基于FPGA的CNN加速器在Zynq-7020上,用于嵌入式船舶识别在无人地面车辆中
Abdelilah Haijoub1, Aissam Bekkari2, Anas Hatim3
1Engineering Sciences Laboratory, National School of Applied Sciences of Kenitra, Ibn Tofail University, Kenitra 14000, Morocco.
Sensors (Basel, Switzerland)
|March 14, 2026
概括
本研究介绍了一种硬件和软件的共同设计,用于加速无人驾驶地面车辆 (USV) 的深度学习模型. 这种方法可以实现节能,近传感器处理,用于海上应用,尽管计算限制.
科学领域:
- 机器人技术和自主系统
- 计算机视觉 计算机视觉
- 嵌入式系统工程 嵌入式系统工程
背景情况:
- 无人驾驶地面车辆 (USV) 需要强大的基于视觉的感知来进行导航和监视.
- 对于USV的机载计算面临严格的尺寸,重量和功率 (SWaP) 限制.
- 深度卷积神经网络 (CNN) 提供高识别精度,但需要大量的计算资源,挑战嵌入式部署.
研究的目的:
- 开发和评估一个硬件-软件共同设计的架构,以加快在USV的嵌入式平台上的CNN.
- 为了实现海上感知任务的节能,近传感器处理.
- 为解决在低成本嵌入式系统上部署CNN的计算和内存限制.
主要方法:
- 一个异质的ARM-FPGA系统被用于CNN加速.
- 在FPGA上实现了基于线路缓冲卷曲和AXI-Stream数据流的全流硬件架构.
- 该ARM处理系统管理轻量化配置,调度和数据移动.
主要成果:
- 拟议的共同设计策略显示了产量,资源利用和电力消耗之间的平衡权衡.
- 使用在海上船舶数据集上训练的代表性CNN模型获得实验结果.
- 该架构在Zynq-7020系统芯片上进行了评估.
结论:
- 开发的硬件和软件联合设计适合在USV中进行节能车载感知.
- 这种方法有效地解决了在严格的嵌入式约束下部署CNN的挑战.
- 这项工作为提高自主海事系统感知能力提供了实际的基础.
相关概念视频
01:30Acceleration Vectors
In everyday conversation, accelerating means speeding up. Acceleration is a vector in the same direction as the change in velocity, Δv, therefore the greater the acceleration, the greater the change in velocity over a given time. Since velocity is a vector, it can change in magnitude, direction, or both. Thus acceleration is a change in speed or direction, or both. For example, if a runner traveling at 10 km/h due east slows to a stop, reverses direction, and continues their run at 10 km/h due...
01:18Uniform Depth Channel Flow: Problem Solving
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
01:30Vector Functions and Motion: Problem Solving
Accurate position tracking is fundamental to the safe and effective operation of unmanned aerial vehicles (UAVs), particularly during precision maneuvers near complex structures. In this scenario, a drone is programmed to perform a high-precision inspection of a vertical structure, starting at position ((x, y, z) = (3, 0, 0)), with an initial velocity oriented in the positive z-direction. The trajectory of the drone is governed by a time-dependent acceleration function a(t), which is predefined...