Underwater Object Detection Algorithm Based on Improved CenterNet

Rongrong Wang; Zhongyun Jiang

doi:10.3788/LOP212230

Journals >Laser & Optoelectronics Progress >Volume 60 >Issue 2 >Page 0215001 > Article

Laser & Optoelectronics Progress
Vol. 60, Issue 2, 0215001 (2023)

Underwater Object Detection Algorithm Based on Improved CenterNet

Rongrong Wang¹ and Zhongyun Jiang^2,*

Author Affiliations

¹College of Information, Shanghai Ocean University, Shanghai 201306, China

²College of Information Technology, Shanghai Jian Qiao University, Shanghai 201306, China

show less

DOI: 10.3788/LOP212230 Cite this Article Set citation alerts

Rongrong Wang, Zhongyun Jiang. Underwater Object Detection Algorithm Based on Improved CenterNet[J]. Laser & Optoelectronics Progress, 2023, 60(2): 0215001 Copy Citation Text

show less

Fig. 1. Model structure. (a) HRNet; (b) BAM; (c) FFM; (d) detection module

Download full size

Fig. 2. HRNet structure

Download full size

Fig. 3. BAM structure

Download full size

Fig. 4. Feature fusion model

Download full size

Fig. 5. RFB model

Download full size

Fig. 6. Example images. (a) Scallop; (b) holothurian; (c) starfish; (d) echinus

Download full size

Fig. 7. Sample distribution

Download full size

Fig. 8. Comparison of detection results of different networks. (a) (c) (e) (g) CenterNet algorithm; (b) (d) (f) (h) proposed algorithm

Download full size

Fig. 9. Detection accuracy of different categories

Download full size

Net	Stage 1	Stage 2	Stage 3	Stage 4	Resolution
Subnet_1	$[\begin{array}{l} 1 \times 1,64 \\ 3 \times 3,64 \\ 1 \times 1,256 \end{array}] \times 4 \times 1$	$[\begin{array}{l} 3 \times 3,32 \\ 3 \times 3,32 \end{array}] \times 4 \times 1$	$[\begin{array}{l} 3 \times 3,32 \\ 3 \times 3,32 \end{array}] \times 4 \times 4$	$[\begin{array}{l} 3 \times 3,32 \\ 3 \times 3,32 \end{array}] \times 4 \times 3$	4×
Subnet_2		$[\begin{array}{l} 3 \times 3,64 \\ 3 \times 3,64 \end{array}] \times 4 \times 1$	$[\begin{array}{l} 3 \times 3,64 \\ 3 \times 3,64 \end{array}] \times 4 \times 4$	$[\begin{array}{l} 3 \times 3,64 \\ 3 \times 3,64 \end{array}] \times 4 \times 3$	8×
Subnet_3			$[\begin{array}{l} 3 \times 3,128 \\ 3 \times 3,128 \end{array}] \times 4 \times 4$	$[\begin{array}{l} 3 \times 3,128 \\ 3 \times 3,128 \end{array}] \times 4 \times 3$	16×
Subnet_4				$[\begin{array}{l} 3 \times 3,256 \\ 3 \times 3,256 \end{array}] \times 4 \times 3$	32×

Table 1. Backbone network structure parameters

Algorithm	Bacbone nework	Size	GPU	mAP /%	FPS
Fast R-CNN	VGG-16	~1000×600	Tian X	70.0	0.5
Reference ［21］	ResNet-50		RTX 2080Ti	72.6
Faster R-CNN	ResNet-101	~1000×600	Tian X	76.4	5.0
SSD300	VGG-16	300×300	Tian X	77.1	45
SSD	VGG-16	320×320	Tian X	77.5	11.2
YOLOv3	Darknet-53	554×554	Tian X	79.3	26.0
RetinaNet	ResNet-101	~1000×600	RTX2080 S	75.3	8.8
Proposed algorithm	FA-HRNet	384×384	RTX2080 S	78.1	7.0
Proposed algorithm	FA-HRNet	512×512	RTX2080 S	79.5	6.7

Table 2. PASCAL VOC dataset test results

Algorithm	Net	Scallop /%	Holothurian /%	Starfish /%	Echinus /%	mAP /%	FPS
CenterNet	Hourglass-104	57.4	71.8	86.0	88.5	75.9	5.2
Proposed algorithm	FA-HRNet	60.2	73.3	85.6	89.7	77.4	7.0

Table 3. Comparison of detection accuracy and speed with CenterNet algorithm

Algorithm	Net	Ipout size	Size /MB	Params /MB	GFLOPs /10⁹
CenterNet	Hourglass-104	384×384	765.7	191.2	164.5
Proposed algorithm	FA-HRNet	384×384	123.0	30.4	32.6

Table 4. Comparison of model complexity with CenterNet algorithm

Algorithm	Bacbone nework	Size /MB	Params /MB	GFLOPs /10⁹	mAP /%	FPS
Faster R-CNN	ResNet-101+FPN	552.8	59.5	91.8	73.7	3.5
Reference ［22］	ResNet-50				72.6
SSD	VGG-16	92.61	24.2	30.6	68.6	16.0
YOLOv3	Darknet-53	246.5	61.5	32.8	73.3	15.0
RetinaNet	ResNet-101	228.5	55.2	100.6	72.2	8.8
CornerNet	Hourglass-104	804.6	201.0	453.0	49.0	3.1
ExtremeNet	Hourglass-104	794.1	198.3	229.9	53.5	2.3
CenterNet	Hourglass-104	765.7	191.2	164.5	75.9	5.2
Proposed algorithm	FA-HRNet	123.0	30.4	32.6	77.4	7.0

Table 5. Performance comparison with mainstream object detection algorithms

No.	HRNet	BAM	FFM	Size /MB	Params /MB	GFLOPs /10⁹	mAP /%	FPS
1	—	—	—	765.7	191.24	164.53	75.9	5.2
2	√	—	—	115.2	28.67	24.16	74.7	8.2
3	√	√	—	115.6	28.74	24.17	76.2	7.9
4	√	√	√	123.0	30.36	32.55	77.4	7.0

Table 6. Influence of different modules on detection performance

Rongrong Wang, Zhongyun Jiang. Underwater Object Detection Algorithm Based on Improved CenterNet[J]. Laser & Optoelectronics Progress, 2023, 60(2): 0215001

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