论文标题
实时HOG+SVM基于SOC FPGA用于UHD视频流的对象检测
Real-time HOG+SVM based object detection using SoC FPGA for a UHD video stream
论文作者
论文摘要
对象检测是许多视觉系统的重要组成部分。例如，行人检测用于高级驾驶员辅助系统（ADA）和高级视频监视系统（AVSS）。当前，大多数检测器都使用深卷积神经网络（例如，Yolo-您只看一次 - 家庭），但是由于其高计算复杂性，它无法实时处理非常高分辨率的视频流，尤其是在有限的能源预算中。在本文中，我们介绍了著名的行人探测器的硬件实现，该探测器（定向梯度的直方图）特征提取和SVM（支持向量机）分类。我们在AMD Xilinx Zynq Ultrascale+ MPSOC（芯片上的多处理器系统）上运行的系统允许4K分辨率的实时处理（UHD- Ultra高清，3840 x 2160像素）视频，每秒60帧。该系统能够单个尺度检测行人。获得的结果证实了可重编程设备在嵌入式视觉系统的实时实现中的高适合性。
Object detection is an essential component of many vision systems. For example, pedestrian detection is used in advanced driver assistance systems (ADAS) and advanced video surveillance systems (AVSS). Currently, most detectors use deep convolutional neural networks (e.g., the YOLO -- You Only Look Once -- family), which, however, due to their high computational complexity, are not able to process a very high-resolution video stream in real-time, especially within a limited energy budget. In this paper we present a hardware implementation of the well-known pedestrian detector with HOG (Histogram of Oriented Gradients) feature extraction and SVM (Support Vector Machine) classification. Our system running on AMD Xilinx Zynq UltraScale+ MPSoC (Multiprocessor System on Chip) device allows real-time processing of 4K resolution (UHD -- Ultra High Definition, 3840 x 2160 pixels) video for 60 frames per second. The system is capable of detecting a pedestrian in a single scale. The results obtained confirm the high suitability of reprogrammable devices in the real-time implementation of embedded vision systems.
