期刊
SUSTAINABILITY
卷 14, 期 13, 页码 -出版社
MDPI
DOI: 10.3390/su14137912
关键词
intelligent traffic; vehicle recognition; deep learning; drone video; morphological detection
资金
- Scientific Research Project of Traffic System & Safety in Mountain Cities [2018TSSMC05]
- two Chongqing Research Program of Basic Research and Frontier Technology Innovation [cstc2017jcyjAX0473, cstc2018jscxmsybX0295]
This study proposed a method combining morphological detection and deep convolutional networks for locating and identifying vehicle models from UAV videos. The improved AlexNet* model achieved superior performance in vehicle recognition, demonstrating effective identification of UAV video targets.
For accurate and effective automatic vehicle identification, morphological detection and deep convolutional networks were combined to propose a method for locating and identifying vehicle models from unmanned aerial vehicle (UAV) videos. First, the region of interest of the video frame image was sketched and grey-scale processing was performed; sub-pixel-level skeleton images were generated based on the Canny edge detection results of the region of interest; then, the image skeletons were decomposed and reconstructed. Second, a combination of morphological operations and connected domain morphological features were applied for vehicle target recognition, and a deep learning image benchmark library containing 244,520 UAV video vehicle samples was constructed. Third, we improved the AlexNet model by adding convolutional layers, pooling layers, and adjusting network parameters, which we named AlexNet*. Finally, a vehicle recognition method was established based on a candidate target extraction algorithm with AlexNet*. The validation analysis revealed that AlexNet* achieved a mean F-1 of 85.51% for image classification, outperforming AlexNet (82.54%), LeNet (63.88%), CaffeNet (46.64%), VGG16 (16.67%), and GoogLeNet (14.38%). The mean values of P-cor, P-re, and P-miss for cars and buses reached 94.63%, 6.87%, and 4.40%, respectively, proving that this method can effectively identify UAV video targets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据