无人机
块(置换群论)
计算机科学
目标检测
人工智能
深度学习
编码(集合论)
卷积(计算机科学)
计算机视觉
骨干网
图像(数学)
实时计算
模式识别(心理学)
人工神经网络
电信
遗传学
几何学
数学
集合(抽象数据类型)
生物
程序设计语言
作者
Shuxiao Cheng,Yishuang Zhu,Shaohua Wu
标识
DOI:10.1016/j.oceaneng.2023.115440
摘要
The use of drones to observe ships is an effective means of maritime surveillance. However, the object scale from drone-captured images changes dramatically, presenting a significant challenge for ship detection. Additionally, the limited computing resources on drones make it difficult to achieve fast detection speed. To address these issues, we propose an efficient deep learning based network, namely the YOLOv5-ODConvNeXt, for ship detection from drone-captured images. YOLOv5-ODConvNeXt is a more accurate and faster network designed to improve the efficiency of maritime surveillance. Based on YOLOv5, we implement Omni-dimensional Convolution (ODConv) in the YOLOv5 backbone to boost the accuracy without increasing the network width and depth. We also replace the original C3 block with a ConvNeXt block in YOLOv5 backbone to accelerate detection speed with only a slight decline in accuracy. We test our model on a self-constructed ship detection dataset containing 3200 images captured by drones or with a drone view. The experimental results show that our model achieves 48.0% AP, exceeding the accuracy of YOLOv5s by 1.2% AP. The detection speed of our network is 8.3 ms per image on an NVIDIA RTX3090 GPU, exceeding the detection speed of YOLOv5s by 13.3%. Our code is available at https://github.com/chengshuxiao/YOLOv5-ODConvNeXt.
科研通智能强力驱动
Strongly Powered by AbleSci AI