To address the issues of short flight duration and the inability to carry high-computation resources in small observation Unmanned Aerial Vehicle (UAV) due to limited energy and payload capacities, we proposes a deployment framework for an air-water surface collaborative observation system based on energy replenishment and computation offloading. In this framework, the UAV serve as platforms for observation tools, while Unmanned Surface Vehicle (USV) act as platforms for energy replenishment and edge computing nodes. The edge computing nodes process, analyze, and distribute the observation data received from the UAV. Upon receiving a charging signal, the UAV perform coordinated positioning with the USV using high-precision BeiDou positioning, land on the USV. After recharging, the UAV resume their observation tasks. Experimental results demonstrate that this framework prevents the small observation UAV from having to carry heavy computational loads during flight，and also, the small observation UAV can utilize the USV platform for cyclic recharging and takeoff. The findings of this study can be extended to the collaborative application of multiple UAVs and USVs, enabling broader and more sustained observations. This approach has significant potential for applications in environmental monitoring, disaster rescue, marine mapping, border patrol, and marine aquaculture capacity monitoring.