Improved YOLOv3 Garbage Classification and Detection Model for Edge Computing Devices

Zipeng Wang; Rongfen Zhang; Yuhong Liu; Jihui Huang; Zhixu Chen

doi:10.3788/LOP202259.0415002

Journals >Laser & Optoelectronics Progress >Volume 59 >Issue 4 >Page 0415002 > Article

Laser & Optoelectronics Progress
Vol. 59, Issue 4, 0415002 (2022)

Improved YOLOv3 Garbage Classification and Detection Model for Edge Computing Devices

Zipeng Wang, Rongfen Zhang^*, Yuhong Liu, Jihui Huang, and Zhixu Chen

Author Affiliations

College of Big Data and Information Engineering, Guizhou University, Guiyang , Guizhou 550025, China

show less

DOI: 10.3788/LOP202259.0415002 Cite this Article Set citation alerts

Zipeng Wang, Rongfen Zhang, Yuhong Liu, Jihui Huang, Zhixu Chen. Improved YOLOv3 Garbage Classification and Detection Model for Edge Computing Devices[J]. Laser & Optoelectronics Progress, 2022, 59(4): 0415002 Copy Citation Text

show less

Fig. 2. Structure of spatial pyramid pooling

Download full size

Fig. 3. Improved YOLOv3 Model

Download full size

Fig. 4. Comparison of three situations

Download full size

Fig. 5. Training loss curve

Download full size

Fig. 6. Comparison of detection effects of four algorithms. (a) Improved YOLOv3; (b) YOLOv3; (c) YOLOv3-Tiny; (d) YOLOv4

Download full size

Fig. 7. Overall work flow diagram of system

Download full size

	Type	Number of filters	Size	Output
	Convolutional	32	3×3	416×416
	Convolutional	64	3×3 /2	208×208
1×	Convolutional	32	1×1
	Convolutional	64	3×3
	Residual			208×208
	Convolutional	128	3×3/2	104×104
2×	Convolutional	64	1×1
	Convolutional	128	3×3
	Residual			104×104
	Convolutional	256	3×3/2	52×52
8×	Convolutional	128	1×1
	Convolutional	256	3×3
	Residual			52×52
	Convolutional	512	3×3/2	26×26
8×	Convolutional	256	1×1
	Convolutional	512	3×3
	Residual			26×26
	Convolutional	1024	3×3/2	13×13
4×	Convolutional	512	1×1
	Convolutional	1024	3×3
	Residual			13×13
	Avgpool		Global
	Connected		1000
	Softmax

Table 1. Network structure of Darknet53

Input	Operator	Exp size	#Out	SE	NL	Step
416 $\times$ 416 $\times$ 3	Conv2d		16		HS	2
208 $\times$ 208 $\times$ 16	bneck，3 $\times$ 3	16	16		RE	1
208 $\times$ 208 $\times$ 16	bneck，3 $\times$ 3	64	24		RE	2
104 $\times$ 104 $\times$ 24	bneck，3 $\times$ 3	72	24		RE	1
104 $\times$ 104 $\times$ 24	bneck，5 $\times$ 5	72	40	0	RE	2
52 $\times$ 52 $\times$ 40	bneck，5 $\times$ 5	120	40		RE	1
52 $\times$ 52 $\times$ 40	bneck，5 $\times$ 5	120	40		RE	1
52 $\times$ 52 $\times$ 40	bneck，3 $\times$ 3	240	80		HS	2
26 $\times$ 26 $\times$ 80	bneck，3 $\times$ 3	200	80	0	HS	1
26 $\times$ 26 $\times$ 80	bneck，3 $\times$ 3	184	80		HS	1
26 $\times$ 26 $\times$ 80	bneck，3 $\times$ 3	184	80		HS	1
26 $\times$ 26 $\times$ 80	bneck，3 $\times$ 3	480	112	√	HS	1
26 $\times$ 26 $\times$ 112	bneck，3 $\times$ 3	672	112	√	HS	1
26 $\times$ 26 $\times$ 112	bneck，5 $\times$ 5	672	160	√	HS	2
13 $\times$ 13 $\times$ 160	bneck，5 $\times$ 5	960	160	√	HS	1
13 $\times$ 13 $\times$ 160	bneck，5 $\times$ 5	960	160	√	HS	1
13 $\times$ 13 $\times$ 160	Conv2d，1 $\times$ 1		960		HS	1
13 $\times$ 13 $\times$ 960	pool，7 $\times$ 7					1
1 $\times$ 1 $\times$ 960	Conv2d，1 $\times$ 1 NBN		1280		HS	1
1 $\times$ 1 $\times$ 1280	Conv2d，1 $\times$ 1 NBN		k			1

Table 2. Network structure of MobileNetv3-Large^［22］

Garbage category	Number
Cigarette case	460
Glass bottles	580
Milk box	720
Plastic bottle	810
Screw	370
Batteries	330
Cigarette end	420
Disposable paper cup	650
Packing bag	460
Pen	280
Tissue paper ball	310
Toothpick	650
Walnut shell	390
Banana peel	410
Vegetable leaf	360
Egg shell	390
Orange peel	420
Shells of Sunflower seed	410
Tea leaves	420
Cotton swab	370
Drugs	360
Lipstick	530
Mask	850

Table 3. Quantity of various garbage

Network

mAP /%

Model size /

Detection speed /(frame·s^-1)

MobileNetv3

68.8

26.1

MobileNetv3+SPP

70.9

27.6

YOLOv3

67.2

246.8

Table 4. Performance comparison of different networks

Network	mAP /%
MobileNetv3+SPP+CIOU	72.1
YOLOv3+CIOU	69.3
MobileNetv3+SPP	70.9
YOLOv3	67.2

Table 5. Comparison before and after the introduction of CIOU function

Garbage category	Improved YOLOv3	YOLOv3	YOLOv3-Tiny	YOLOv4
Cigarette case	59.58	53.85	42.01	60.9
Glass bottles	69.85	61.84	54.03	73.94
Milk box	70.06	59.84	50.18	72.22
Plastic bottle	79.98	79.91	66.86	79.97
Screw	63.95	46.27	37.42	60.19
Batteries	76.21	71.21	52.57	78.7
Cigarette end	74.63	72.44	66.32	77.55
Disposable paper cup	75.52	72.64	67.56	80.45
Packing bag	77.95	70.95	62.12	78.35
Pen	74.49	73.28	60.58	76.5
Tissue paper ball	73.2	70.1	55.01	74.24
Toothpick	76.98	74.61	64.4	77.11
Walnut shell	57.6	51.57	30.53	60.09
Banana peel	78.85	75.75	66.88	79.85
Vegetable leaf	66.14	62.68	47.49	71.8
Egg shell	71.95	71.52	56.49	72.8
Orange peel	75.35	65.25	63.28	75.87
Shells of Sunflower seed	75.51	73.88	64.5	76.61
Tea leaves	72.66	70.43	57.57	73.22
Cotton swab	65.97	64.47	63.39	68.64
Drugs	75.27	71.25	67.53	77.95
Lipstick	77.93	74.62	61.33	78.37
Mask	68.8	68.37	53.53	69.94

Table 6. Comparison of AP values of four algorithms

Network	mAP /%	Model size /MB	Detection speed /（frame·s^-1）
Improved YOLOv3	72.1	27.6	74
YOLOv3	67.2	246.8	43
YOLOv3-Tiny	56.6	34.9	77
YOLOv4	73.7	256.6	50
SSD	65.4	97.3	48
MobileNet+YOLOv3	66.8	25.3	75
MobileNetv3+YOLOv3-Tiny	55.8	11.7	82

Table 7. Comparison of overall detection performance of seven algorithms

Network	Detection speed /（frame·s^-1）	mAP /%
Improved YOLOv3	19	72.1
YOLOv3	8	67.2
YOLOv3-Tiny	20	56.6
YOLOv4	11	73.7

Table 8. Comparison of detection speed of four algorithms on NVIDIA Xavier NX

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information