Dynamic Receptive Field-Based Object Detection in Aerial Imaging

Fig. 9. Statistical of the VISDrone-g. (a) Object scale distribution characteristics; (b) object frame length and width proportional distribution characteristics

Download full size

Fig. 10. Detailed explanation of COCO object detection and evaluation indexes^[26]

Download full size

Fig. 11. Visual contrast between DRF-RetinaNet and RetinaNet^*. (a)(c)(e) DRF-RetinaNet's detection result; (b)(d)(f) RetinaNet's detection result

Download full size

Fig. 12. Detection results of dim light

Download full size

Fig. 13. Detection results of dense objects

Download full size

Fig. 14. Detection results of oblique view

Download full size

Fig. 15. Detection results of down view

Download full size

Table 1. Focal Loss parameter tuning
View table
Table 1. Focal Loss parameter tuning
α_t γ AP /% AP₅₀ /% F_1-score
0.20 2.0 23.93 38.18 47.24
0.25 2.0 24.37 39.95 48.43
0.25 3.0 25.14 42.62 52.47
0.30 3.0 24.82 41.23 50.72

Table 2. Performance comparison of model components

View table

Table 2. Performance comparison of model components

Module	Whether or not it contains
RetinaNet^*	√
SE-ResNeXt		√	√	√	√	√
Bottom-up			√		√	√
GCU				√	√	√
DRF detection subnet						√
AP /%	18.97	20.22	21.33	22.05	23.17	25.14
AP₅₀ /%	28.65	30.64	32.78	34.33	37.83	42.62
Note:*indicates that anchor parameters have been adjusted according to section 4.2.

Table 3. Performance comparison of each algorithm

View table

Table 3. Performance comparison of each algorithm

Method	Input size	Basebone Network	AP /%	AP₅₀ /%	AP₇₅ /%	AR₁ /%	AR₁₀ /%	AR₁₀₀ /%	Time /ms
Faster R-CNN	600	Resnet-50	16.72	24.32	14.15	4.21	12.47	16.65	137
R-FCN	600	Resnet-101	19.35	30.18	19.52	5.65	18.73	22.56	178
SSD	512	Vgg-16	12.23	17.29	11.54	3.71	11.22	15.41	54
RFB-Net	512	Resnet-50	14.87	22.17	12.06	4.34	13.15	17.38	75
YOLO v3	416	Darknet-53	14.75	21.86	12.17	4.12	12.93	17.41	67
RetinaNet	608	Resnet-50	16.35	23.18	13.92	4.85	14.75	18.36	85
RetinaNet^*	608	Resnet-50	18.97	28.65	17.42	4.92	17.25	20.52	88
DRF-RetinaNet	608	SE-ResNeXt-50	25.14	42.62	24.71	7.82	24.22	31.24	103
Note:*indicates that anchor parameters have been adjusted according to section 4.2.

Table 4. Performance comparison of algorithms for different scales object detection

View table

Table 4. Performance comparison of algorithms for different scales object detection

Method	AP^small /%	AP^medium /%	AP^large /%	AR^small /%	AR^medium /%	AR^large /%	F_1-score
Faster R-CNN	7.14	24.42	36.73	10.62	26.75	41.41	33.15
R-FCN	9.85	26.13	40.25	14.57	32.71	47.79	40.67
SSD	5.85	20.03	34.07	7.63	24.97	38.68	26.41
RFB-Net	6.62	22.18	34.28	9.55	25.77	40.82	33.13
YOLO v3	6.25	22.26	36.17	9.72	25.72	40.27	32.73
RetinaNet	7.27	23.95	36.72	10.31	26.63	42.23	32.69
RetinaNet^*	9.82	25.35	38.31	14.93	31.91	44.82	37.92
DRF-RetinaNet	13.62	40.34	55.95	17.42	49.97	61.53	52.47
Note:*indicates that anchor parameters have been adjusted according to section 4.2.

Tools

Get Citation

Copy Citation Text

Xueli Xie, Chuanxiang Li, Xiaogang Yang, Jianxiang Xi, Tong Chen. Dynamic Receptive Field-Based Object Detection in Aerial Imaging[J]. Acta Optica Sinica, 2020, 40(4): 0415001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites