多角度遥感对地观测能够提供更加丰富、多方向的遥感特征，提高地类之间的可区分性，为地物覆盖的精确识别打下坚实的数据基础。GF-7是我国继ZY-3号卫星后的首颗亚米级测绘卫星，这为利用多角度特性解决“异物同谱”的问题，提高作物的识别精度带来了机遇。本文利用GF-7号前视、后视全色及后视多光谱数据，各种特征组合输入到支撑向量机分类器进行分类，相对于光谱、纹理等特征，分析多角度特征对作物识别精度的作用。结果表明，较仅应用光谱特征，光谱与角差特征组合使用大蒜和冬小麦的制图精度分别提高了4.07%和3.15%，用户精度分别提高了6.73%和2.12%；较应用光谱与纹理特征，光谱、纹理与角差特征组合使用大蒜和冬小麦的制图精度分别提高了3.14%和1.01%，用户精度分别提高了5.11%和0.67%。通过McNemar检验分析，这种分类精度的提高是稳定的，角差特征使用能有效提高作物的识别精度。究其原因，多角度特征对不同作物类型在多角度观测时的光谱响应具备特有的差异性，这种差异提高了作物之间的可分性，从而保证作物遥感识别的精度。

Multi-angle remote sensing can provide richer and multi-directional features for ground objects observation, improve the distinguishability between land types, and lay a solid data foundation for the accurate identification of ground cover. GF-7 is the first domestic sub meter surveying and mapping satellite after ZY-3 satellite, which brings an opportunity to solve the problem of "foreign matter homospectrum" using multi-angle characteristics and improve the identification accuracy of crops. This paper use GF-7 forward-looking, backward looking panchromatic and backward looking multi-spectral data, and various features combinations are input to the SVM (support vector machine) classifier for classification, used to analyze the influence of multi-angle features on crop recognition accuracy relative to spectral and texture features. The results show that, compared with only spectral features, add the angle difference feature, the production accuracy of garlic and winter wheat is increased by 4.07% and 3.15%, and the user accuracy is increased by 6.73% and 2.12%, respectively. Compared with the combination of spectral and texture features, add the angle difference feature, the production accuracy of garlic and winter wheat is increased by 3.14% and 1.01%, and the user accuracy increased by 5.11% and 0.67%, respectively. Through the analysis of McNemar test, the improvement of classification accuracy is stable, angle difference feature can effectively improve the identification accuracy of crops. Tracing it to its cause, the multi-angle characteristics of GF-7 satellite have unique differences in the spectral response of different crop types during multi-angle observation. The difference improves the separability between crops so as to ensure the accuracy of crop remote sensing mapping.