Claim Missing Document
Check
Articles

Found 2 Documents
Search

OBJECT DETECTION FOR LOW-LIGHT ENVIRONMENT USING MULTISCALE RETINEX Anthonius Adi Nugroho
Jurnal Riset Informatika Vol. 8 No. 2 (2026): Maret 2026
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34288/jri.v8i2.493

Abstract

Object detection is a critical task in computer vision, yet its performance degrades significantly under low-light conditions due to loss of detail and diminished features. This study proposes an image enhancement framework to improve detection robustness in challenging lighting. The methodology integrates Multiscale Retinex (MSR) for image enhancement and SSD MobileNet V2 for object detection. MSR was configured with optimal parameters (scale1:10, scale2:60, scale3:180, σ:100, β:30) to enhance brightness while preserving crucial image details. The experimental results demonstrate that Retinex correction is highly effective in extreme low-light scenarios. In 0 lux conditions, where objects were completely undetectable without processing, the proposed method enabled detection with confidence levels between 62% and 96%, yielding an average accuracy increase of 50%. In 15 lux conditions, accuracy improved by 6.6%. However, the system degraded at intensities above 25 lux, suggesting that the enhancement is most beneficial in near-dark environments. In conclusion, Multiscale Retinex significantly enhances the capability of SSD MobileNet V2 for object detection in environments with illumination below 77 lux. This approach provides a viable solution for improving the reliability of surveillance and automated systems operating in unpredictable lighting.
PERANCANGAN MAINAN INTERAKTIF UNTUK MELATIH KOORDINASI MOTORIK HALUS: STUDI KASUS PERMAINAN LABIRIN 2-AXIS BERBASIS MIKROKONTROLER Anthonius Adi Nugroho; Karen Elvina
Jurnal Kreatif : Desain Produk Industri dan Arsitektur Vol. 14 No. 1 (2026): Vol. 14., No. 1., April 2026
Publisher : Indonesian Society of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46964/jkdpia.v14i1.1834

Abstract

Shift in children's preferences from traditional toys to digital games has raised concerns regarding the deficiency of physical activity and underdeveloped motor skills. Fine motor skills and hand-eye coordination are fundamentally crucial for a child's cognitive and physical development. This research endeavors to design an interactive microcontroller-based maze toy that integrates technology with physical interaction to train fine motor coordination. The research methodology employed was Research and Development (R&D), utilizing a simplified Borg & Gall model encompassing the stages of needs analysis, prototyping, and testing. The system was engineered using a dual-axis mechanism (X-axis for roll and Y-axis for pitch), which is controlled by a potentiometer and servo motors, enabling the board to move with precision across eight distinct positions. The testing results demonstrate that the game interface is easily understood by users, with the fastest completion time recorded at 32 seconds and the average completion time at 51.7 seconds. Furthermore, a significant performance increase was observed, evidenced by a 53.76% reduction in the average completion time from the first to the sixth trial. This leads to the conclusion that this 2-axis maze game is effective as an interactive educational medium for training and enhancing users' hand-eye coordination and fine motor skills.