Multi-Scale Feature Fusion Based Adaptive Object Detection for UAV

Fig. 6. Visualization detection results of the proposed algorithm in different situations. (a) Small target detection results; (b) dense target detection results;(c) detection results of target under different illuminations

Download full size

Table 1. Lightweight deep residual network model

View table

Table 1. Lightweight deep residual network model

Layer	Type	Kernel	Output size	Number of output channels
X	input		224×224	3
Conv_1	Convolution	3×3,64 stride 2	112×112	32
Conv_2	Convolution	$\begin{matrix} [\begin{matrix} 3 \times 3,1 \\ 1 \times 1,64 \\ 3 \times 3,1 \\ 1 \times 1,64 \end{matrix}] \end{matrix}$ ×3	56×56	64
Conv_3	Convolution	$\begin{matrix} [\begin{matrix} 3 \times 3,1 \\ 1 \times 1,128 \\ 3 \times 3,1 \\ 1 \times 1,128 \end{matrix}] \end{matrix}$ ×4	28×28	128
Conv_4	Convolution	$\begin{matrix} [\begin{matrix} 3 \times 3,1 \\ 1 \times 1,256 \\ 3 \times 3,1 \\ 1 \times 1,256 \end{matrix}] \end{matrix}$ ×6	14×14	256
Conv_5	Convolution	$\begin{matrix} [\begin{matrix} 3 \times 3,1 \\ 1 \times 1,512 \\ 3 \times 3,1 \\ 1 \times 1,512 \end{matrix}] \end{matrix}$ ×3	7×7	512

Table 2. Deconvolution layer parameters
View table
Table 2. Deconvolution layer parameters
Layer Type Kernel Stride Output size
h1 Deconvolution 3×3 1 14×14×256
h2 Deconvolution 3×3 1 28×28×256
h3 Deconvolution 3×3 1 56×56×256

Table 3. Feature extraction network comparison
View table
Table 3. Feature extraction network comparison
Model Size /MB Ratio /% Accuracy /%
Resnet 97.7 — 81.3
LResnet 10.2 10.4 80.6

Table 4. Effectiveness test of each module for different methods%
View table
Table 4. Effectiveness test of each module for different methods%
Method mAP AP⁵⁰ AP⁷⁵
①Faster-RCN(Resnet50+RPN) 18.63 35.87 17.86
②LResnet+RPN 18.52 35.75 17.44
③LResnet+DC+RPN 21.03 38.46 18.03
④LResnet+DC+GA-RPN(ours) 22.12 38.76 21.53

Table 5. Comparison between the results of ten categories from ours model and Faster-RCNN on VisDrone dataset%
View table
Table 5. Comparison between the results of ten categories from ours model and Faster-RCNN on VisDrone dataset%
Method Pedestrian Person Bicycle Car Van Truck Tricycle Awn Bus Motor
Faster-RCNN 18.34 7.62 6.76 43.31 27.53 19.95 10.13 7.65 36.87 8.79
Ours 22.43 7.61 8.56 50.18 34.63 24.34 14.11 9.08 36.25 14.88

Table 6. Comparison test of UAV aerial data with mainstream object detection algorithm
View table
Table 6. Comparison test of UAV aerial data with mainstream object detection algorithm
Method mAP /% AP⁵⁰ /% AP⁷⁵ /% Frame rate /(frame·s^-1)
FPN 16.51 32.20 14.91 6
YOLOv3 20.30 44.12 15.80 44
RetinaNet 11.81 21.37 11.62 11
CornerNet 17.41 34.12 15.78 13
Ours 22.12 38.76 21.53 24

Tools

Get Citation

Copy Citation Text

Fang Liu, Zhiwei Wu, Anzhe Yang, Xiao Han. Multi-Scale Feature Fusion Based Adaptive Object Detection for UAV[J]. Acta Optica Sinica, 2020, 40(10): 1015002

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites