Abstract：A large number of proposed monocular depth estimation network research has a huge and bloated network structure,which will have the problems of large occupation and high delay in the actual deployment.In order to solve the problems,a lightweight depth estimation network based on learned step quantization strategy is proposed in this paper.The network adopts the structure of feature pyramid network(FPN)to extract the feature information of different scales.Combined with memory optimization,depthwise separable convolution is used in the feature extraction part of the network,so that the total amount of network parameters relative to ResNet is reduced by 1/3.At the same time,the skip connection transfer parameters in network computing is reduced by 68.61% compared with ResNet due the fine designed decoder.In this paper,the lightweight depth estimation network parameter bit width is reduced from 32bits to 3 bits.The experimental results show that the network parameter size of the lightweight depth estimation network is reduced by 90.59%,and the absolute relative error on the KITTI data set is 16.0%.Finally,the lightweight network size is reduced from 34.12MB to 3.21MB.
胡坤,陈迟晓,李伟,甘中学. 深度估计网络的可学习步长轻量化研究[J]. 小型微型计算机系统, 2022, 43(1): 50-55.
HU Kun,CHEN Chi-xiao,LI Wei,GAN Zhong-xue. Research of Learned Step Quantization Based Lightweight Depth Prediction Network. Journal of Chinese Computer Systems, 2022, 43(1): 50-55.
2022, Vol. 43 
