| InGaAs近红外人脸图像检测超轻量算法研究 |
| |
| 引用本文： | 苏晏园,范广宇,龚海梅,李雪,陈永平.InGaAs近红外人脸图像检测超轻量算法研究[J].红外与激光工程,2022,51(10):20220078-1-20220078-10. |
| |
| 作者姓名： | 苏晏园 范广宇 龚海梅 李雪 陈永平 |
| |
| 作者单位： | 1.中国科学院上海技术物理研究所 传感技术国家重点实验室，上海 200083 |
| |
| 摘 要： | InGaAs近红外探测器广泛应用于航天航空、军事与民生领域。为了实现InGaAs探测器智能化，结合人脸检测应用，提出了可部署于低功耗移动智能设备的超轻量InGaAs近红外人脸检测算法。主要针对近红外人脸样本较少与低功耗设备部署问题展开研究，采用迁移学习与二值量化方案训练网络。算法首先通过大规模可见光人脸数据集实现了基于SSD的预训练人脸检测网络。然后使用二值量化方案大幅压缩网络参数空间大小与计算量，但同时造成网络准确度下降。为进一步提升网络二值量化效果，为二值量化过程引入了特征均值信息，并以对抗卷积形式弥补了准确度损失。最后，算法通过小规模近红外人脸数据对预训练二值网络进行微调，实现最终网络。所实现的二值量化人脸检测网络在采集的近红外人脸验证集中可以获得71.18%平均准确度。
|
| 关 键 词： | 二值化 近红外人脸检测 SSD 网络压缩 InGaAs探测器 |
| 收稿时间： | 2022-01-29 |
Research of ultra-light InGaAs NIR face detection algorithm |
| |
| Affiliation: | 1.State Key Laboratories of Transducer Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China2.Key Laboratory of Infrared Imaging Materials and Detectors, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China3.ShanghaiTech University, Shanghai 201210, China |
| |
| Abstract: | InGaAs NIR detectors are widely used in aerospace, military and civilian fields. In order to realize the intelligence of InGaAs detectors, combined with face detection applications, an ultra-lightweight InGaAs NIR face detection algorithm that can be deployed in low-power mobile smart devices is proposed. This paper mainly studies the problems of few NIR face samples and low-power device deployment, and uses transfer learning and binary quantization to train the network. The algorithm first realizes a pre-trained face detection network based on SSD through a large-scale visible light face dataset. Then, the binary quantization scheme is used to greatly compress the network parameter space size and calculation amount, but the network accuracy is reduced at the same time. In order to further improve the effect of network binary quantization, this paper introduces feature mean information for the binary quantization process and makes up for the loss of accuracy in the form of adversarial convolution. Finally, the algorithm fine-tunes the pre-trained binary network through small-scale NIR face data to achieve the final network. The binarization face detection network implemented in this paper can achieve an average accuracy of 71.18% in the collected NIR face verification set. |
| |
| Keywords: | |
|
| 点击此处可从《红外与激光工程》浏览原始摘要信息 |
|
点击此处可从《红外与激光工程》下载全文 |
|
