激光与光电子学进展, 2019, 56 (19): 191003, 网络出版: 2019-10-12
基于YOLO v3的机场场面飞机检测方法 下载: 1829次
Airport Scene Aircraft Detection Method Based on YOLO v3
图 & 表
图 2. 空洞卷积。(a) rrate=1;(b) rrate=2;(c) rrate=3
Fig. 2. Dilated convolutions. (a) rrate=1; (b) rrate=2; (c) rrate=3
图 3. 改进后YOLO v3的骨干网络及FPN结构
Fig. 3. Backbone network and FPN architecture of the improved YOLO v3
图 4. 空洞卷积残差结构。(a)空洞卷积瓶颈层;(b)带1×1卷积结构的空洞卷积瓶颈层
Fig. 4. Structure of dilated convolution residuals. (a) Dilated convolution bottleneck; (b) dilated convolution bottleneck with 1×1 Conv projection
图 8. 不同方法检测多尺度小目标的结果
Fig. 8. Detecting results of multi-scale small targets by different methods
图 9. 不同遮挡程度的飞机检测对比实验。(a)(b)遮挡比例接近于20%;(c)(d)遮挡比例接近于60%;(e)(f)有明显颜色特征、遮挡比例接近于60%;(g)(h)遮挡比例接近于80%
Fig. 9. Contrast experiments of aircraft detection with different occlusion proportions. (a)(b) Occlusion is close to 20%; (c)(d) occlusion is close to 60%; (e)(f) obvious color characteristics, occlusion is close to 60%; (g)(h) occlusion is close to 80%
表 2不同遮挡比例的检测性能对比
Table2. Detection performance comparison of different overlapped proportions
|
表 3多种检测方法性能对比
Table3. Performance comparison of various detection methods
|
郭进祥, 刘立波, 徐峰, 郑斌. 基于YOLO v3的机场场面飞机检测方法[J]. 激光与光电子学进展, 2019, 56(19): 191003. Jinxiang Guo, Libo Liu, Feng Xu, Bin Zheng. Airport Scene Aircraft Detection Method Based on YOLO v3[J]. Laser & Optoelectronics Progress, 2019, 56(19): 191003.