Dahnial Syauqy

A laser-vision based obstacle detection and distance estimation for smart wheelchair navigation

The aim of the research is to present an approach of obstacle distance estimation and navigation for smart wheelchair. The smart wheelchair is an electric wheelchair equipped with camera and line laser to navigate and avoid an obstacle. The camera was used to capture images from the environment to sense the pathway condition. The line laser was used in combination with camera to recognize an obstacle in the pathway based on the shape of line laser image in certain angle. A blob method detection was applied on the line laser image to recognize the pattern of the detected obstacles. The line laser projector and camera were mounted in fixed-certain position to make sure a fixed relation between blobs-gaps and obstacle-to-wheelchair distance. A simple linear regression from 16 obtained data was used to represent this relation as the estimated obstacle distance. As a result, the average error between the estimation and actual distance was 1.25 cm from 7 data testing experiments. The experiments result indicates that the proposed method is able to estimate well the distance between wheelchair and obstacle. Later, the smart wheelchair needs to decide further action whether it should turn left, right or just walk straight when facing certain obstacle to avoid it.

Dehydration Level Detection System Based on Urine Condition

The aim of the research is to present a design of early dehydration detection system by analyzing the urine condition. Dehydration is a condition that occurs when the bodys organ function is disrupted caused by lack of fluid present in the human body. There are several causes of excessive fluid secretion which cause the body lack of fluid, including excessive sweating, burns, vomiting and diarrhea. There are three levels of dehydration: mild, moderate and severe dehydration. Severe dehydration level can even cause death. Dehydration symptoms can be detected by various methods. One of them is by analyzing the urine condition. Urine condition has information related to dehydration detection: the color and odor of the urine. The higher level of dehydration experienced, the urine will be more concentrated and has a strong smell. In the proposed system, the color of urine was detected using a color sensor which provide urine color information in the form of RGB values. Meanwhile, the smell of urine is directly proportional to the levels of ammonia in the body and was detected by using an ammonia gas sensor that provides information on ammonia levels in the form of ppm values. In this research, testing is done by putting urine to be tested into a transparent test tube. The bottom part of the test tube is inserted into a black box which has been equipped with a color sensor to detect the color of the urine. While the top of the test tube is an open part, it is used to place the ammonia gas sensor to detect the ammonia levels in the urine. The dehydration level classification was done by using Naïve Bayes method. This method was chosen because it can work independently on each feature object that will be classified. The output features of each sensor became the input for Naïve Bayes classification. There were 66 datasets used in this research, 44 data as training data and 22 data as test data. From the test result, it can be seen that our proposed system has an accuracy of 95.45% in determining the level of dehydration based on urine condition.

Onward movement detection and distance estimation of object using disparity map on stereo vision

The object tracking is used as instruction controller in wheelchair that track the movement direction of object along time. The movement direction include left, right and onward. The left and right direction can be calculated by using the changing of x-coordinate of object in every sub sequence frame. The challenge is to determine the onward moving. The onward moving cannot calculate simply by coordinate of object in 2D. The solution to detect the onward moving is by using the stereo vision camera. We proposed a method to detect the onward movement and calculate the distance of object from camera using stereo vision. The detection rate is 83.1%. The estimation of object distance from the camera is actually only 3–4 meters away. The system detect that the distance of object is 0–5 meters in front of the camera. The determination of distance estimation is appropriate with the actual distance state.

Development of computer vision based obstacle detection and human tracking on smart wheelchair for disabled patient

People with physical disability such as quadriplegics may need a device which assist their mobility. Smart wheelchair is developed based on conventional wheelchair and is also generally equipped with sensors, cameras and computer based system as main processing unit to be able to perform specific algorithm for the intelligent capabilities. We develop smart wheelchair system that facilitates obstacle detection and human tracking based on computer vision. The experiment result of obstacle distance estimation using RANSAC showed lower average error, which is only 1.076 cm compared to linear regression which is 2.508 cm. The average accuracy of human guide detecting algorithm also showed acceptable result, which yield over 80% of accuracy.

Determining direction of moving object using object tracking for smart weelchair controller

People with disabilities who cannot move their whole body need other people to control the smart wheelchair or track the moving of object interest, in this case people. In this paper, we have proposed new movement controller of smart wheelchair using object tracking for disabled people who cannot move their whole body. The proposed method for determining direction of moving object using object tracking has been evaluated using invariant video. Our result study have success rate of multiple object detection is 82.01%, tracking object interest is 90.00%, and determining the moving object directions is 79.63%.