Research on Detection Algorithm of Foreign Object Debris and Small Targets in Airport Runway Based on SSD
Authors:
Open Access
- 28 January 2021
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Abstract
The SSD algorithm is currently a widely used target detection algorithm. In view of the small size of common foreign objects on airport runways and the low accuracy of SSD processing small target objects, this paper applies feature fusion method in SSD model to construct a new small target object detection algorithm model. The accuracy of the model is detected on the self-built airport runway foreign body data set, and the detection result mAP is 5% higher than the original SSD network.Keywords
This publication has 2 references indexed in Scilit:
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014