作者
Mason Liu, Menglong Zhu
发表日期
2018
研讨会论文
Proceedings of the IEEE conference on computer vision and pattern recognition
页码范围
5686-5695
简介
This paper introduces an online model for object detection in videos with real-time performance on mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short term memory (LSTM) layers to create an interweaved recurrent-convolutional architecture. Additionally, we propose an efficient Bottleneck-LSTM layer that significantly reduces computational cost compared to regular LSTMs. Our network achieves temporal awareness by using Bottleneck-LSTMs to refine and propagate feature maps across frames. This approach is substantially faster than existing detection methods in video, outperforming the fastest single-frame models in model size and computational cost while attaining accuracy comparable to much more expensive single-frame models on the Imagenet VID 2015 dataset. Our model reaches a real-time inference speed of up to 15 FPS on a mobile CPU.
学术搜索中的文章
M Liu, M Zhu - Proceedings of the IEEE conference on computer …, 2018