Anthropogenic activities such as urban development, waterfront expansion, and large-scale land reclamation increasingly disrupt sediment dynamics in rivers, estuaries, and coastal zones. These disturbances elevate suspended sediment concentration (SSC), degrading water quality by reducing light penetration, damaging benthic habitats, altering trophic interactions, and threatening biodiversity. Conventional SSC monitoring methods, such as manual sampling, fixed turbidity sensors, and satellite remote sensing, have limitations: manual sampling and sensors offer limited spatiotemporal data, whereas satellite imagery is costly, weather-dependent, and infrequent. To address these constraints, in this study, we propose a high-resolution SSC monitoring framework that integrates unmanned aerial vehicle (UAV)-acquired RGB imagery with in situ turbidity measurements. UAV images were processed via photogrammetry, including orthomosaic generation and pixel-level radiometric analysis. Brightness values from the red spectral channel, highly sensitive to sediment reflectance, were extracted. A linear regression model correlating these pixel values with field-measured SSC achieved strong predictive performance (R² = 0.84). Field experiments at a riverine sediment source confirmed the system’s ability to detect rapid SSC increases on minute-to-hour scales and to identify sediment plume boundaries with high spatial accuracy. While promising, further validation across broader sediment compositions and turbidity conditions is needed. Incorporating multispectral or hyperspectral sensors can enhance predictive accuracy and expand applicability. Overall, this framework bridges the gap between fixed sensors and satellites, providing a flexible, scalable, and cost-effective solution for SSC monitoring.