MOT Challenge

HISP_DAL: Robust Online Multi-target Visual Tracking using a HISP Filter with Discriminative Deep Appearance Learning

MOT16-01

MOT16-01

MOT16-03

MOT16-06

MOT16-07

MOT16-08

MOT16-12

MOT16-14

Benchmark:

MOT16 |

Short name:

HISP_DAL

Detector:

Public

Description:

n/a

Reference:

N. Baisa. Robust online multi-target visual tracking using a HISP filter with discriminative deep appearance learning. In Journal of Visual Communication and Image Representation, 2021.

Last submitted:

July 09, 2019 (2 years ago)

Published:

July 27, 2019 at 15:09:33 CET

Submissions:

2

Project page / code:

n/a

Open source:

No

Hardware:

3 GHZ, 1 Core

Runtime:

3.3 Hz

Benchmark performance:

Sequence	MOTA	IDF1	HOTA	MT	ML	FP	FN	Rcll	Prcn	AssA	DetA	AssRe	AssPr	DetRe	DetPr	LocA	FAF	ID Sw.	Frag
MOT16	37.4	30.5	25.7	58 (7.6)	386 (50.9)	3,222	108,865	40.3	95.8	21.9	30.4	22.7	78.7	31.6	75.1	79.6	0.5	2,101 (52.1)	2,151 (53.4)

Detailed performance:

Sequence	MOTA	IDF1	HOTA	MT	ML	FP	FN	Rcll	Prcn	AssA	DetA	AssRe	AssPr	DetRe	DetPr	LocA	FAF	ID Sw.	Frag
MOT16-01	24.1	25.4	21.0	2	13	57	4,748	25.8	96.7	23.3	19.0	24.1	76.3	19.4	72.9	77.5	0.1	51	68
MOT16-03	44.2	32.0	27.1	17	41	1,190	56,211	46.2	97.6	21.2	34.9	21.8	80.1	36.2	76.4	79.8	0.8	925	1,150
MOT16-06	40.1	42.8	32.6	16	115	299	6,408	44.5	94.5	33.2	32.3	35.3	74.9	33.8	71.9	77.7	0.3	209	183
MOT16-07	32.1	27.4	22.7	4	26	417	10,381	36.4	93.4	19.3	27.2	19.9	73.9	28.2	72.4	78.1	0.8	279	278
MOT16-08	27.5	23.9	21.7	5	29	481	11,385	32.0	91.8	18.6	25.4	19.6	78.4	26.4	75.8	82.0	0.8	267	172
MOT16-12	34.2	33.7	28.1	9	44	487	4,773	42.5	87.9	25.2	31.6	26.3	76.4	34.0	70.3	80.2	0.5	200	104
MOT16-14	16.6	21.1	17.2	5	118	291	14,959	19.1	92.4	20.7	14.4	21.6	74.9	14.8	71.7	78.6	0.4	170	196

Raw data:

HISP_DAL