MOT challenge: KITTI data to MOT data convertion

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

• Hardware Platform (Jetson / GPU) jetson Nano 4gb
• DeepStream Version 5.1
• JetPack Version (valid for Jetson only) 4
5.1

Am working on measuring the MOTA MOTP and id switches using MOT challenge. I have enabled in deepstream-app config file “kitti-track-output-dir”.

I receive many. txt files containing following information of this format
Person 1 8348953480534.0 0 0.0 90.000000 208.125000 372.000000 469.687500 1589998464.000000 0.0 0.0 0.0 0.0 0.0 0.0

For measuring metrics, MOT challenge requires format of each line must contain 10 values:

, , , , , , , , , The world coordinates x,y,z are ignored for the 2D challenge and can be filled with -1. However, each line is still required to contain 10 values.

All frame numbers, target IDs and bounding boxes are 1-based. Here is an example:

Tracking with bounding boxes
(MOT15, MOT16, MOT17, MOT20)
1, 3, 794.27, 247.59, 71.245, 174.88, -1, -1, -1, -1
1, 6, 1648.1, 119.61, 66.504, 163.24, -1, -1, -1, -1
1, 8, 875.49, 399.98, 95.303, 233.93, -1, -1, -1, -1
…

Anyone can give me clue how I can convert it?

5

Hi,
kitti output for tracking is in this format,
fprintf (bbox_params_dump_file,
“%s %lu 0.0 0 0.0 %f %f %f %f 0.0 0.0 0.0 0.0 0.0 0.0 0.0 %f\n”,
obj->obj_label, id, left, top, right, bottom, confidence);
as for MOT required format, you need to figure out what each value means for the 10 values in each line. then we can see if enough of these values and how to get converted from the kitti output for tracking.

6

I am trying to understand what format my tracker output should be:

in 1. its confusing for me, conf and what is det.txt and in 2. here conf value is -1.

my question, in my tracker output do i print conf as -1 ? and what does this following statement mean? “The conf value contains the detection confidence in the det.txt files.” i am aware that my detector can produce txt files with confidence value. so, does it mean in the tracker output i don’t print conf value and make it -1 and let my detector print conf value?

1.
frame, id, bb_left, bb_top, bb_width, bb_height, conf, x, y, z
The conf value contains the detection confidence in the det.txt files.For the ground truth, it acts as a flag whether the entry is to be considered. A value of 0 means that this particular instance is ignored in the evaluation, while any other value can be used to mark it as active.

2.
Tracking with bounding boxes
(MOT15, MOT16, MOT17, MOT20)
1, 3, 794.27, 247.59, 71.245, 174.88, -1, -1, -1, -1
1, 6, 1648.1, 119.61, 66.504, 163.24, -1, -1, -1, -1
1, 8, 875.49, 399.98, 95.303, 233.93, -1, -1, -1, -1
…

7

gfloat confidence

Holds a confidence value for the object, set by the inference component.

confidence will be set to -0.1, if “Group Rectangles” mode of clustering is chosen since the algorithm does not preserve confidence values. Also, for objects found by tracker and not inference component, confidence will be set to -0.1

gfloat tracker_confidence

Holds a confidence value for the object set by nvdcf_tracker.

tracker_confidence will be set to -0.1 for KLT and IOU tracker
If the tracker algorithm does not generate confidence value, then tracker confidence value will be set to -0.1 for tracked objects. For KLT and IOU tracker tracker_confidence is set to -0.1 as these algorithms do not generate confidence values for tracked objects. Nvdcf tracker generates confidence for the tracked objects, and its value is set in tracker_confidence field in NvDsObjectMeta structure
https://docs.nvidia.com/metropolis/deepstream/sdk-api/Meta/_NvDsObjectMeta.html