Energy-Constrained Model Pruning for Efficient In-Orbit Object Detection in Optical Remote Sensing Images

Efficient object detection from optical remote sensing (RS) images has always been an important interpretation task for in-orbit RS applications. In recent years, convolutional neural networks have been widely used for object detection with significantly improved detection accuracy. However, the large detection models pose great challenges for the computing, memory and energy supply of resource-constrained in-orbit platforms. In this paper, we propose an efficient in-orbit object detection method with low memory, computation and energy requirements. The proposed method first integrates the compact modules of GhostNet into the detector and further performs the L1-norm based filter pruning to significantly reduce model size and computational complexity. Besides, we propose to use energy as a key metric in filter pruning, and present a novel energy-guided layer-wise pruning rate estimation method so as to achieve energy-efficient object detection. Comprehensive experiments have shown the effectiveness of the proposed method in terms of model size, computational complexity, latency and energy consumption, while maintaining comparable detection accuracy.