Abstract: Taking the main urban area of Fuzhou City as an example, this research, based on Tencent street view data and satellite remote sensing images, integrates the traditional remote sensing interpretation and machine learning algorithms to measure and compare the spatial difference between its street green view index and vegetation coverage rate. It further analyzes the street green view index influencing factors, and finally proposes a planning and design strategy to intensively improve the quality of street greenery. The research has found that: 1) The green view index in the main urban area of Fuzhou forms a “core-edge” structure that is “higher inside the second ring road and decreases outside the second ring road”, and the vegetation coverage rate is generally “low in streets, and high in mountains and suburbs”. 2) There is a significant difference in the spatial distribution of green view index and vegetation coverage rate in the main urban area of Fuzhou. There are many areas with a high green view index but a low vegetation coverage rate, which is mainly caused by the surrounding natural environment or some green structures. There are few areas with a low green view index but a high vegetation coverage rate, which is mainly caused by occlusion and difference in height. 3) Positive factors influencing green view index include better landscape permeability, greater depth of auxiliary green space, layout of green space beside the streets, tall sidewalk trees, arbor and shrub collocation, and street-side recreation space creation. Negative factors include solid wall blocking, road elevation difference, backward infrastructure, and open entrance to the street. Through the comparative study on the vegetation coverage rate and green view index, this paper discloses the trend shift of greenery quality measurement on a human scale, and the planning and design strategy of the street greenery quality can also provide some reference for related researches.