现场可编程门阵列
计算机科学
卷积神经网络
目标检测
嵌入式系统
方案(数学)
GSM演进的增强数据速率
实时计算
人工神经网络
功率消耗
人工智能
功率(物理)
计算机硬件
模式识别(心理学)
物理
数学分析
量子力学
数学
作者
Junyu Tang,Xin Zheng,Qiang Wu,Jinling Cui
标识
DOI:10.1145/3532213.3532284
摘要
This paper proposes Target detection system design and FPGA implementation based on YOLOX algorithm, in order to realize offline real-time image detection in a UAV platform with limited resources and power consumption. First, this paper studied the algorithm of YOLOX convolutional neural network,image fusion mechanism is added to this network, designed and trained the neural network. Secondly, an embedded edge computing system is designed to further speed up the target detection speed at the hardware level.In this paper, the above scheme is implemented at the board level. The test results show that the average recognition speed is 50frame/s on the system, which basically achieves the design goal of real-time detection.
科研通智能强力驱动
Strongly Powered by AbleSci AI