Document detail
ID

oai:arXiv.org:2310.10166

Topic
Computer Science - Computer Vision... Computer Science - Machine Learnin...
Author
Xue, Lihui Wang, Zhihao Wang, Xueqian Li, Gang
Category

Computer Science

Year

2023

listing date

10/18/2023

Keywords
large-scale bi-temporal existing computer lpcdnet image detection methods patch pixel-level change pairs cd
Metrics

Abstract

Existing satellite remote sensing change detection (CD) methods often crop original large-scale bi-temporal image pairs into small patch pairs and then use pixel-level CD methods to fairly process all the patch pairs.

However, due to the sparsity of change in large-scale satellite remote sensing images, existing pixel-level CD methods suffer from a waste of computational cost and memory resources on lots of unchanged areas, which reduces the processing efficiency of on-board platform with extremely limited computation and memory resources.

To address this issue, we propose a lightweight patch-level CD network (LPCDNet) to rapidly remove lots of unchanged patch pairs in large-scale bi-temporal image pairs.

This is helpful to accelerate the subsequent pixel-level CD processing stage and reduce its memory costs.

In our LPCDNet, a sensitivity-guided channel pruning method is proposed to remove unimportant channels and construct the lightweight backbone network on basis of ResNet18 network.

Then, the multi-layer feature compression (MLFC) module is designed to compress and fuse the multi-level feature information of bi-temporal image patch.

The output of MLFC module is fed into the fully-connected decision network to generate the predicted binary label.

Finally, a weighted cross-entropy loss is utilized in the training process of network to tackle the change/unchange class imbalance problem.

Experiments on two CD datasets demonstrate that our LPCDNet achieves more than 1000 frames per second on an edge computation platform, i.e., NVIDIA Jetson AGX Orin, which is more than 3 times that of the existing methods without noticeable CD performance loss.

In addition, our method reduces more than 60% memory costs of the subsequent pixel-level CD processing stage.

Xue, Lihui,Wang, Zhihao,Wang, Xueqian,Li, Gang, 2023, The Road to On-board Change Detection: A Lightweight Patch-Level Change Detection Network via Exploring the Potential of Pruning and Pooling

Document

Open

Share

Source

Articles recommended by ES/IODE AI

Endothelial dysfunction in breast cancer survivors on aromatase inhibitors: changes over time
cardiotoxicity breast cancer aromatase inhibitors endothelial function postmenopausal changes er+ endopat® cv cardiovascular performed using aromatase ai ais cancer women vascular breast