Object Detection Method Based on Improved YOLO Lightweight Network

Chengyue Li; Jianmin Yao; Zhixian Lin; Qun Yan; Baoqing Fan

doi:10.3788/LOP57.141003

Laser & Optoelectronics Progress, Volume. 57, Issue 14, 141003(2020)

Object Detection Method Based on Improved YOLO Lightweight Network

Chengyue Li^1,2, Jianmin Yao^1,2,3、*, Zhixian Lin^1,2, Qun Yan^1,2, and Baoqing Fan^1,2

¹Flat Panel Display National and Local Joint Engineering Laboratory, National University Science Park Sunshine Technology Building, Fuzhou University, Fuzhou, Fujian 350116, China

²College of Physics and Information Engineering, Fuzhou University, Fuzhou, Fujian 350116, China

³Jinjiang Bosen Electronic Technology Co., Ltd., Quanzhou, Fujian 362200, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(16)

Fig. 1. YOLOv3 network structure

Download full size

Fig. 2. Structural unit of YOLOv3. (a) Convolutional unit; (b) ResNet unit; (c) Convolutional Set unit

Download full size

Fig. 3. Improved backbone network

Download full size

Fig. 4. Improved dense network module

Download full size

Fig. 5. Improved spatial pyramid pooling network module

Download full size

Fig. 6. DS-YOLO network structure. (a) Network structure; (b) DC-SPP unit; (c) Conv-Residual unit

Download full size

Fig. 7. YOLOv3tiny test results

Download full size

Fig. 8. DS-YOLO test results

Download full size

Fig. 9. YOLOv3 test results

Download full size

Table 1. Comparison of Base-YOLO and YOLOv3
View table
Table 1. Comparison of Base-YOLO and YOLOv3
Method Weight /MB BFLOPS mAP /% Speed /(frame/s)
Base-YOLO 17.2 7.8 65.9 150
YOLOv3 236 65.86 78.3 30

Table 2. Comparison of D-YOLO and Base-YOLO
View table
Table 2. Comparison of D-YOLO and Base-YOLO
Method Weight /MB BFLOPS mAP /% Speed /(frame/s)
Base-YOLO 17.2 7.8 65.9 150
D-YOLO 24.6 8.54 67.7 143

Table 3. Comparison of S-YOLO and Base-YOLO
View table
Table 3. Comparison of S-YOLO and Base-YOLO
Method Weight /MB BFLOPS mAP /% Speed /(frame/s)
Base-YOLO 17.2 7.8 65.9 150
S-YOLO 17.5 7.92 67.1 147

Table 4. Comparison of DS-YOLO and YOLO%

View table

Table 4. Comparison of DS-YOLO and YOLO%

Method	AP																																			mAP
Method	Aero	Bike	Bird	Boat	Bottle	Bus		Car		Cat		Chair		Cow		Table		Dog		Horse		Mbike		Person		Plant		Sheep		Sofa		Train		Tv		mAP
YOLO-v3tiny	65.3	70	43.8	47	24.9		68.9		74.7		65.7		33.4		53.7		49		61		75.3		72.1		69.1		26.9		59		50.9		75		60.8		57.3
DS-YOLO	78.3	78.9	60.6	62.8	51		76.3		85.5		76.7		49.4		70.8		66.1		71.3		80		79.9		80.9		36.9		66.8		66.2		81.7		68		69.4
YOLO-v3	84.5	85	77.2	68.8	65.4		85.2		86.3		86.3		62.3		79.9		74.8		85.7		87.4		86.2		81.1		50.8		80.2		77.4		82.7		75.6		78.1

Table 5. Comparison of DS-YOLO and others algorithms in VOC2007, 2012

View table

Table 5. Comparison of DS-YOLO and others algorithms in VOC2007, 2012

Method (size)	Year	Base network	mAP /%	Speed /(frame/s)
Faster RCNN	2015	VGG16	73.2	7
SSD(300)SSD(300)SSDLite(300)DSSD(321)STDN(300)	20162017201720172018	VGG16MobileNetv2MobileNetResNet-101DenseNet-169	74.377.472.778.678.1	4650569.541.5
YOLOv2(416)YOLOv3tiny(416)YOLOv3(416)	201720182018	Darknet19-Darknet53	76.857.178.3	6716830
DS-YOLO	2019	-	69.4	141

Table 6. Comparison of DS-YOLO and YOLO
View table
Table 6. Comparison of DS-YOLO and YOLO
Method Weight /MB BFLOPS
YOLOv3tinyYOLOv3 34236 5.5765.86
DS-YOLO 25 8.58

Table 7. Comparison of DS-YOLO and YOLO、SSD in COCO
View table
Table 7. Comparison of DS-YOLO and YOLO、SSD in COCO
Method AP, IoU AP, Area
0.5∶0.95 0.5 0.75 S M L
YOLOv3tinySSD 14.423.2 33.141.2 16.323.4 3.25.3 18.523.2 30.239.6
DS-YOLOYOLOv3 20.431.1 40.355.3 18.135.2 4.814.2 21.334.1 34.746.4

Tools

Get Citation

Copy Citation Text

Chengyue Li, Jianmin Yao, Zhixian Lin, Qun Yan, Baoqing Fan. Object Detection Method Based on Improved YOLO Lightweight Network[J]. Laser & Optoelectronics Progress, 2020, 57(14): 141003

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites