Object Detection Algorithm Based on Improved Faster R-CNN

Bing Zhou; Runxin Li; Zhenhong Shang; Xiaowu Li

doi:10.3788/LOP57.101009

Journals >Laser & Optoelectronics Progress >Volume 57 >Issue 10 >Page 101009 > Article

Laser & Optoelectronics Progress
Vol. 57, Issue 10, 101009 (2020)

Object Detection Algorithm Based on Improved Faster R-CNN

Bing Zhou, Runxin Li^*, Zhenhong Shang, and Xiaowu Li

Author Affiliations

Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan 650500, China

show less

DOI: 10.3788/LOP57.101009 Cite this Article Set citation alerts

Bing Zhou, Runxin Li, Zhenhong Shang, Xiaowu Li. Object Detection Algorithm Based on Improved Faster R-CNN[J]. Laser & Optoelectronics Progress, 2020, 57(10): 101009 Copy Citation Text

show less

Fig. 1. Structure of Faster R-CNN algorithm

Download full size

Fig. 2. Region proposal network

Download full size

Fig. 3. Problem with ROI pooling

Download full size

Fig. 4. Problem with non-maximum suppression algorithm

Download full size

Fig. 5. Detection results with normal conditions. (a) Faster R-CNN; (b) add Soft-NMS+crop_and_resize; (c) add data enhancement; (d) our algorithm

Download full size

Fig. 6. Detection results with grayscale image. (a) Faster R-CNN; (b) add Soft-NMS+crop_and_resize; (c) add data enhancement; (d) our algorithm

Download full size

Fig. 7. Detection results with multiple targets overlapping. (a) Faster R-CNN; (b) add Soft-NMS+crop_and_resize; (c) add data enhancement; (d) our algorithm

Download full size

Algorithm	Backbone	Training set	Testing set	mAP /%
Fast R-CNN	VGG-16	VOC2007	VOC2007	66.90
Faster R-CNN	VGG-16	VOC2007	VOC2007	69.90
SSD300	VGG-16	VOC2007	VOC2007	68.00
YOLO	GoogleNet	VOC2007	VOC2007	63.40
Data enhancement	VGG-16	VOC2007	VOC2007	70.90
Soft-NMS+crop_and_resize	VGG-16	VOC07++	VOC2007	73.10
Ours	VGG-16	VOC07++	VOC2007	76.40

Table 1. Test results on the PASCAL VOC2007

Enter size	Backbone	Training set	Testing set	mAP /%
128²,256²,521²	VGG-16	VOC07++	VOC2007	76.40
64²,128²,256²,521²	VGG-16	VOC07++	VOC2007	77.69
32²,64²,128²,256²,521²	VGG-16	VOC07++	VOC2007	77.63

Table 2. Detection results on PASCAL VOC07 ++ data set at different scales

Algorithm	Backbone	Training set	Testing set	mAP /%
Fast R-CNN	VGG-16	VOC07+12	VOC2007	70.00
Faster R-CNN	VGG-16	VOC07+12	VOC2007	73.20
Faster R-CNN	ResNet-101	VOC07+12	VOC2007	76.40
MR-CNN	ResNet-101	VOC07+12	VOC2007	78.20
ION	VGG-16	VOC07+12	VOC2007	76.50
YOLO	GoogleNet	VOC07+12	VOC2007	63.40
YOLOV2	Darknet-19	VOC07+12	VOC2007	78.60
SSD300	VGG-16	VOC07+12	VOC2007	77.20
Data enhancement	VGG-16	VOC07+12	VOC2007	75.80
Soft-NMS+crop_and_resize	VGG-16	VOC07+++12	VOC2007	78.40
Ours	VGG-16	VOC07+++12	VOC2007	81.20

Table 3. Test results on PASCAL VOC07+12 test set

Enter size	Backbone	Training set	Testing set	mAP /%
128²,256²,521²	VGG-16	VOC07+++12	VOC2007	81.22
64²,128²,256²,521²	VGG-16	VOC07+++12	VOC2007	83.00
32²,64²,128²,256²,521²	VGG-16	VOC07+++12	VOC2007	82.94

Table 4. Detection results on PASCAL VOC07+++12 at different scales

Algorithm	Training set	IOU			Image size
Algorithm	Training set	0.50∶0.95	0.50	0.75	S	M	L
Fast R-CNN	train	19.70	35.90	-	-	-	-
Faster R-CNN	train	20.50	39.90	19.40	4.10	20.00	35.80
Faster R-CNN	train	21.90	42.70	-	-	-	-
ION^[18]	train	23.60	43.20	23.60	6.40	24.10	38.30
Faster R-CNN	trainval35	24.20	45.30	23.50	7.70	26.40	37.10
SSD300	trainval35	23.20	41.20	23.40	5.30	23.20	39.60
SSD512	trainval35	26.80	46.50	27.80	9.00	28.90	41.90
YOLOV2^[19]	trainval35	21.60	44.00	19.20	5.00	22.40	35.50
Ours	trainval35	26.60	47.20	27.00	11.40	30.80	37.10

Table 5. mAP of different algorithms on COCO2014unit:%

Algorithm	Training set	Number of iterations			Image size
Algorithm	Training set	1	10	100	S	M	L
Faster R-CNN	train	21.30	29.50	30.10	7.30	32.10	52.00
ION	train	23.20	32.70	33.50	10.10	37.70	53.60
Faster R-CNN	trainval35	23.80	34.00	34.60	12.00	38.50	54.40
SSD300	trainval35	22.50	33.20	35.30	9.60	37.60	56.50
SSD512	trainval35	24.80	37.50	39.80	14.00	43.50	59.00
YOLOV2	trainval35	20.70	31.60	33.30	9.80	36.50	54.40
Ours	trainval35	25.50	38.30	39.30	19.70	45.50	55.40

Table 6. mAR of different algorithms on COCO2014unit:%

Bing Zhou, Runxin Li, Zhenhong Shang, Xiaowu Li. Object Detection Algorithm Based on Improved Faster R-CNN[J]. Laser & Optoelectronics Progress, 2020, 57(10): 101009

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information