Real-Time Object Detection Using Efficient Convolutional Networks

While recent object detection approaches have greatly improved the accuracy and robustness, the detection speed remains a Challenge for the community. In this paper, we propose an efficient fully convolutional network (EFCN) for real time object detection. EFCN employs the lightweight MobileNet [1] as the base network to significantly reduce the computation cost. Meanwhile, it detects objects in feature maps with multiple scales, and deploys a refining module on the top of each of these feature maps to alleviate the accuracy loss brought by the simple base network. We evaluate EFCN on the challenging KITTI [2] dataset and compare it with the state-of-the-art methods. The results show that EFCN keeps a good balance between speed and accuracy, it has \(25{\times }\) fewer parameters and is up to \(31{\times }\) faster than Faster-RCNN [3] while maintaining similar or better accuracy.