Infrared Vehicle Detection Algorithm Based on Improved Shuffle-RetinaNet

Xiaochang Fan; Yu Liang; Wei Zhang

doi:10.3788/LOP230713

Journals >Laser & Optoelectronics Progress >Volume 60 >Issue 24 >Page 2410006 > Article

Laser & Optoelectronics Progress
Vol. 60, Issue 24, 2410006 (2023)

Infrared Vehicle Detection Algorithm Based on Improved Shuffle-RetinaNet

Xiaochang Fan, Yu Liang, and Wei Zhang^*

Author Affiliations

School of Microelectronics, Tianjin University, Tianjin 300072

show less

DOI: 10.3788/LOP230713 Cite this Article Set citation alerts

Xiaochang Fan, Yu Liang, Wei Zhang. Infrared Vehicle Detection Algorithm Based on Improved Shuffle-RetinaNet[J]. Laser & Optoelectronics Progress, 2023, 60(24): 2410006 Copy Citation Text

show less

Fig. 1. Overall architecture of infrared vehicle detection algorithm based on improved Shuffle-RetinaNet

Download full size

Fig. 2. Structure of DBAM

Download full size

Fig. 3. Different feature network design. (a) Conventional FPN; (b) PANet; (c) our network design

Download full size

Fig. 4. Inconsistency of classification and regression

Download full size

Fig. 5. Partial infrared vehicle images in the dataset

Download full size

Fig. 6. Comparison of detection results before and after introducing calibration factor. (a) Before improvement; (b) after improvement

Download full size

Fig. 7. Comparison of detection effect of Shuffle-RetinaNet before and after improvement. (a) Before improvement; (b) after improvement

Download full size

Platform and tools	Version
Operating system	Ubuntu 16.0.7
Graphic processing unit	NVIDIA Quadro RTX 8000
Graphics driver	510.47.03
Programing language	Python 3.7
Framework	PyTorch 1.7.1

Table 1. Experimental platform configuration

Backbone	Number of parameters /10⁶	FLOPs /10⁹	Speed /（frame·s^-1）	$A P_{50}$ /%
ResNet50	36.10	65.35	14.2	87.4
ShuffleNetV1 1.0×（g=3）	11.91	27.32	29.8	84.9
ShuffleNetV2 1.0×（g=3）	11.15	24.09	32.4	86.9
MobileNetV2	14.01	26.97	28.4	85.1
MobileNetV3	14.98	24.03	30.3	86.1

Table 2. Comparison of lightweight backbones

Method	DBAM	Improved feature network	Calibration factor	$A P_{50}$ /%	Number of parameters /10⁶	FLOPs /10⁹	Speed /（frame $∙ s^{- 1}$ ）
RetinaNet				87.4	36.10	65.35	14.2
Shuffle-RetinaNet				86.9	11.15	24.09	32.4
Ours	√			89.1	11.44	24.21	31.7
	√	√		91.1	11.74	24.35	31.1
	√	√	√	92.9	11.74	24.35	30.9

Table 3. Overall ablation experimental results

Method	DBAM	Improved feature network	Calibration factor	$A P_{s}$ /%	$A P_{m}$ /%	$A P_{l}$ /%
RetinaNet				45.2	59.5	66.5
Shuffle-RetinaNet				42.9	55.7	64.7
Ours	√			43.1	55.9	65.3
	√	√		44.9	58.4	65.9
	√	√	√	45.7	59.9	66.7

Table 4. Ablation study results of multi-scale detection accuracy

Parameter value of calibration factor	AP /%	AP₅₀ /%
$α$ =0.5， $β$ =6	56.2	91.0
$α$ =0.5， $β$ =8	56.2	91.1
$α$ =0.5， $β$ =10	56.1	91.0
$α$ =1.0， $β$ =6	56.9	92.4
$α$ =1.0， $β$ =8	57.4	92.9
$α$ =1.0， $β$ =10	57.4	92.5
$α$ =1.5， $β$ =6	56.3	91.4
$α$ =1.5， $β$ =8	57.1	92.0
$α$ =1.5， $β$ =10	56.8	91.8

Table 5. Results of calibration factor comparison

Parameter value of calibration factor	Self-built dataset	FLIR ADAS
Parameter value of calibration factor	AP₅₀ /%	AP₅₀ /%
No calibration factor	86.9	87.6
$α$ =0.5， $β$ =6	87.1	87.9
$α$ =0.5， $β$ =8	87.2	87.8
$α$ =0.5， $β$ =10	87.1	87.9
$α$ =1.0， $β$ =6	88.9	89.5
$α$ =1.0， $β$ =8	89.1	89.7
$α$ =1.0， $β$ =10	89.0	89.5
$α$ =1.5， $β$ =6	88.6	89.1
$α$ =1.5， $β$ =8	88.7	89.2
$α$ =1.5， $β$ =10	88.4	89.0

Table 6. Results of calibration factor comparison on Shuffle-RetinaNet

Method	AP₅₀ /%	Number of parameters /10⁶	FLOPs /10⁹	Speed /（frame $∙ s^{- 1}$ ）
Faster RCNN	88.6	41.12	67.75	12.4
RetinaNet	87.4	36.10	65.35	14.2
YOLOv5s	88.3	7.21	26.67	31.6
SSD512	86.2	36.04	60.85	18.1
Ours	92.9	11.74	24.35	30.9

Table 7. Comparision with classical object detection algorithms

Method	AP/%	Number of parameters /10⁶
Algorithms 1^［20］	76.57	20.60
Algorithms 2^［6］	85.00	70.53
Algorithms 3^［21］	91.30	—
Algorithms 4^［22］	90.50	8.10
Ours	91.70	11.74

Table 8. Comparision with classical infrared vehicle detection algorithms

Xiaochang Fan, Yu Liang, Wei Zhang. Infrared Vehicle Detection Algorithm Based on Improved Shuffle-RetinaNet[J]. Laser & Optoelectronics Progress, 2023, 60(24): 2410006

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information

微信扫一扫：分享

微信扫一扫：分享