A Light-Weight Object Detection Framework with FPA Module for Optical Remote Sensing Imagery

by   Xi Gu, et al.

With the development of remote sensing technology, the acquisition of remote sensing images is easier and easier, which provides sufficient data resources for the task of detecting remote sensing objects. However, how to detect objects quickly and accurately from many complex optical remote sensing images is a challenging hot issue. In this paper, we propose an efficient anchor free object detector, CenterFPANet. To pursue speed, we use a lightweight backbone and introduce the asymmetric revolution block. To improve the accuracy, we designed the FPA module, which links the feature maps of different levels, and introduces the attention mechanism to dynamically adjust the weights of each level of feature maps, which solves the problem of detection difficulty caused by large size range of remote sensing objects. This strategy can improve the accuracy of remote sensing image object detection without reducing the detection speed. On the DOTA dataset, CenterFPANet mAP is 64.00 22.2, which is close to the accuracy of the anchor-based methods currently used and much faster than them. Compared with Faster RCNN, mAP is 6.76 60.87 accuracy in large-scale optical remote sensing object detection.



page 8


R^2-CNN: Fast Tiny Object Detection in Large-scale Remote Sensing Images

Recently, convolutional neural network has brought impressive improvemen...

Feature Fusion Detector for Semantic Cognition of Remote Sensing

The value of remote sensing images is of vital importance in many areas ...

Fusion Detection via Distance-Decay IoU and weighted Dempster-Shafer Evidence Theory

In recent years, increasing attentions are paid on object detection in r...

Tackling the Background Bias in Sparse Object Detection via Cropped Windows

Object detection on Unmanned Aerial Vehicles (UAVs) is still a challengi...

CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery

Accurate and robust detection of multi-class objects in optical remote s...

Counting dense objects in remote sensing images

Estimating accurate number of interested objects from a given image is a...

Deep Adaptive Proposal Network for Object Detection in Optical Remote Sensing Images

Object detection is a fundamental and challenging problem in aerial and ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.