Compact One-Stage Object Detection Network
- Resource Type
- Conference
- Authors
- Xing, Chen; Liang, Xi; Yang, Rongjie
- Source
- 2020 IEEE 8th International Conference on Computer Science and Network Technology (ICCSNT) Computer Science and Network Technology (ICCSNT), 2020 IEEE 8th International Conference on. :115-118 Nov, 2020
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
Feature extraction
Object detection
Drones
Real-time systems
Automobiles
Training
Residual neural networks
YOLO
object detection
small target
- Language
The targets in aerial images captured by drones are difficult to detect due to their small size, those neural networks with better detecting accuracy are too complicated to run real-time job on drone-mounted computer. This paper proposes a network combined residual network and YOLOv3-Tiny, residual network is used to merge different level features for improving YOLOv3-Tiny's small object detecting performance. During the experiment, the proposed network gets 2.9 higher mAP than YOLOv3-Tiny.