Intelligent Domestic Garbage Recognition Based on Faster RCNN

Canhua Wen; Jia Li; Xue Dong

doi:10.3788/LOP57.201014

Journals >Laser & Optoelectronics Progress >Volume 57 >Issue 20 >Page 201014 > Article

Laser & Optoelectronics Progress
Vol. 57, Issue 20, 201014 (2020)

Intelligent Domestic Garbage Recognition Based on Faster RCNN

Canhua Wen, Jia Li^*, and Xue Dong

Author Affiliations

China-UK Low Carbon College, Shanghai Jiao Tong University, Shanghai, 201306, China

show less

DOI: 10.3788/LOP57.201014 Cite this Article Set citation alerts

Canhua Wen, Jia Li, Xue Dong. Intelligent Domestic Garbage Recognition Based on Faster RCNN[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201014 Copy Citation Text

show less

Fig. 1. Experimental equipment

Download full size

Fig. 2. Typical image samples from each class

Download full size

Fig. 3. Network structure of Faster RCNN

Download full size

Fig. 4. Faster RCNN train process combined with hard samples enhancement and special layer fine-tuning

Download full size

Fig. 5. Total loss convergence and mAP of test dataset during training procedure

Download full size

Fig. 9. Probability threshold decision curve on MobileNet_v1

Download full size

Dataset	Metal	Plastic	Carton	Battery	Bulb	Pill	Total
Original dataset	1321	1392	807	1058	1129	1402	7109
Augmented train dataset	2429	2435	1938	2389	2398	2528	14117
Augmented test dataset	630	585	483	597	617	630	3542
Augmented dataset	3059	3020	2421	2986	3015	3158	17659

Table 1. Object quantity on garbage dataset

Network	Number ofparameters /10⁷	Number ofFLOPs /10¹⁰	Layernumbers
VGG-16	136.79	166.37	20
Res101	47.21	167.25	105
MobileNet_v1	5.61	19.02	32

Table 2. Number of parameters, FLOPs and layers for different networks

Backbonenetwork		AP						mAP	OptimizedmAP	Detection speed /(frame·s^-1)
Backbonenetwork		Metal	Plastic	Carton	Battery	Pill	Bulb	mAP	OptimizedmAP	Detection speed /(frame·s^-1)
Res101	TR	1.0	0.9996	0.9985	0.9996	0.9973	1.0	0.9992	0.9993	~7
	TE	0.9770	0.9597	0.9817	0.9695	0.9728	0.9811	0.9736	0.9857
VGG-16	TR	1.0	0.9997	0.9997	0.9996	0.9970	1.0	0.9993	0.9992	~9
	TE	0.9758	0.9639	0.9866	0.9835	0.9813	0.9853	0.9794	0.9923
MobileNet_v1	TR	0.9817	0.9715	0.9732	0.9851	0.9831	0.9879	0.9804	0.9833	~20
	TE	0.9139	0.8737	0.9204	0.9408	0.9671	0.9554	0.9285	0.9490

Table 3. Network results on train dataset (TR) and test dataset (TE)

Backbone network	Original mAP	Status	mAP under different background types
Backbone network	Original mAP	Status	Pure color	Texture	Garbage
Res101	1.0	Before re-training	0.9913	0.9222	0.9050
		After re-training	1.0	1.0	1.0
VGG-16	1.0	Before re-training	0.9901	0.8835	0.6494
		After re-training	1.0	1.0	1.0
MobileNet_v1	0.9917	Before re-training	0.9691	0.7433	0.4204
		After re-training	0.9999	0.9933	0.9793

Table 4. Test results on background dataset

Backbone network(P₁,P₂)	Parameter	Recyclable garbage				Hazardous garbage
Backbone network(P₁,P₂)	Parameter	Metal	Plastic	Carton	Mean	Battery	Pill	Bulb	Mean
Res101(0.76, 0.24)	Precision	0.9796	0.9662	0.9834	0.9764	0.9497	0.9792	0.9698	0.9662
	Recall	0.9889	0.9778	0.9834	0.9834	0.9799	0.9714	0.9887	0.9800
VGG-16(0.62, 0.38)	Precision	0.9583	0.9487	0.9775	0.9615	0.9657	0.9658	0.9534	0.9491
	Recall	0.9857	0.9795	0.9876	0.9843	0.9899	0.9873	0.9951	0.9908
MobileNet_v1(0.56, 0.44)	Precision	0.8943	0.9235	0.9109	0.9096	0.9266	0.9636	0.8867	0.9256
	Recall	0.9609	0.9322	0.9654	0.9528	0.9728	0.9739	0.9854	0.9774

Table 5. Precision and recall on test dataset under optimal threshold of each network

Canhua Wen, Jia Li, Xue Dong. Intelligent Domestic Garbage Recognition Based on Faster RCNN[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201014

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information