database construction for indoor positioning system. This work aims to aid and ease the signal fingerprint database construction process which currently conducted manually by carrying the data acquisition tools around the experimental field. The robot architecture design considered the values and constraint in performance, aesthetic, cost, and expandability. Analysis of the robot’s mobile specification was made in order to choose the optimum hardware components. The robot has three main sections which are mobile platform, storage compartment, and user interactive screen that is capable to display facial expression and other useful information.

The amount of light is an important issue in several scenarios ranging from scenic design, light pollution study, robots navigation, occupational health and safety, illumination engineering, agriculture, medical appliances and many more. It is typically determined by using an illumination meter. The meter, also known as lux meter is used to measure the density of light in an area which measured in lx unit. It is used in photometry as a measure of the intensity, as perceived by the human eye of light that hits or passes through a surface. As in normal meter, the lux value was obviously a displayed value, and hardly used for embedded application as well as for lighting monitoring considering its expensive price. This limits the lighting monitoring in certain critical field. Therefore, in this paper, we present our initial works on the development of a webcam based lux meter that is applicable and suitable for lighting monitoring as well as the ability to be used in embedded application. A series of controlled images are taken, and image processing is applied to the images. The results of image processing are statistically analyzed and a linear relationship between lux value and average grayscale has been obtained with satisfactory R2. The linear function is tested and the results are justified where the algorithm for low cost webcam-based digital lux meter has been successfully developed.