OLFWMOT: Orthogonalized Layer Features with Wavelet for Multi-Object Tracking


Video not available.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Benchmark:

MOT17 | MOT20 |

Short name:

OLFWMOT

Detector:

Public

Description:

we proposes leveraging wavelet decomposition to segregate target features of distinct frequency tiers. Features obtained from two-dimensional wavelet decomposition exhibit orthogonality and complementarity along the horizontal and vertical directions. Low-frequency components typically pertain to occluded targets, while high-frequency energy often emanates from targets undergoing occlusion, enabling discrimination between multi-layered objectives. Furthermore, advancing with local attention enhanced GRU learning mechanism for refactor features and further discriminating similar targets, increasing response energy in specific regions.

Reference:

Last submitted:

September 10, 2023 (7 months ago)

Published:

March 12, 2024 at 13:56:28 CET

Submissions:

1

Project page / code:

n/a

Open source:

No

Hardware:

1400MHz, 1 Core.

Runtime:

74.7 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT1770.370.956.3816 (34.6)459 (19.5)28,284136,61475.893.856.156.763.072.761.576.281.91.62,832 (0.0)9,093 (0.0)

Detailed performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT17-01-DPM55.954.944.2872132,57560.194.843.845.148.670.248.075.781.00.556173
MOT17-01-FRCNN55.954.944.2872132,57560.194.843.845.148.670.248.075.781.00.556173
MOT17-01-SDP55.954.944.2872132,57560.194.843.845.148.670.248.075.781.00.556173
MOT17-03-DPM87.582.365.813105,3737,54892.894.862.169.969.475.076.277.882.63.6191753
MOT17-03-FRCNN87.582.365.813105,3737,54892.894.862.169.969.475.076.277.882.63.6191753
MOT17-03-SDP87.582.365.813105,3737,54892.894.862.169.969.475.076.277.882.63.6191753
MOT17-06-DPM60.862.247.162485093,94766.593.947.048.055.467.951.672.879.10.4165369
MOT17-06-FRCNN60.862.247.162485093,94766.593.947.048.055.467.951.672.879.10.4165369
MOT17-06-SDP60.862.247.162485093,94766.593.947.048.055.467.951.672.879.10.4165369
MOT17-07-DPM53.350.741.51381,3316,37662.388.839.044.943.463.549.871.080.62.7174547
MOT17-07-FRCNN53.350.741.51381,3316,37662.388.839.044.943.463.549.871.080.62.7174547
MOT17-07-SDP53.350.741.51381,3316,37662.388.839.044.943.463.549.871.080.62.7174547
MOT17-08-DPM37.641.234.0152236612,64640.195.937.331.443.365.332.677.981.80.6171434
MOT17-08-FRCNN37.641.234.0152236612,64640.195.937.331.443.365.332.677.981.80.6171434
MOT17-08-SDP37.641.234.0152236612,64640.195.937.331.443.365.332.677.981.80.6171434
MOT17-12-DPM57.163.550.022244853,20663.091.852.947.663.271.051.775.382.70.529162
MOT17-12-FRCNN57.163.550.022244853,20663.091.852.947.663.271.051.775.382.70.529162
MOT17-12-SDP57.163.550.022244853,20663.091.852.947.663.271.051.775.382.70.529162
MOT17-14-DPM42.955.838.121441,1519,24050.088.942.334.845.871.238.067.678.41.5158593
MOT17-14-FRCNN42.955.838.121441,1519,24050.088.942.334.845.871.238.067.678.41.5158593
MOT17-14-SDP42.955.838.121441,1519,24050.088.942.334.845.871.238.067.678.41.5158593

Raw data:


OLFWMOT