With the rapid technological development of various different satellite sensors, a huge volume of high-resolution image data sets can now be obtained and widely used in military and civilian fields. Detecting typical targets in satellite images is a challenging task due to the varying size, orientation and background of the target object. Traditional manually engineered features (i.e. HOG, Gabor feature and Hough transform, etc.) do not work well for massive high-resolution remote sensing image data. Thus, we are expected to find an efficient way to automatically learn the presentations from the massive image data and increase the computational efficiency of target detection. Robust and computationally efficient systems are required which can learn presentations from the massive satellite imagery. Comparing to the general objects in nature images, the edge information of targets in satellite images shows more distinctive and concise characteristics. This paper proposes a new target detection framework based on Edge Boxes and Convolutional Neural Networks (CNN). CNN can learn rich features automatically and is invariant to small rotation and shifts, has achieved state of-the-art performance in many image classification databases. Edge Boxes can generate a smaller set of object proposals based on the edges of objects. The proposed method can reduce the computational time of the detector. Moreover, CNN is invariant to minor rotations and shifts in the target object. Extensive experiments demonstrate that the proposed framework is effective in typical target detection systems