Loading...
Please wait, while we are loading the content...
Similar Documents
Fast and Accurate Object Detection in Remote Sensing Images Based on Lightweight Deep Neural Network
| Content Provider | MDPI |
|---|---|
| Author | Lang, Lei Xu, Ke Zhang, Qian Wang, Dong |
| Copyright Year | 2021 |
| Description | Deep learning-based object detection in remote sensing images is an important yet challenging task due to a series of difficulties, such as complex geometry scene, dense target quantity, and large variant in object distributions and scales. Moreover, algorithm designers also have to make a trade-off between model’s complexity and accuracy to meet the real-world deployment requirements. To deal with these challenges, we proposed a lightweight YOLO-like object detector with the ability to detect objects in remote sensing images with high speed and high accuracy. The detector is constructed with efficient channel attention layers to improve the channel information sensitivity. Differential evolution was also developed to automatically find the optimal anchor configurations to address issue of large variant in object scales. Comprehensive experiment results show that the proposed network outperforms state-of-the-art lightweight models by 5.13% and 3.58% in accuracy on the RSOD and DIOR dataset, respectively. The deployed model on an NVIDIA Jetson Xavier NX embedded board can achieve a detection speed of 58 FPS with less than 10W power consumption, which makes the proposed detector very suitable for low-cost low-power remote sensing application scenarios. |
| Starting Page | 5460 |
| e-ISSN | 14248220 |
| DOI | 10.3390/s21165460 |
| Journal | Sensors |
| Issue Number | 16 |
| Volume Number | 21 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2021-08-13 |
| Access Restriction | Open |
| Subject Keyword | Sensors Remote Sensing Remote Sensing Image Object Detection Anchor Configurations Differential Evolution Yolo Attention Module |
| Content Type | Text |
| Resource Type | Article |
