MOT17Det Results

Click on a measure to sort the table accordingly. See below for a more detailed description.


DetectorAPMODAMODPFAFTPFPFNPrecisionRecall
UNV_Det
1.
0.89
81.979.02.1106,47812,7048,08689.392.9
Anonymous submission
PA_Det_NJ
2.
0.89
82.179.32.4108,48014,4176,08488.394.7
PA_TECH_NJ
YTLAB
3.
0.89
76.780.22.8104,55516,68510,00986.291.3
Z. Cai, Q. Fan, R. Feris, N. Vasconcelos. A unified multi-scale deep convolutional neural network for fast object detection. In European Conference on Computer Vision, 2016.
KDNT
4.
0.89
67.180.14.8105,47328,6239,09178.792.1
F. Yu, W. Li, Q. Li, Y. Liu, X. Shi, J. Yan. POI: Multiple Object Tracking with High Performance Detection and Appearance Feature. In BMTT, SenseTime Group Limited, 2016.
meow_det
5.
0.88
-41.478.425.9105,644153,1308,92040.892.2
Anonymous submission
meow_det2
6.
0.87
-105.678.138.4106,378227,3898,18631.992.9
Anonymous submission
HRCN
7.
0.87
-53.678.528.2105,551166,9689,01338.792.1
Anonymous submission
HRCNdet
8.
0.86
-39.278.625.3104,927149,8849,63741.291.6
Anonymous submission
PA_MOT_Det
9.
0.86
83.479.22.2108,58113,0715,98389.394.8
Anonymous submission
ZIZOM
10.
0.81
72.079.82.295,41412,99019,13988.083.3
C. Lin, L. Jiwen, G. Wang, J. Zhou. Graininess-Aware Deep Feature Learning for Pedestrian Detection. In ECCV, 2018.
DetectorAPMODAMODPFAFTPFPFNPrecisionRecall
SDP
11.
0.81
76.978.01.395,6997,59918,86592.683.5
F. Yang, W. Choi, Y. Lin. Exploit All the Layers: Fast and Accurate CNN Object Detector With Scale Dependent Pooling and Cascaded Rejection Classifiers. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
XYZvX
12.
0.81
74.479.42.7101,19715,93013,36786.488.3
Anonymous submission
hbv20
13.
0.80
70.578.52.897,00016,28517,56485.684.7
Anonymous submission
HBv20Rep
14.
0.80
69.178.13.297,94818,83016,61683.985.5
Anonymous submission
XYZvN
15.
0.80
69.378.52.594,44115,03720,12386.382.4
Anonymous submission
ViPeD
16.
0.80
75.474.11.896,88410,48917,68090.284.6
Anonymous submission
HumanBoxes
17.
0.79
58.077.34.995,65829,18618,90676.683.5
Anonymous submission
RTFCP
18.
0.76
-64.476.528.896,504170,27518,06036.284.2
Anonymous submission
Strong_SSD
19.
0.72
53.477.04.990,03628,85424,52875.778.6
Anonymous submission
FRCNN
20.
0.72
68.578.01.788,60110,08125,96389.877.3
S. Ren, K. He, R. Girshick, J. Sun. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In NIPS, 2015.
DetectorAPMODAMODPFAFTPFPFNPrecisionRecall
YOLO_Virt
21.
0.71
63.970.52.286,42913,25428,13586.775.4
Anonymous submission
yolov3_ft
22.
0.70
60.271.82.382,76713,80931,79785.772.2
Anonymous submission
Cas_CH_17
23.
0.65
51.580.05.189,43630,40425,11774.678.1
Anonymous submission
DPM
24.
0.61
31.275.87.178,00742,30836,55764.868.1
P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan. Object Detection with Discriminatively Trained Part Based Models. In TPAMI, 2010.
YOLOv3_XYZ
25.
0.60
37.573.15.877,18234,26737,38269.367.4
Anonymous submission
VIS_DET1
26.
0.54
58.679.80.670,6183,51643,93595.361.6
Anonymous submission
MHD
27.
0.49
11.269.98.864,63751,80149,92755.556.4
Mobilenet-based Human Detection
YLHDv2
28.
0.46
56.973.22.580,09314,93834,47184.369.9
https://arxiv.org/abs/1612.08242
HDGP
29.
0.45
42.176.41.355,6807,43658,88488.248.6
A. Garcia-Martin, R. Sanchez-Matilla, J. Martinez. Hierarchical detection of persons in groups. In Signal, Image and Video Processing, 2017.
VDet
30.
0.44
44.775.71.056,9805,76557,58490.849.7
Vitrociset Detection Algorithm
DetectorAPMODAMODPFAFTPFPFNPrecisionRecall
muDetect
31.
0.43
42.076.81.355,9527,83458,61287.748.8
Anonymous submission
muDetectV2
32.
0.39
38.476.82.558,66414,63655,90080.051.2
Anonymous submission
muDetectV3
33.
0.37
31.375.43.757,97222,08556,59272.450.6
Anonymous submission
ACF
34.
0.32
18.172.12.837,31216,53977,25269.332.6
P. Dollar, R. Appel, S. Belongie, P. Perona. Fast Feature Pyramids for Object Detection. In TPAMI, 2014.
cn
35.
0.00
-97.062.518.9891112,039113,6730.80.8
Anonymous submission
XYZv3
36.
0.00
-67.278.311.58768,309101,3650.10.1
Anonymous submission

Benchmark Statistics

SequencesFramesBoxes
75919188076

Evaluation Measures

Lower is better. Higher is better.
Measure Better Perfect Description
AP higher 100 % Average Precision taken over a set of reference recall values (0:0.1:1)
MODA higher 100 % Multiple Object Detection Accuracy [1]. This measure combines false positives and missed targets.
MOTP higher 100 % Multiple Object Detection Precision [1]. The misalignment between the annotated and the predicted bounding boxes.
FAF lower 0 The average number of false alarms per frame.
TP higher #GT The total number of true positives.
FP lower 0 The total number of false positives.
FN lower 0 The total number of false negatives (missed targets).
Precision higher 100 % Ratio of TP / (TP+FP).
Recall higher 100 % Ratio of correct detections to total number of GT boxes.

Legend

Symbol Description
new This entry has been submitted or updated less than a week ago.

References:


[1] Stiefelhagen, R., Bernardin, K., Bowers, R., Garofolo, J.S., Mostefa, D. & Soundararajan, P. The CLEAR 2006 Evaluation. In CLEAR, 2006.