: : Remote sensing image scene classification is a hot research area for its wide applications. It aims to quickly and accurately identify
and locate a large number of objects of predefined categories in a given image scenes. Here we are using some pre-defined model and custom
model to recognize the image scenes from given video feed and image. In the representative algorithms of each stage are introduced in detail.
Then the public and special datasets commonly used in target detection are introduced, and various representative algorithms are analyzed and
compared in this field. Finally, the potential challenges for target detection are prospected.
.
Keywords: Object detection and recognition, Deep Learning, Classification performance.