107 research outputs found
HOG Feature Extraction and KNN Classification for Detecting Vehicle in The Highway
No full textAutonomous car is a vehicle that can guide itself without human intervention. Various types of rudderless vehicles are being developed. Future systems where computers take over the art of driving. The problem is prior to being attention in an autonomous car for obtaining the high safety. Autonomous car need early warning system to avoid accidents in front of the car, especially the system can be used in the Highway location. In this paper, we propose a vision-based vehicle detection system for Autonomous car. Our detection algorithm consists of three main components: HOG feature extraction, KNN classifier, and vehicle detection. Feature extraction has been used to recognize an object such as cars. In this case, we use HOG feature extraction to detect as a car or non-car. We use the KNN algorithm to classify. KNN Classification in previous studies had quite good results. Car detected by matching about trining data with testing data. Trining data created by extract HOG feature from image 304 x 240 pixels. The system will produce a classification between car or non-car
Human guide tracking using combined histogram of oriented gradient and entropy difference minimization algorithm for camera follower
No full textMoving human is quite complicated to track since there are variations in background, texture, and lighting in an environment. This paper presents an effective method for tracking a human guide from a camera follower in both indoor and outdoor condition. This algorithm is designed to be embedded in a smart wheelchair. A conventional human detection by using Histogram of Oriented Gradient (HOG) was used at the first stage, then each detected human by HOG is utilized for tracking algorithm. The detected area from HOG is converted to grayscale image and its Entropy Difference Minimization (HOG-EDM) is calculated. The process is repeated for every frame. The entropy minimization is used as matching function in the tracking subsystem to determine the candidate of tracked object in the upcoming frame. The proposed algorithm has been proven to work well in indoor and outdoor area, even with textured background. Our testing based on self-made and public datasets shows that HOG-EDM method reaches over 80% accurac
Sistem Pengenalan Suara Pada Lingkungan Bising Untuk Kursi Roda Pintar Menggunakan MFCC dan ResNet50V2
No full textIndonesia pada tahun 2022 kurang lebih mencapai 900.000 jiwa. Pada kasus
tertentu, terdapat juga seseorang yang mengidap lebih dari 1 jenis disabilitas
sehingga dikategorikan sebagai penyandang disabilitas ganda. Untuk membantu
penyandang disabilitas ganda dalam beraktivitas sehari-hari, terutama dalam
meningkatkan mobilitasnya, maka dilakukan sebuah penelitian dengan judul
”Pengenalan Papan Nama Ruangan untuk Kendali Kursi Roda Pintar
menggunakan YOLOv7-Tiny dan EasyOCR berbasis TX2" (Alqadri &
Utaminingrum, 2023) untuk mengembangkan sistem navigasi otonom pada kursi
roda yang dapat mengantarkan pengguna ke ruangan yang dituju. Namun sistem
tersebut masih memerlukan input dari keyboard sehingga belum dapat
menyelesaikan permasalahan yang dialami penyandang disabilitas ganda. Oleh
sebab itu, diperlukan pengembangan input alternatif lainnya yang dapat
mengurangi interaksi fisik pengguna dengan sistem, salah satunya adalah dengan
menggunakan suara. Sistem pengenalan suara sendiri memiliki beberapa
rintangan yang perlu dihadapi, salah satunya adalah noise yang dapat
mengurangi keandalan sistem. Oleh sebab itu, diperlukan pengembangan sistem
pengenalan suara yang mampu beroperasi pada lingkungan bising dengan
menggunakan metode noise reduction Spectral Gating, ekstraksi ciri MFCC dan
model deep learning ResNet50v2. Berdasarkan pengujian yang dilakukan,
diketahui bahwa epoch ke-37 merupakan epoch terbaik yang digunakan untuk
melatih model. Selain itu, diketahui bahwa rata-rata waktu komputasi sistem
adalah sebesar 2385.2 ms. Kemudian berdasarkan pengujian oleh 5 subjek,
diketahui bahwa rata-rata akurasi pada ruang hening dan bising secara berturutturut
sebesar 91% dan 81%
Text detection and recognition using multiple phase method on various product label for visual impaired people
No full textBuilding Segmentation of Satellite Image based on Area and Perimeter using Region Growing
No full textA building can be known by look shape, color, and texture. Building can be detected by using many method. Region growing is one simple segmentation method because only use seed point. Before segmentation, the image must be preprocessing include sharpening, binerization by otsu method. Sharpening for clarify image and otsu method changed image valued 0 and 1. Next step is post-preprocessing include segmentation using region growing and opening closing operation. And the last process is detection building where building of detection will be signed. In this research, we present region growing for building segmentation by using both area and perimeter as a important variable in the region growing. Value of area more than 10 and perimeter is more than 50 are produced most of building
Newton’s Method for Distance Optimization in Firefly Algorithm in Determining Optimum Nutrition for Laying Hens
No full textAn accurate calculation of feed nutrition and more affordable price is an extremely complex. Firefly algorithm is an algorithm designed for optimization calculation whose output is highly dependent on light intensity (β), which is influenced by distance (r). Therefore, in order to produce maximum output values, an optimization of firefly distance should be done. The most appropriate method is Newton’s Method as it has the capability of solving roots of equations accurately. From the testing of distance optimization in firefly algorithm, a fairly good increase in the fitness value was obtained.Keywords: Newton Method, Firefly Algorith
Error numerical analysis for result of rainfall prediction between Tsukamoto FIS and hybrid Tsukamoto FIS with GA
No full text
- …
