Real-Time and Anti-Occlusion Visual Tracking Algorithm Based on Multi-Layer Deep Convolutional Features

Zhoujuan Cui; Junshe An; Tianshu Cui

doi:10.3788/AOS201939.0715002

Acta Optica Sinica, Volume. 39, Issue 7, 0715002(2019)

Real-Time and Anti-Occlusion Visual Tracking Algorithm Based on Multi-Layer Deep Convolutional Features

Zhoujuan Cui^1,2、*, Junshe An¹, and Tianshu Cui^1,2

¹ Key Laboratory of Electronics and Information Technology for Space Systems, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, China

² University of Chinese Academy of Sciences, Beijing 100049, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(15)

Fig. 1. Framework of the proposed visual tracking algorithm

Download full size

Fig. 2. Network structure of VGG-Net-19_OT

Download full size

Fig. 3. [in Chinese]

Download full size

Fig. 4. Qualitative results of the 10 tracking algorithms on different video sequences. (a) Ironman 1; (b) Ironman 2; (c) Doll; (d) MotorRolling; (e) Bolt2; (f) Skiing

Download full size

Fig. 5. Qualitative results of the 10 tracking algorithms on different occluded video sequences. (a) Jogging-1; (b) Walking2; (c) Coke; (d) Soccer

Download full size

Fig. 6. Algorithm of OPE on OTB-2015. (a) Precision plot; (b) overlap success plot

Download full size

Fig. 7. Algorithm of OPE on UAV123. (a) Precision plot; (b) overlap success plot

Download full size

Fig. 8. Precision plots on 11 different attributes video sequences of OTB-2015

Download full size

Fig. 9. Success plots on 11 different attributes video sequences of OTB-2015

Download full size

Table 1. Parameters of VGG-Net-19

View table

Table 1. Parameters of VGG-Net-19

Structure	Filter	Output size /(pixel×pixel×pixel)	Memory /bit	Parameter
Image input		224×224×3	224×224×3=150528	0
Conv1_1Conv1_2	6464	224×224×64224×224×64	224×224×64=3211264224×224×64=3211264	3×3×3×64=17283×3×64×64=36864
POOL1		112×112×64	112×112×64=802816	0
Conv2_1Conv2_2	128128	112×112×128112×112×128	112×112×128=1605632112×112×128=1605632	3×3×64×128=737283×3×128×128=147456
POOL2		56×56×128	56×56×128=401408	0
Conv3_1Conv3_2Conv3_3Conv3_4	256256256256	56×56×25656×56×25656×56×25656×56×256	56×56×256=80281656×56×256=80281656×56×256=80281656×56×256=802816	3×3×128×256=2949123×3×256×256=5898243×3×256×256=5898243×3×256×256=589824
POOL3		28×28×256	28×28×256=200704	0
Conv4_1Conv4_2Conv4_3Conv4_4	512512512512	28×28×51228×28×51228×28×51228×28×512	28×28×512=40140828×28×512=40140828×28×512=40140828×28×512=401408	3×3×256×512=11796483×3×512×512=23592963×3×512×512=23592963×3×512×512=2359296
POOL4		14×14×512	14×14×512=100352	0
Conv5_1Conv5_2Conv5_3Conv5_4	512512512512	14×14×51214×14×51214×14×51214×14×512	14×14×512=10035214×14×512=10035214×14×512=10035214×14×512=100352	3×3×512×512=23592963×3×512×512=23592963×3×512×512=23592963×3×512×512=2359296
POOL5		7×7×512	7×7×512=25088	0
FC6	4096	1×1×4096	1×1×4096=4096	7×7×512×4096=102760448
FC7	4096	1×1×4096	1×1×4096=4096	4096×4096=16777216
FC8	1000	1×1×1000	1×1×1000=1000	4096×1000=4096000

Table 2. Video attributes of OTB-2015

View table

Table 2. Video attributes of OTB-2015

Video attribute	Value	Video attribute	Value
Background clutters (BC)	31	Motion blur (MB)	29
Deformation	44	Occlusion	49
Fast motion (FM)	39	Out-of-plane rotation (OPR)	63
Illumination variation (IV)	38	Out-of-view (OV)	14
In-plane rotation (IPR)	51	Scale variation (SV)	64
Low resolution (LR)	9

Table 3. Video attributes of UAV123

View table

Table 3. Video attributes of UAV123

Video attribute	Value	Video attribute	Value
Scale variation (SV)	109	Out of view (OV)	30
Aspect ratio change (ARC)	68	Background clutter (BC)	21
Low resolution (LR)	48	Illumination variation (IV)	31
Fast motion (FM)	28	Viewpoint change (VC)	60
Full occlusion (FOC)	33	Camera motion (CM)	70
Partial occlusion (POC)	73	Similar object (SOB)	39

Table 4. Precision values and success rates on 12 different attributes video sequences of UAV123

View table

Table 4. Precision values and success rates on 12 different attributes video sequences of UAV123

Sequence	Proposed algorithm		KCF		HCFTstar
Sequence	Precision value	Success rate	Precision value	Success rate	Precision value	Success rate
Aspect ratio change (ARC)	0.619	0.464	0.447	0.292	0.610	0.434
Background clutter (BC)	0.585	0.447	0.536	0.413	0.584	0.470
Camera motion (CM)	0.677	0.556	0.502	0.366	0.682	0.543
Fast motion (FM)	0.544	0.402	0.301	0.200	0.516	0.377
Full occlusion (FOC)	0.567	0.358	0.420	0.243	0.561	0.381
Illumination variation (IV)	0.627	0.506	0.464	0.334	0.614	0.451
Low resolution (LR)	0.555	0.333	0.435	0.251	0.579	0.346
Out of view (OV)	0.609	0.500	0.406	0.277	0.603	0.467
Partial occlusion (POC)	0.632	0.499	0.497	0.365	0.628	0.491
Scale variation (SV)	0.644	0.534	0.497	0.339	0.646	0.498
Similar object (SOB)	0.691	0.566	0.616	0.418	0.693	0.552
Viewpoint change (VC)	0.637	0.494	0.450	0.302	0.625	0.440

Table 5. Tracking speedsframe /s
View table
Table 5. Tracking speedsframe /s
Sequence Basketball FaceOcc1 Football1 Girl Jogging1 Jumping Soccer Sylvester Trellis
Speed 31.3 34.5 26.1 35.9 28.2 26.1 25.1 32.6 27.9

Table 6. Average tracking speed comparison for the deep learning-based tracking algorithmframe /s
View table
Table 6. Average tracking speed comparison for the deep learning-based tracking algorithmframe /s
Algorithm Proposed FCNT MDNet HCFT
Tracking speed 29.6 3 1 10

Tools

Get Citation

Copy Citation Text

Zhoujuan Cui, Junshe An, Tianshu Cui. Real-Time and Anti-Occlusion Visual Tracking Algorithm Based on Multi-Layer Deep Convolutional Features[J]. Acta Optica Sinica, 2019, 39(7): 0715002

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites