Advances in remote sensing technologies for precision agriculture, including small unoccupied aerial vehicles (UAV) or drones, have increased in recent years and become more cost effective and accessible for public consumers to operate. We investigated the use of a small, “off-the-shelf” aerial drone to collect high-resolution (1 cm/px) imagery of intertidal shellfish farms in Washington state to demonstrate applications for inventory development, vegetation mapping and monitoring for nuisance species. Drone flights were completed during summer low-tides (June – August) in 2023 and 2024 on shellfish farms in Willapa Bay and Puget Sound, WA. Imagery was collected with a DJI Mavic 3 multispectral drone with RGB, visible light camera (20 MP) and multispectral camera with green, red, red-edge, and near infrared sensors (5 MP). Images were post-processed and georeferenced into orthomosaics using the photogrammetry software Agisoft Metashape v.2.1.2. Raster orthomosaics were imported into ArcGIS Pro to identify benthic features of interest: bottom grown Pacific oysters (Crassostrea gigas), aquaculture gear (anti-predator clam nets, oyster longlines and flip bags), macroalgae (Ulva spp.), eelgrass (Zostera marina), and ghost shrimp burrows (Neotrypaea californiensis). Benthic features visible in the raster imagery were either heads up digitized (aquaculture gear) or classified (on-bottom Pacific oysters, eelgrass, macroalgae, shrimp burrows) using object-based image analysis (OBIA). For the process of OBIA, raster images were first segmented using groups of neighboring pixels (objects) that share similar attributes. Following image segmentation, training data was created for each benthic feature to be classified. Using the Support Vector Machine (SVM) algorithm, images were classified with inputs from the training data. Any mis-classified areas were re-classified to improve the final classified image. Classified benthic features were converted from raster to vector polygon layers and summary statistics were calculated to determine total areal cover (acres) of each feature. Shellfish biomass estimates were calculated by multiplying average planting or stocking densities for each culture type by total areal cover. Orthomosaics and classified layers can be further utilized by farms in a GIS or web map environment. Repeat drone image collections and classifications can facilitate change detection of benthic features over time at farm-scale, including the distribution of sensitive habitats (eelgrass) or nuisance species (Ulva spp., ghost shrimp). This study demonstrates the use of classified orthomosaics from high-resolution (1 cm/px) drone imagery as a potential tool for intertidal shellfish farm management including biomass estimates for inventory development.