| 基于卷积神经网络的实时车辆检测 |
| |
| 引用本文： | 金旺,易国洪,洪汉玉,陈思媛. 基于卷积神经网络的实时车辆检测[J]. 计算机工程与应用, 2021, 57(5): 222-228. DOI: 10.3778/j.issn.1002-8331.2005-0328 |
| |
| 作者姓名： | 金旺 易国洪 洪汉玉 陈思媛 |
| |
| 作者单位： | 1.武汉工程大学 计算机科学与工程学院，武汉 4302052.武汉工程大学 智能机器人湖北省重点实验室，武汉 4302053.武汉工程大学 图像处理与智能控制实验室，武汉 430205 |
| |
| 基金项目： | 国家自然科学基金面上项目 |
| |
| 摘 要： | 为了解决对于尺度变换较大车辆及遮挡车辆检测性能不足的问题,提出了一种实时车辆检测模型.针对车辆检测算法对于尺度敏感的问题,通过使用深度残差网络作为特征提取层,构建特征金字塔网络用于多尺度检测;利用软化非极大抑制线性衰减置信得分解决车辆遮挡问题,从而降低车辆的漏检率;同时对模型进行通道级裁剪缩减模型参数规模,节省计算资源...
|
| 关 键 词： | 车辆检测 卷积神经网络 残差学习 特征金字塔 网络裁剪 |
Real-Time Vehicle Detection Based on Convolutional Neural Network |
| |
| JIN Wang,YI Guohong,HONG Hanyu,CHEN Siyuan. Real-Time Vehicle Detection Based on Convolutional Neural Network[J]. Computer Engineering and Applications, 2021, 57(5): 222-228. DOI: 10.3778/j.issn.1002-8331.2005-0328 |
| |
| Authors: | JIN Wang YI Guohong HONG Hanyu CHEN Siyuan |
| |
| Affiliation: | 1.School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan 430205, China 2.Hubei Provincial Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan 430205, China3.Laboratory of Image Processing and Intelligent Control, Wuhan Institute of Technology, Wuhan 430205, China |
| |
| Abstract: | In order to solve the problem of insufficient detection performance for vehicles with large scale transformation and overlapping, this paper proposes a single-stage deep convolutional neural network for real-time vehicle detection. For the scale-sensitive problems of vehicle detection algorithms, the deep residual network is used as the feature extraction layer to obtain fine-grained features, and the feature pyramid network is constructed for multi-scale detection; the soft non-maximum suppression is used to linearly attenuate the confidence score to solve the problem of vehicle overlapping so that the vehicle’s missed detection rate can be reduced. At the same time, it pruns the model at channel level to reduce the size of model parameters, saves computing resources and improves the speed of model detection. Experiments on VOC dataset show that the proposed method has high performance in both detection accuracy and detection speed. In terms of detection accuracy, it reaches 87.6%, which is 3.7 percentage points higher than that of YOLOv3, and 9.8 percentage points higher than that of SSD512. In terms of detection speed, the number of detection frames per second reaches 42 f/s, realizing real-time detection of vehicles. In particular, applying the model to the Apollo dataset with complex environment, it has better robustness than YOLOv3. |
| |
| Keywords: | vehicle detection convolutional neural network residual network feature pyramid network network pruning |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
|
